diff --git a/model_zoo/official/cv/FCN8s/README.md b/model_zoo/official/cv/FCN8s/README.md index 40cfb0dbcc9..01d9ab9e6d7 100755 --- a/model_zoo/official/cv/FCN8s/README.md +++ b/model_zoo/official/cv/FCN8s/README.md @@ -1,6 +1,7 @@ # Contents -- [FCN 介绍](#FCN-介绍) +- [Contents](#contents) +- [FCN 介绍](#fcn-介绍) - [模型架构](#模型架构) - [数据集](#数据集) - [环境要求](#环境要求) @@ -8,6 +9,8 @@ - [脚本介绍](#脚本介绍) - [脚本以及简单代码](#脚本以及简单代码) - [脚本参数](#脚本参数) + - [生成数据步骤](#生成数据步骤) + - [训练数据](#训练数据) - [训练步骤](#训练步骤) - [训练](#训练) - [评估步骤](#评估步骤) @@ -17,12 +20,21 @@ - [推理过程](#推理过程) - [推理](#推理) - [模型介绍](#模型介绍) - - [性能](#性能) + - [性能](#性能) - [评估性能](#评估性能) + - [FCN8s on PASCAL VOC 2012](#fcn8s-on-pascal-voc-2012) + - [Inference Performance](#inference-performance) + - [FCN8s on PASCAL VOC](#fcn8s-on-pascal-voc) - [如何使用](#如何使用) - [教程](#教程) +- [Set context](#set-context) +- [Load dataset](#load-dataset) +- [Define model](#define-model) +- [optimizer](#optimizer) +- [loss scale](#loss-scale) +- [callback for saving ckpts](#callback-for-saving-ckpts) - [随机事件介绍](#随机事件介绍) -- [ModelZoo 主页](#ModelZoo-主页) +- [ModelZoo 主页](#modelzoo-主页) # [FCN 介绍](#contents) @@ -405,7 +417,7 @@ python export.py | Model Version | FCN-8s | FCN-8s | | Resource | Ascend 910; CPU 2.60GHz, 192cores; Memory 755G; OS Euler2.8 | NV SMX2 V100-32G | | uploaded Date | 12/30/2020 (month/day/year) | 06/11/2021 (month/day/year) | -| MindSpore Version | 1.1.0-alpha | 1.2.0 | +| MindSpore Version | 1.1.0 | 1.2.0 | | Dataset | PASCAL VOC 2012 and SBD | PASCAL VOC 2012 and SBD | | Training Parameters | epoch=500, steps=330, batch_size = 32, lr=0.015 | epoch=500, steps=330, batch_size = 8, lr=0.005 | | Optimizer | Momentum | Momentum | @@ -424,7 +436,7 @@ python export.py | Model Version | FCN-8s | FCN-8s | Resource | Ascend 910; OS Euler2.8 | NV SMX2 V100-32G | Uploaded Date | 10/29/2020 (month/day/year) | 06/11/2021 (month/day/year) -| MindSpore Version | 1.1.0-alpha | 1.2.0 +| MindSpore Version | 1.1.0 | 1.2.0 | Dataset | PASCAL VOC 2012 | PASCAL VOC 2012 | batch_size | 16 | 16 | outputs | probability | probability diff --git a/model_zoo/official/cv/alexnet/README.md b/model_zoo/official/cv/alexnet/README.md index 0688e620fc9..df91383be38 100644 --- a/model_zoo/official/cv/alexnet/README.md +++ b/model_zoo/official/cv/alexnet/README.md @@ -1,25 +1,27 @@ # Contents -- [AlexNet Description](#alexnet-description) -- [Model Architecture](#model-architecture) -- [Dataset](#dataset) -- [Environment Requirements](#environment-requirements) -- [Quick Start](#quick-start) -- [Script Description](#script-description) - - [Script and Sample Code](#script-and-sample-code) - - [Script Parameters](#script-parameters) - - [Training Process](#training-process) - - [Training](#training) - - [Evaluation Process](#evaluation-process) - - [Evaluation](#evaluation) +- [Contents](#contents) + - [AlexNet Description](#alexnet-description) + - [Model Architecture](#model-architecture) + - [Dataset](#dataset) + - [Environment Requirements](#environment-requirements) + - [Quick Start](#quick-start) + - [Script Description](#script-description) + - [Script and Sample Code](#script-and-sample-code) + - [Script Parameters](#script-parameters) + - [Training Process](#training-process) + - [Training](#training) + - [Evaluation Process](#evaluation-process) + - [Evaluation](#evaluation) - [Inference Process](#inference-process) - [Export MindIR](#export-mindir) - [Infer on Ascend310](#infer-on-ascend310) - [Result](#result) -- [Model Description](#model-description) - - [Performance](#performance) - - [Evaluation Performance](#evaluation-performance) -- [ModelZoo Homepage](#modelzoo-homepage) + - [Model Description](#model-description) + - [Performance](#performance) + - [Evaluation Performance](#evaluation-performance) + - [Description of Random Situation](#description-of-random-situation) + - [ModelZoo Homepage](#modelzoo-homepage) ## [AlexNet Description](#contents) @@ -406,8 +408,8 @@ Inference result is saved in current path, you can find result like this in acc. | Parameters | Ascend | GPU | | -------------------------- | ------------------------------------------------------------| -------------------------------------------------| | Resource | Ascend 910; CPU 2.60GHz, 192cores; Memory 755G; OS Euler2.8 | NV SMX2 V100-32G | -| uploaded Date | 06/09/2020 (month/day/year) | 17/09/2020 (month/day/year) | -| MindSpore Version | 1.0.0 | 0.7.0-beta | +| uploaded Date | 07/05/2021 (month/day/year) | 17/09/2020 (month/day/year) | +| MindSpore Version | 1.2.1 | 1.2.1 | | Dataset | CIFAR-10 | CIFAR-10 | | Training Parameters | epoch=30, steps=1562, batch_size = 32, lr=0.002 | epoch=30, steps=1562, batch_size = 32, lr=0.002 | | Optimizer | Momentum | Momentum | diff --git a/model_zoo/official/cv/alexnet/README_CN.md b/model_zoo/official/cv/alexnet/README_CN.md index ef2ec05b167..9eb865dff06 100644 --- a/model_zoo/official/cv/alexnet/README_CN.md +++ b/model_zoo/official/cv/alexnet/README_CN.md @@ -3,27 +3,27 @@ - [目录](#目录) -- [AlexNet描述](#alexnet描述) -- [模型架构](#模型架构) -- [数据集](#数据集) -- [环境要求](#环境要求) -- [快速入门](#快速入门) -- [脚本说明](#脚本说明) - - [脚本及样例代码](#脚本及样例代码) - - [脚本参数](#脚本参数) - - [训练过程](#训练过程) - - [训练](#训练) - - [评估过程](#评估过程) - - [评估](#评估) + - [AlexNet描述](#alexnet描述) + - [模型架构](#模型架构) + - [数据集](#数据集) + - [环境要求](#环境要求) + - [快速入门](#快速入门) + - [脚本说明](#脚本说明) + - [脚本及样例代码](#脚本及样例代码) + - [脚本参数](#脚本参数) + - [训练过程](#训练过程) + - [训练](#训练) + - [评估过程](#评估过程) + - [评估](#评估) - [推理过程](#推理过程) - - [导出MindIR](#导出MindIR) - - [在Ascend310执行推理](#在Ascend310执行推理) + - [导出MindIR](#导出mindir) + - [在Ascend310执行推理](#在ascend310执行推理) - [结果](#结果) -- [模型描述](#模型描述) - - [性能](#性能) - - [评估性能](#评估性能) -- [随机情况说明](#随机情况说明) -- [ModelZoo主页](#modelzoo主页) + - [模型描述](#模型描述) + - [性能](#性能) + - [评估性能](#评估性能) + - [随机情况说明](#随机情况说明) + - [ModelZoo主页](#modelzoo主页) @@ -332,16 +332,16 @@ bash run_infer_310.sh [MINDIR_PATH] [DATASET_NAME] [DATASET_PATH] [NEED_PREPROCE | 参数 | Ascend | GPU | | -------------------------- | ------------------------------------------------------------| -------------------------------------------------| | 资源 | Ascend 910；CPU 2.60GHz，192核；内存 755G；系统 Euler2.8 | NV SMX2 V100-32G | -| 上传日期 | 2020-09-06 | 2020-09-17 | -| MindSpore版本 | 0.5.0-beta | 0.7.0-beta | +| 上传日期 | 2021-07-05 | 2020-09-17 | +| MindSpore版本 | 1.2.1 | 1.2.1 | | 数据集 | CIFAR-10 | CIFAR-10 | | 训练参数 | epoch=30, step=1562, batch_size=32, lr=0.002 | epoch=30, step=1562, batch_size=32, lr=0.002 | | 优化器 | 动量 | 动量 | | 损失函数 | Softmax交叉熵 | Softmax交叉熵 | | 输出 | 概率 | 概率 | 概率 | | 损失 | 0.0016 | 0.01 | -| 速度 | 21毫秒/步 | 16.8毫秒/步 | -| 总时间 | 17分钟 | 14分钟| +| 速度 | 7毫秒/步 | 16.8毫秒/步 | +| 总时间 | 6分钟 | 14分钟| | 微调检查点 | 445M （.ckpt文件） | 445M （.ckpt文件） | | 脚本 | [AlexNet脚本](https://gitee.com/mindspore/mindspore/tree/master/model_zoo/official/cv/alexnet) | [AlexNet脚本](https://gitee.com/mindspore/mindspore/tree/master/model_zoo/official/cv/alexnet) | diff --git a/model_zoo/official/cv/deeplabv3/README.md b/model_zoo/official/cv/deeplabv3/README.md index 6bd78c34abb..d1e2e3f3291 100644 --- a/model_zoo/official/cv/deeplabv3/README.md +++ b/model_zoo/official/cv/deeplabv3/README.md @@ -1,6 +1,8 @@ # Contents -- [DeepLabV3 Description](#DeepLabV3-description) +- [Contents](#contents) +- [DeepLabV3 Description](#deeplabv3-description) + - [Description](#description) - [Model Architecture](#model-architecture) - [Dataset](#dataset) - [Features](#features) @@ -11,12 +13,26 @@ - [Script and Sample Code](#script-and-sample-code) - [Script Parameters](#script-parameters) - [Training Process](#training-process) + - [Usage](#usage) + - [Running on Ascend](#running-on-ascend) + - [Running on CPU](#running-on-cpu) + - [Result](#result) + - [Running on Ascend](#running-on-ascend-1) + - [Running on CPU](#running-on-cpu-1) + - [Transfer Training](#transfer-training) - [Evaluation Process](#evaluation-process) + - [Usage](#usage-1) + - [Running on Ascend](#running-on-ascend-2) + - [Result](#result-1) + - [Training accuracy](#training-accuracy) - [Export MindIR](#export-mindir) - [Inference Process](#inference-process) + - [Usage](#usage-2) + - [result](#result-2) - [Model Description](#model-description) - [Performance](#performance) - [Evaluation Performance](#evaluation-performance) + - [Inference Performance](#inference-performance) - [Description of Random Situation](#description-of-random-situation) - [ModelZoo Homepage](#modelzoo-homepage) @@ -803,8 +819,8 @@ Inference result is saved in current path, you can find result in acc.log file. | -------------------------- | -------------------------------------- | | Model Version | DeepLabV3 | Resource | Ascend 910; OS Euler2.8 | -| Uploaded Date | 09/04/2020 (month/day/year) | -| MindSpore Version | 0.7.0-alpha | +| Uploaded Date | 07/05/2021 (month/day/year) | +| MindSpore Version | 1.3.0 | | Dataset | PASCAL VOC2012 + SBD | | Training Parameters | epoch = 300, batch_size = 32 (s16_r1)
epoch = 800, batch_size = 16 (s8_r1)
epoch = 300, batch_size = 16 (s8_r2) | | Optimizer | Momentum | @@ -824,8 +840,8 @@ Inference result is saved in current path, you can find result in acc.log file. | ------------------- | --------------------------- | | Model Version | DeepLabV3 V1 | | Resource | Ascend 910; OS Euler2.8 | -| Uploaded Date | 09/04/2020 (month/day/year) | -| MindSpore Version | 0.7.0-alpha | +| Uploaded Date | 07/05/2021 (month/day/year) | +| MindSpore Version | 1.3.0 | | Dataset | VOC datasets | | batch_size | 32 (s16); 16 (s8) | | outputs | probability | diff --git a/model_zoo/official/cv/deeplabv3/README_CN.md b/model_zoo/official/cv/deeplabv3/README_CN.md index 15094b3c8e9..21f85fbdce8 100644 --- a/model_zoo/official/cv/deeplabv3/README_CN.md +++ b/model_zoo/official/cv/deeplabv3/README_CN.md @@ -17,10 +17,14 @@ - [训练过程](#训练过程) - [用法](#用法) - [Ascend处理器环境运行](#ascend处理器环境运行) + - [CPU环境运行](#cpu环境运行) + - [迁移训练](#迁移训练) - [结果](#结果) + - [Ascend处理器环境运行](#ascend处理器环境运行-1) + - [CPU环境运行](#cpu环境运行-1) - [评估过程](#评估过程) - [用法](#用法-1) - - [Ascend处理器环境运行](#ascend处理器环境运行-1) + - [Ascend处理器环境运行](#ascend处理器环境运行-2) - [结果](#结果-1) - [训练准确率](#训练准确率) - [导出mindir模型](#导出mindir模型) @@ -29,7 +33,8 @@ - [结果](#结果-2) - [模型描述](#模型描述) - [性能](#性能) - - [评估性能](#评估性能) + - [训练性能](#训练性能) + - [推理性能](#推理性能) - [随机情况说明](#随机情况说明) - [ModelZoo主页](#modelzoo主页) @@ -815,8 +820,8 @@ bash run_infer_310.sh [MINDIR_PATH] [DATA_PATH] [DATA_ROOT] [DATA_LIST] [DEVICE_ | -------------------------- | -------------------------------------- | | 模型版本 | DeepLabV3 | 资源 | Ascend 910；系统 Euler2.8 | -| 上传日期 | 2020-09-04 | -| MindSpore版本 | 0.7.0-alpha | +| 上传日期 | 2021-07-05 | +| MindSpore版本 | 1.3.0 | | 数据集 | PASCAL VOC2012 + SBD | | 训练参数 | epoch = 300, batch_size = 32 (s16_r1) epoch = 800, batch_size = 16 (s8_r1) epoch = 300, batch_size = 16 (s8_r2) | | 优化器 | Momentum | @@ -833,8 +838,8 @@ bash run_infer_310.sh [MINDIR_PATH] [DATA_PATH] [DATA_ROOT] [DATA_LIST] [DEVICE_ | ------------------- | --------------------------- | | 模型版本 | DeepLabV3 V1 | | 资源 | Ascend 910；系统 Euler2.8 | -| 上传日期 | 2020-09-04 | -| MindSpore 版本 | 0.7.0-alpha | +| 上传日期 | 2020-07-05 | +| MindSpore 版本 | 1.3.0 | | 数据集 | VOC 数据集 | | batch_size | 32 (s16); 16 (s8) | | 输出 | 概率 | diff --git a/model_zoo/official/cv/googlenet/README.md b/model_zoo/official/cv/googlenet/README.md index b93cae220e0..bd47b920471 100644 --- a/model_zoo/official/cv/googlenet/README.md +++ b/model_zoo/official/cv/googlenet/README.md @@ -2,6 +2,7 @@ [查看中文](./README_CN.md) +- [Contents](#contents) - [GoogleNet Description](#googlenet-description) - [Model Architecture](#model-architecture) - [Dataset](#dataset) @@ -14,19 +15,23 @@ - [Script Parameters](#script-parameters) - [Training Process](#training-process) - [Training](#training) - - [Distributed Training](#distributed-training) + - [Distributed Training](#distributed-training) - [Evaluation Process](#evaluation-process) - [Evaluation](#evaluation) - - [Export Process](#Export-process) - - [Export](#Export) - - [Inference Process](#Inference-process) - - [Inference](#Inference) -- [Model Description](#model-description) - - [Performance](#performance) - - [Evaluation Performance](#evaluation-performance) - - [Inference Performance](#evaluation-performance) - - [How to use](#how-to-use) + - [Export Process](#export-process) + - [Export](#export) + - [Inference Process](#inference-process) - [Inference](#inference) +- [Model Description](#model-description) + - [Performance](#performance) + - [Evaluation Performance](#evaluation-performance) + - [GoogleNet on CIFAR-10](#googlenet-on-cifar-10) + - [GoogleNet on 1200k images](#googlenet-on-1200k-images) + - [Inference Performance](#inference-performance) + - [GoogleNet on CIFAR-10](#googlenet-on-cifar-10-1) + - [GoogleNet on 1200k images](#googlenet-on-1200k-images-1) + - [How to use](#how-to-use) + - [Inference](#inference-1) - [Continue Training on the Pretrained Model](#continue-training-on-the-pretrained-model) - [Transfer Learning](#transfer-learning) - [Description of Random Situation](#description-of-random-situation) @@ -507,8 +512,8 @@ Current batch_ Size can only be set to 1. | -------------------------- | ----------------------------------------------------------- | ---------------------- | | Model Version | Inception V1 | Inception V1 | | Resource | Ascend 910; CPU 2.60GHz, 192cores; Memory 755G; OS Euler2.8 | NV SMX2 V100-32G | -| uploaded Date | 10/28/2020 (month/day/year) | 10/28/2020 (month/day/year) | -| MindSpore Version | 1.0.0 | 1.0.0 | +| uploaded Date | 07/05/2021 (month/day/year) | 07/05/2021 (month/day/year) | +| MindSpore Version | 1.3.0 | 1.3.0 | | Dataset | CIFAR-10 | CIFAR-10 | | Training Parameters | epoch=125, steps=390, batch_size = 128, lr=0.1 | epoch=125, steps=390, batch_size=128, lr=0.1 | | Optimizer | Momentum | Momentum | @@ -528,8 +533,8 @@ Current batch_ Size can only be set to 1. | -------------------------- | ----------------------------------------------------------- | | Model Version | Inception V1 | | Resource | Ascend 910; CPU 2.60GHz, 56cores; Memory 314G; OS Euler2.8 | -| uploaded Date | 10/28/2020 (month/day/year) | -| MindSpore Version | 1.0.0 | +| uploaded Date | 07/05/2021 (month/day/year) | +| MindSpore Version | 1.3.0 | | Dataset | 1200k images | | Training Parameters | epoch=300, steps=5000, batch_size=256, lr=0.1 | | Optimizer | Momentum | @@ -550,8 +555,8 @@ Current batch_ Size can only be set to 1. | ------------------- | --------------------------- | --------------------------- | | Model Version | Inception V1 | Inception V1 | | Resource | Ascend 910; OS Euler2.8 | GPU | -| Uploaded Date | 10/28/2020 (month/day/year) | 10/28/2020 (month/day/year) | -| MindSpore Version | 1.0.0 | 1.0.0 | +| Uploaded Date | 07/05/2021 (month/day/year) | 07/05/2021 (month/day/year) | +| MindSpore Version | 1.3.0 | 1.3.0 | | Dataset | CIFAR-10, 10,000 images | CIFAR-10, 10,000 images | | batch_size | 128 | 128 | | outputs | probability | probability | @@ -564,8 +569,8 @@ Current batch_ Size can only be set to 1. | ------------------- | --------------------------- | | Model Version | Inception V1 | | Resource | Ascend 910; OS Euler2.8 | -| Uploaded Date | 10/28/2020 (month/day/year) | -| MindSpore Version | 1.0.0 | +| Uploaded Date | 07/05/2021 (month/day/year) | +| MindSpore Version | 1.3.0 | | Dataset | 1200k images | | batch_size | 256 | | outputs | probability | diff --git a/model_zoo/official/cv/googlenet/README_CN.md b/model_zoo/official/cv/googlenet/README_CN.md index bdfff7d4ec4..8e26807c620 100644 --- a/model_zoo/official/cv/googlenet/README_CN.md +++ b/model_zoo/official/cv/googlenet/README_CN.md @@ -33,7 +33,7 @@ - [CIFAR-10上的GoogleNet](#cifar-10上的googlenet-1) - [120万张图像上的GoogleNet](#120万张图像上的googlenet-1) - [使用流程](#使用流程) - - [推理](#推理) + - [推理](#推理-1) - [继续训练预训练模型](#继续训练预训练模型) - [迁移学习](#迁移学习) - [随机情况说明](#随机情况说明) @@ -481,8 +481,8 @@ python export.py --config_path [CONFIG_PATH] | -------------------------- | ----------------------------------------------------------- | ---------------------- | | 模型版本 | Inception V1 | Inception V1 | | 资源 | Ascend 910；CPU 2.60GHz，192核；内存 755G；系统 Euler2.8 | NV SMX2 V100-32G | -| 上传日期 | 2020-08-31 | 2020-08-20 | -| MindSpore版本 | 0.7.0-alpha | 0.6.0-alpha | +| 上传日期 | 2021-07-05 | 2021-07-05 | +| MindSpore版本 | 1.3.0 | 1.3.0 | | 数据集 | CIFAR-10 | CIFAR-10 | | 训练参数 | epoch=125, steps=390, batch_size = 128, lr=0.1 | epoch=125, steps=390, batch_size=128, lr=0.1 | | 优化器 | Momentum | Momentum | @@ -502,8 +502,8 @@ python export.py --config_path [CONFIG_PATH] | -------------------------- | ----------------------------------------------------------- | | 模型版本 | Inception V1 | | 资源 | Ascend 910；CPU 2.60GHz，56核；内存 314G；系统 Euler2.8 | -| 上传日期 | 2020-09-20 | -| MindSpore版本 | 0.7.0-alpha | +| 上传日期 | 2021-07-05 | +| MindSpore版本 | 1.3.0 | | 数据集 | 120万张图像 | | 训练参数 | epoch=300, steps=5000, batch_size=256, lr=0.1 | | 优化器 | Momentum | @@ -524,8 +524,8 @@ python export.py --config_path [CONFIG_PATH] | ------------------- | --------------------------- | --------------------------- | | 模型版本 | Inception V1 | Inception V1 | | 资源 | Ascend 910；系统 Euler2.8 | GPU | -| 上传日期 | 2020-08-31 | 2020-08-20 | -| MindSpore 版本 | 0.7.0-alpha | 0.6.0-alpha | +| 上传日期 | 2021-07-05 | 2021-07-05 | +| MindSpore 版本 | 1.3.0 | 1.3.0 | | 数据集 | CIFAR-10, 1万张图像 | CIFAR-10, 1万张图像 | | batch_size | 128 | 128 | | 输出 | 概率 | 概率 | @@ -538,8 +538,8 @@ python export.py --config_path [CONFIG_PATH] | ------------------- | --------------------------- | | 模型版本 | Inception V1 | | 资源 | Ascend 910；系统 Euler2.8 | -| 上传日期 | 2020-09-20 | -| MindSpore版本 | 0.7.0-alpha | +| 上传日期 | 2021-07-05 | +| MindSpore版本 | 1.3.0 | | 数据集 | 12万张图像 | | batch_size | 256 | | 输出 | 概率 | diff --git a/model_zoo/official/cv/inceptionv3/README.md b/model_zoo/official/cv/inceptionv3/README.md index 0d7ffcc12ac..9b2c932dead 100644 --- a/model_zoo/official/cv/inceptionv3/README.md +++ b/model_zoo/official/cv/inceptionv3/README.md @@ -1,18 +1,31 @@ # Contents -- [InceptionV3 Description](#InceptionV3-description) -- [Model Architecture](#model-architecture) +- [Contents](#contents) +- [InceptionV3 Description](#inceptionv3-description) +- [Model architecture](#model-architecture) - [Dataset](#dataset) - [Features](#features) - - [Mixed Precision](#mixed-precision) + - [Mixed Precision(Ascend)](#mixed-precisionascend) - [Environment Requirements](#environment-requirements) -- [Script Description](#script-description) - - [Script and Sample Code](#script-and-sample-code) - - [Training Process](#training-process) - - [Evaluation Process](#evaluation-process) - - [Evaluation](#evaluation) -- [Model Description](#model-description) - - [Performance](#performance) +- [Script description](#script-description) + - [Script and sample code](#script-and-sample-code) + - [Script Parameters](#script-parameters) + - [Training process](#training-process) + - [Usage](#usage) + - [Launch](#launch) + - [Result](#result) + - [Ascend](#ascend) + - [CPU](#cpu) + - [Eval process](#eval-process) + - [Usage](#usage-1) + - [Launch](#launch-1) + - [Result](#result-1) + - [Model Export](#model-export) + - [Inference Process](#inference-process) + - [Usage](#usage-2) + - [result](#result-2) +- [Model description](#model-description) + - [Performance](#performance) - [Evaluation Performance](#evaluation-performance) - [Inference Performance](#inference-performance) - [Description of Random Situation](#description-of-random-situation) @@ -403,8 +416,8 @@ accuracy:78.742 | -------------------------- | ---------------------------------------------- | | Model Version | InceptionV3 | | Resource | Ascend 910; cpu 2.60GHz, 192cores; memory 755G; OS Euler2.8 | -| uploaded Date | 08/21/2020 | -| MindSpore Version | 0.6.0-beta | +| uploaded Date | 07/05/2021 | +| MindSpore Version | 1.3.0 | | Dataset | 1200k images | | Batch_size | 128 | | Training Parameters | src/model_utils/default_config.yaml | @@ -412,11 +425,11 @@ accuracy:78.742 | Loss Function | SoftmaxCrossEntropy | | Outputs | probability | | Loss | 1.98 | -| Total time (8p) | 11h | +| Total time (8p) | 10h | | Params (M) | 103M | | Checkpoint for Fine tuning | 313M | | Model for inference | 92M (.onnx file) | -| Speed | 1pc:1050 img/s;8pc:8000 img/s | +| Speed | 1pc:1200 img/s;8pc:9500 img/s | | Scripts | [inceptionv3 script](https://gitee.com/mindspore/mindspore/tree/master/model_zoo/official/cv/inceptionv3) | ### Inference Performance @@ -425,8 +438,8 @@ accuracy:78.742 | ------------------- | --------------------------- | | Model Version | InceptionV3 | | Resource | Ascend 910; cpu 2.60GHz, 192cores; memory 755G; OS Euler2.8 | -| Uploaded Date | 08/22/2020 | -| MindSpore Version | 0.6.0-beta | +| Uploaded Date | 07/05/2021 | +| MindSpore Version | 1.3.0 | | Dataset | 50k images | | Batch_size | 128 | | Outputs | probability | diff --git a/model_zoo/official/cv/inceptionv3/README_CN.md b/model_zoo/official/cv/inceptionv3/README_CN.md index 5bd1324a323..04058783c99 100644 --- a/model_zoo/official/cv/inceptionv3/README_CN.md +++ b/model_zoo/official/cv/inceptionv3/README_CN.md @@ -16,10 +16,16 @@ - [用法](#用法) - [启动](#启动) - [结果](#结果) + - [Ascend](#ascend) + - [CPU](#cpu) - [评估过程](#评估过程) - [用法](#用法-1) - [启动](#启动-1) - [结果](#结果-1) + - [模型导出](#模型导出) + - [推理过程](#推理过程) + - [使用方法](#使用方法) + - [结果](#结果-2) - [模型描述](#模型描述) - [性能](#性能) - [训练性能](#训练性能) @@ -408,8 +414,8 @@ accuracy:78.742 | -------------------------- | ------------------------------------------------------- | | 模型版本 | InceptionV3 | | 资源 | Ascend 910；CPU 2.60GHz，192核；内存 755G；系统 Euler2.8| -| 上传日期 | 2020-08-21 | -| MindSpore版本 | 0.6.0-beta | +| 上传日期 | 2021-07-05 | +| MindSpore版本 | 1.3.0 | | 数据集 | 120万张图像 | | Batch_size | 128 | | 训练参数 | src/model_utils/default_config.yaml | @@ -417,10 +423,10 @@ accuracy:78.742 | 损失函数 | Softmax交叉熵 | | 输出 | 概率 | | 损失 | 1.98 | -| 总时长（8卡） | 11小时 | +| 总时长（8卡） | 10小时 | | 参数(M) | 103M | | 微调检查点 | 313M | -| 训练速度 | 单卡：1050img/s;8卡：8000 img/s | +| 训练速度 | 单卡：1200img/s;8卡：9500 img/s | | 脚本 | [inceptionv3脚本](https://gitee.com/mindspore/mindspore/tree/master/model_zoo/official/cv/inceptionv3) | #### 推理性能 @@ -429,8 +435,8 @@ accuracy:78.742 | ------------------- | --------------------------- | | 模型版本 | InceptionV3 | | 资源 | Ascend 910；CPU 2.60GHz，192核；内存 755G；系统 Euler2.8| -| 上传日期 | 2020-08-22 | -| MindSpore 版本 | 0.6.0-beta | +| 上传日期 | 2021-07-05 | +| MindSpore 版本 | 1.3.0 | | 数据集 | 5万张图像 | | Batch_size | 128 | | 输出 | 概率 | diff --git a/model_zoo/official/cv/lenet/README.md b/model_zoo/official/cv/lenet/README.md index d22758b8552..512ed9d7ea3 100644 --- a/model_zoo/official/cv/lenet/README.md +++ b/model_zoo/official/cv/lenet/README.md @@ -1,26 +1,28 @@ # Contents -- [LeNet Description](#lenet-description) -- [Model Architecture](#model-architecture) -- [Dataset](#dataset) -- [Environment Requirements](#environment-requirements) -- [Quick Start](#quick-start) -- [Script Description](#script-description) - - [Script and Sample Code](#script-and-sample-code) +- [Contents](#contents) + - [LeNet Description](#lenet-description) + - [Model Architecture](#model-architecture) + - [Dataset](#dataset) + - [Environment Requirements](#environment-requirements) + - [Quick Start](#quick-start) + - [Script Description](#script-description) + - [Script and Sample Code](#script-and-sample-code) - [Script Parameters](#script-parameters) - [Training Process](#training-process) - - [Training](#training) + - [Training](#training) - [Evaluation Process](#evaluation-process) - [Evaluation](#evaluation) - - [Inference Process](#inference-process) + - [Inference Process](#inference-process) - [Export MindIR](#export-mindir) - [Infer on Ascend310](#infer-on-ascend310) - [result](#result) -- [Model Description](#model-description) - - [Performance](#performance) - - [Evaluation Performance](#evaluation-performance) - - [Inference Performance](#inference-performance) -- [ModelZoo Homepage](#modelzoo-homepage) + - [Model Description](#model-description) + - [Performance](#performance) + - [Evaluation Performance](#evaluation-performance) + - [Inference Performance](#inference-performance) + - [Description of Random Situation](#description-of-random-situation) + - [ModelZoo Homepage](#modelzoo-homepage) ## [LeNet Description](#contents) @@ -303,8 +305,8 @@ Inference result is saved in current path, you can find result like this in acc. | Parameters | LeNet | | -------------------------- | ----------------------------------------------------------- | | Resource | Ascend 910; CPU 2.60GHz, 192cores; Memory 755G; OS Euler2.8 | -| uploaded Date | 09/16/2020 (month/day/year) | -| MindSpore Version | 1.0.0 | +| uploaded Date | 07/05/2021 (month/day/year) | +| MindSpore Version | 1.3.0 | | Dataset | MNIST | | Training Parameters | epoch=10, steps=1875, batch_size = 32, lr=0.01 | | Optimizer | Momentum | diff --git a/model_zoo/official/cv/lenet/README_CN.md b/model_zoo/official/cv/lenet/README_CN.md index a849f284df1..d0d0b279e43 100644 --- a/model_zoo/official/cv/lenet/README_CN.md +++ b/model_zoo/official/cv/lenet/README_CN.md @@ -3,13 +3,13 @@ - [目录](#目录) -- [LeNet描述](#lenet描述) -- [模型架构](#模型架构) -- [数据集](#数据集) -- [环境要求](#环境要求) -- [快速入门](#快速入门) -- [脚本说明](#脚本说明) - - [脚本及样例代码](#脚本及样例代码) + - [LeNet描述](#lenet描述) + - [模型架构](#模型架构) + - [数据集](#数据集) + - [环境要求](#环境要求) + - [快速入门](#快速入门) + - [脚本说明](#脚本说明) + - [脚本及样例代码](#脚本及样例代码) - [脚本参数](#脚本参数) - [训练过程](#训练过程) - [训练](#训练) @@ -19,12 +19,12 @@ - [导出MindIR](#导出mindir) - [在Ascend310执行推理](#在ascend310执行推理) - [结果](#结果) -- [模型描述](#模型描述) + - [模型描述](#模型描述) - [性能](#性能) - [评估性能](#评估性能) - [推理性能](#推理性能) -- [随机情况说明](#随机情况说明) -- [ModelZoo主页](#modelzoo主页) + - [随机情况说明](#随机情况说明) + - [ModelZoo主页](#modelzoo主页) @@ -303,16 +303,16 @@ bash run_infer_310.sh [MINDIR_PATH] [DATA_PATH] [DVPP] [DEVICE_ID] | 参数 | LeNet | | -------------------- | ------------------------------------------------------- | | 资源 | Ascend 910；CPU 2.60GHz，192核；内存 755G；系统 Euler2.8| -| 上传日期 | 2020-06-09 | -| MindSpore版本 | 0.5.0-beta | +| 上传日期 | 2021-07-05 | +| MindSpore版本 | 1.3.0 | | 数据集 | MNIST | | 训练参数 | epoch=10, steps=1875, batch_size = 32, lr=0.01 | | 优化器 | Momentum | | 损失函数 | Softmax交叉熵 | | 输出 | 概率 | | 损失 | 0.002 | -| 速度 | 1.70毫秒/步 | -| 总时长 | 43.1秒 | +| 速度 | 1.0毫秒/步 | +| 总时长 | 32.1秒 | | 微调检查点 | 482k (.ckpt文件) | | 脚本 | [LeNet脚本](https://gitee.com/mindspore/mindspore/tree/master/model_zoo/official/cv/lenet) | diff --git a/model_zoo/official/cv/lenet_quant/Readme.md b/model_zoo/official/cv/lenet_quant/Readme.md index cc74a4c8a0f..ea99e89e528 100644 --- a/model_zoo/official/cv/lenet_quant/Readme.md +++ b/model_zoo/official/cv/lenet_quant/Readme.md @@ -1,21 +1,25 @@ # Contents -- [LeNet Description](#lenet-description) -- [Model Architecture](#model-architecture) -- [Dataset](#dataset) -- [Environment Requirements](#environment-requirements) -- [Quick Start](#quick-start) -- [Script Description](#script-description) +- [Contents](#contents) + - [LeNet Description](#lenet-description) + - [Model Architecture](#model-architecture) + - [Dataset](#dataset) + - [Environment Requirements](#environment-requirements) + - [Quick Start](#quick-start) + - [Script Description](#script-description) - [Script and Sample Code](#script-and-sample-code) - [Script Parameters](#script-parameters) - [Training Process](#training-process) - [Training](#training) - [Evaluation Process](#evaluation-process) - [Evaluation](#evaluation) -- [Model Description](#model-description) - - [Performance](#performance) - - [Evaluation Performance](#evaluation-performance) -- [ModelZoo Homepage](#modelzoo-homepage) + - [Model Export](#model-export) + - [Ascend 310 inference](#ascend-310-inference) + - [Model Description](#model-description) + - [Performance](#performance) + - [Evaluation Performance](#evaluation-performance) + - [Description of Random Situation](#description-of-random-situation) + - [ModelZoo Homepage](#modelzoo-homepage) ## [LeNet Description](#contents) @@ -193,9 +197,9 @@ You can view the results through the file "acc.log". The accuracy of the test da | Parameters | LeNet | | -------------------------- | ----------------------------------------------------------- | -| Resource | Ascend 910; CPU 2.60GHz, 192cores; Memory 755G; OS Euler2.8 | -| uploaded Date | 06/09/2020 (month/day/year) | -| MindSpore Version | 0.5.0-beta | +| Resource | Ascend 910; CPU 2.60GHz, 192cores; Memory 755G; OS Euler2.8 | +| uploaded Date | 07/05/2021 (month/day/year) | +| MindSpore Version | 1.3.0 | | Dataset | MNIST | | Training Parameters | epoch=10, steps=937, batch_size = 64, lr=0.01 | | Optimizer | Momentum | diff --git a/model_zoo/official/cv/lenet_quant/Readme_CN.md b/model_zoo/official/cv/lenet_quant/Readme_CN.md index cc0852e25a0..4824d69e121 100644 --- a/model_zoo/official/cv/lenet_quant/Readme_CN.md +++ b/model_zoo/official/cv/lenet_quant/Readme_CN.md @@ -3,23 +3,25 @@ - [目录](#目录) -- [LeNet描述](#lenet描述) -- [模型架构](#模型架构) -- [数据集](#数据集) -- [环境要求](#环境要求) -- [快速入门](#快速入门) -- [脚本说明](#脚本说明) - - [脚本及样例代码](#脚本及样例代码) - - [脚本参数](#脚本参数) - - [训练过程](#训练过程) - - [训练](#训练) - - [评估过程](#评估过程) - - [评估](#评估) -- [模型描述](#模型描述) - - [性能](#性能) - - [评估性能](#评估性能) -- [随机情况说明](#随机情况说明) -- [ModelZoo主页](#modelzoo主页) + - [LeNet描述](#lenet描述) + - [模型架构](#模型架构) + - [数据集](#数据集) + - [环境要求](#环境要求) + - [快速入门](#快速入门) + - [脚本说明](#脚本说明) + - [脚本及样例代码](#脚本及样例代码) + - [脚本参数](#脚本参数) + - [训练过程](#训练过程) + - [训练](#训练) + - [评估过程](#评估过程) + - [评估](#评估) + - [模型导出](#模型导出) + - [Ascend 310推理](#ascend-310推理) + - [模型描述](#模型描述) + - [性能](#性能) + - [评估性能](#评估性能) + - [随机情况说明](#随机情况说明) + - [ModelZoo主页](#modelzoo主页) @@ -198,8 +200,8 @@ bash run_infer_310.sh [AIR_PATH] [DATA_PATH] [LABEL_PATH] [DEVICE_ID] | 参数 | LeNet | | -------------------------- | ----------------------------------------------------------- | | 资源 | Ascend 910；CPU 2.60GHz，192核；内存 755G；系统 Euler2.8 | -| 上传日期 | 2020-06-09 | -| MindSpore版本 | 0.5.0-beta | +| 上传日期 | 2021-07-05 | +| MindSpore版本 | 1.3.0 | | 数据集 | MNIST | | 训练参数 | epoch=10, steps=937, batch_size = 64, lr=0.01 | | 优化器 | Momentum | diff --git a/model_zoo/official/cv/maskrcnn/README.md b/model_zoo/official/cv/maskrcnn/README.md index ea4c4cf2031..d3d113c6d80 100644 --- a/model_zoo/official/cv/maskrcnn/README.md +++ b/model_zoo/official/cv/maskrcnn/README.md @@ -1,23 +1,28 @@ # Contents +- [Contents](#contents) - [MaskRCNN Description](#maskrcnn-description) - [Model Architecture](#model-architecture) - [Dataset](#dataset) - [Environment Requirements](#environment-requirements) - [Quick Start](#quick-start) -- [Run in docker](#Run-in-docker) +- [Run in docker](#run-in-docker) - [Script Description](#script-description) - [Script and Sample Code](#script-and-sample-code) - [Script Parameters](#script-parameters) - [Training Script Parameters](#training-script-parameters) - [Parameters Configuration](#parameters-configuration) - [Training Process](#training-process) - - [Training](#training) - - [Distributed Training](#distributed-training) - - [Training Result](#training-result) + - [Training](#training) + - [Distributed Training](#distributed-training) + - [Training Result](#training-result) - [Evaluation Process](#evaluation-process) - - [Evaluation](#evaluation) - - [Evaluation Result](#evaluation-result) + - [Evaluation](#evaluation) + - [Evaluation result](#evaluation-result) + - [Model Export](#model-export) + - [Inference Process](#inference-process) + - [Usage](#usage) + - [result](#result) - [Model Description](#model-description) - [Performance](#performance) - [Evaluation Performance](#evaluation-performance) @@ -706,8 +711,8 @@ Accumulating evaluation results... | -------------------------- | ----------------------------------------------------------- | | Model Version | V1 | | Resource | Ascend 910; CPU 2.60GHz, 192cores; Memory 755G; OS Euler2.8 | -| uploaded Date | 08/01/2020 (month/day/year) | -| MindSpore Version | 1.0.0 | +| uploaded Date | 07/05/2021 (month/day/year) | +| MindSpore Version | 1.3.0 | | Dataset | COCO2017 | | Training Parameters | epoch=12, batch_size = 2 | | Optimizer | SGD | @@ -727,8 +732,8 @@ Accumulating evaluation results... | ------------------- | --------------------------- | | Model Version | V1 | | Resource | Ascend 910; OS Euler2.8 | -| Uploaded Date | 08/01/2020 (month/day/year) | -| MindSpore Version | 1.0.0 | +| Uploaded Date | 07/05/2021 (month/day/year) | +| MindSpore Version | 1.3.0 | | Dataset | COCO2017 | | batch_size | 2 | | outputs | mAP | diff --git a/model_zoo/official/cv/maskrcnn/README_CN.md b/model_zoo/official/cv/maskrcnn/README_CN.md index 971e02ef0ae..94d18b7720e 100644 --- a/model_zoo/official/cv/maskrcnn/README_CN.md +++ b/model_zoo/official/cv/maskrcnn/README_CN.md @@ -8,6 +8,7 @@ - [数据集](#数据集) - [环境要求](#环境要求) - [快速入门](#快速入门) +- [在docker上运行](#在docker上运行) - [脚本说明](#脚本说明) - [脚本和样例代码](#脚本和样例代码) - [脚本参数](#脚本参数) @@ -20,12 +21,16 @@ - [评估过程](#评估过程) - [评估](#评估) - [评估结果](#评估结果) + - [模型导出](#模型导出) + - [推理过程](#推理过程) + - [使用方法](#使用方法) + - [结果](#结果) - [模型说明](#模型说明) - [性能](#性能) - [训练性能](#训练性能) - [评估性能](#评估性能) - [随机情况说明](#随机情况说明) -- [ModelZoo首页](#modelzoo首页) +- [ModelZoo主页](#modelzoo主页) @@ -701,8 +706,8 @@ Accumulating evaluation results... | ------------------- | --------------------------------------------------------- | | 模型版本 | V1 | | 资源 | Ascend 910；CPU 2.60GHz，192核；内存 755G；系统 Euler2.8 | -| 上传日期 | 2020-08-01 | -| MindSpore版本 | 0.6.0-alpha | +| 上传日期 | 2021-07-05 | +| MindSpore版本 | 1.3.0 | | 数据集 | COCO2017 | | 训练参数 | epoch=12，batch_size=2 | | 优化器 | SGD | @@ -718,8 +723,8 @@ Accumulating evaluation results... | --------------------- | ----------------------------- | | 模型版本 | V1 | | 资源 | Ascend 910；系统 Euler2.8 | -| 上传日期 | 2020-08-01 | -| MindSpore版本 | 0.6.0-alpha | +| 上传日期 | 2021-07-05 | +| MindSpore版本 | 1.3.0 | | 数据集 | COCO2017 | | 批次大小 | 2 | | 输出 | mAP | diff --git a/model_zoo/official/cv/mobilenetv2/README.md b/model_zoo/official/cv/mobilenetv2/README.md index 61bd47f4de2..c716baaffc5 100644 --- a/model_zoo/official/cv/mobilenetv2/README.md +++ b/model_zoo/official/cv/mobilenetv2/README.md @@ -1,23 +1,30 @@ # Contents +- [Contents](#contents) - [MobileNetV2 Description](#mobilenetv2-description) -- [Model Architecture](#model-architecture) +- [Model architecture](#model-architecture) - [Dataset](#dataset) - [Features](#features) - - [Mixed Precision](#mixed-precision(ascend)) + - [Mixed Precision(Ascend)](#mixed-precisionascend) - [Environment Requirements](#environment-requirements) -- [Script Description](#script-description) - - [Script and Sample Code](#script-and-sample-code) - - [Training Process](#training-process) - - [Evaluation Process](#eval-process) - - [Inference Process](#inference-process) - - [Export MindIR](#export-mindir) - - [Infer on Ascend310](#infer-on-ascend310) - - [result](#result) -- [Model Description](#model-description) +- [Script description](#script-description) + - [Script and sample code](#script-and-sample-code) + - [Training process](#training-process) + - [Usage](#usage) + - [Launch](#launch) + - [Result](#result) + - [Evaluation process](#evaluation-process) + - [Usage](#usage-1) + - [Launch](#launch-1) + - [Result](#result-1) + - [Training with dataset on NFS](#training-with-dataset-on-nfs) + - [Inference process](#inference-process) + - [Export MindIR](#export-mindir) + - [Infer on Ascend310](#infer-on-ascend310) + - [result](#result-2) +- [Model description](#model-description) - [Performance](#performance) - [Training Performance](#training-performance) - - [Evaluation Performance](#evaluation-performance) - [Inference Performance](#inference-performance) - [Description of Random Situation](#description-of-random-situation) - [ModelZoo Homepage](#modelzoo-homepage) @@ -398,8 +405,8 @@ Inference result is saved in current path, you can find result like this in acc. | -------------------------- | ---------------------------------------------------------- | ------------------------- | | Model Version | V1 | V1 | | Resource | Ascend 910; cpu 2.60GHz, 192cores; memory 755G; OS Euler2.8 | NV SMX2 V100-32G | -| uploaded Date | 05/06/2020 | 05/06/2020 | -| MindSpore Version | 0.3.0 | 0.3.0 | +| uploaded Date | 07/05/2021 | 07/05/2021 | +| MindSpore Version | 1.3.0 | 1.3.0 | | Dataset | ImageNet | ImageNet | | Training Parameters | src/config.py | src/config.py | | Optimizer | Momentum | Momentum | diff --git a/model_zoo/official/cv/mobilenetv2/README_CN.md b/model_zoo/official/cv/mobilenetv2/README_CN.md index e52cd0ed106..ce54fad9978 100644 --- a/model_zoo/official/cv/mobilenetv2/README_CN.md +++ b/model_zoo/official/cv/mobilenetv2/README_CN.md @@ -17,10 +17,11 @@ - [用法](#用法-1) - [启动](#启动-1) - [结果](#结果-1) + - [NFS数据集的训练过程](#nfs数据集的训练过程) - [推理过程](#推理过程) - [导出MindIR](#导出mindir) - [在Ascend310执行推理](#在ascend310执行推理) - - [结果](#结果) + - [结果](#结果-2) - [模型描述](#模型描述) - [性能](#性能) - [训练性能](#训练性能) @@ -405,8 +406,8 @@ bash run_infer_310.sh [MINDIR_PATH] [DATA_PATH] [LABEL_PATH] [DVPP] [DEVICE_ID] | -------------------------- | ---------------------------------------------------------- | ------------------------- | | 模型版本 | V1 | V1 | | 资源 | Ascend 910；CPU 2.60GHz，192核；内存 755G；系统 Euler2.8 | NV SMX2 V100-32G | -| 上传日期 | 2020-05-06 | 2020-05-06 | -| MindSpore版本 | 0.3.0 | 0.3.0 | +| 上传日期 | 2021-07-05 | 2021-07-05 | +| MindSpore版本 | 1.3.0 | 1.3.0 | | 数据集 | ImageNet | ImageNet | | 训练参数 | src/config.py | src/config.py | | 优化器 | Momentum | Momentum | diff --git a/model_zoo/official/cv/mobilenetv2_quant/README_CN.md b/model_zoo/official/cv/mobilenetv2_quant/README_CN.md index 94801c75dd3..2694b892678 100644 --- a/model_zoo/official/cv/mobilenetv2_quant/README_CN.md +++ b/model_zoo/official/cv/mobilenetv2_quant/README_CN.md @@ -8,6 +8,7 @@ - [数据集](#数据集) - [特性](#特性) - [混合精度](#混合精度) + - [量化步长可学习的量化感知训练](#量化步长可学习的量化感知训练) - [环境要求](#环境要求) - [脚本说明](#脚本说明) - [脚本和样例代码](#脚本和样例代码) @@ -20,6 +21,8 @@ - [用法](#用法-1) - [启动](#启动-1) - [结果](#结果-1) + - [模型导出](#模型导出) + - [Ascend 310 推理](#ascend-310-推理) - [模型描述](#模型描述) - [性能](#性能) - [训练性能](#训练性能) @@ -279,8 +282,8 @@ bash run_infer_310.sh [AIR_PATH] [DATA_PATH] [LABEL_PATH] [DEVICE_ID] | 量化方案 | 传统量化感知训练（默认） |量化步长可学习的量化感知训练 | | 量化策略 | W:8bit, A:8bit | W:4bit (首尾层为 8bit), A:8bit| | 资源 | Ascend 910；CPU 2.60GHz，192核；内存 755G；系统 Euler2.8 |Ascend 910；CPU 2.60GHz，192核；内存 755G；系统 Euler2.8 | -| 上传日期 | 2020-06-06 |2021-04-30 | -| MindSpore版本 | 0.3.0 |1.3.0 | +| 上传日期 | 2021-07-05 |2021-04-30 | +| MindSpore版本 | 1.3.0 |1.3.0 | | 数据集 | ImageNet |ImageNet | | 训练参数 | src/config.py |src/config.py | | 优化器 | Momentum |Momentum | @@ -301,8 +304,8 @@ bash run_infer_310.sh [AIR_PATH] [DATA_PATH] [LABEL_PATH] [DEVICE_ID] | 量化方案 | 传统量化感知训练（默认） |量化步长可学习的量化感知训练 | | 量化策略 | W:8bit, A:8bit | W:4bit (首尾层为 8bit), A:8bit| | 资源 | Ascend 910；系统 Euler2.8 | Ascend 910；系统 Euler2.8 | -| 上传日期 | 2020-06-06 |2021-04-30 | -| MindSpore版本 | 0.3.0 | 1.3.0 | +| 上传日期 | 2021-07-05 |2021-04-30 | +| MindSpore版本 | 1.3.0 | 1.3.0 | | 数据集 | ImageNet, 1.2W | ImageNet, 1.2W | | 批次大小 | 130（8P） | | | 输出 | 概率 | 概率 | diff --git a/model_zoo/official/cv/mobilenetv2_quant/Readme.md b/model_zoo/official/cv/mobilenetv2_quant/Readme.md index 37c860f004f..12b36aa8023 100644 --- a/model_zoo/official/cv/mobilenetv2_quant/Readme.md +++ b/model_zoo/official/cv/mobilenetv2_quant/Readme.md @@ -1,20 +1,30 @@ # Contents +- [Contents](#contents) - [MobileNetV2 Description](#mobilenetv2-description) -- [Model Architecture](#model-architecture) +- [Model architecture](#model-architecture) - [Dataset](#dataset) - [Features](#features) - [Mixed Precision](#mixed-precision) + - [Learned Step Size Quantization](#learned-step-size-quantization) - [Environment Requirements](#environment-requirements) -- [Script Description](#script-description) - - [Script and Sample Code](#script-and-sample-code) +- [Script description](#script-description) + - [Script and sample code](#script-and-sample-code) - [Script Parameters](#script-parameters) - - [Training Process](#training-process) - - [Evaluation Process](#evaluation-process) -- [Model Description](#model-description) + - [Training process](#training-process) + - [Usage](#usage) + - [Launch](#launch) + - [Result](#result) + - [Evaluation process](#evaluation-process) + - [Usage](#usage-1) + - [Launch](#launch-1) + - [Result](#result-1) + - [Model Export](#model-export) + - [Ascend 310 inference](#ascend-310-inference) +- [Model description](#model-description) - [Performance](#performance) - [Training Performance](#training-performance) - - [Evaluation Performance](#evaluation-performance) + - [Evaluation Performance](#evaluation-performance) - [Description of Random Situation](#description-of-random-situation) - [ModelZoo Homepage](#modelzoo-homepage) @@ -269,8 +279,8 @@ You can view the results through the file "acc.log". The accuracy of the test da | Optimize Option | QAT | LEARNED_SCALE | | Quantization Strategy | W:8bit, A:8bit | W:4bit (The first and last layers are 8bit), A:8bit| | Resource | Ascend 910; cpu 2.60GHz, 192cores; memory 755G; OS Euler2.8 | Ascend 910; cpu 2.60GHz, 192cores; memory 755G; OS Euler2.8 | -| uploaded Date | 06/06/2020 | 04/30/2021 | -| MindSpore Version | 0.3.0 | 1.3.0 | +| uploaded Date | 07/05/2021 | 04/30/2021 | +| MindSpore Version | 1.3.0 | 1.3.0 | | Dataset | ImageNet | ImageNet | | Training Parameters | src/config.py | src/config.py | | Optimizer | Momentum | Momentum | @@ -291,8 +301,8 @@ You can view the results through the file "acc.log". The accuracy of the test da | Optimize Option | QAT | LEARNED_SCALE | | Quantization Strategy | W:8bit, A:8bit | W:4bit (The first and last layers are 8bit), A:8bit| | Resource | Ascend 910; OS Euler2.8 | Ascend 910; OS Euler2.8 | -| uploaded Date | 06/06/2020 | 04/30/2021 | -| MindSpore Version | 0.3.0 | 1.3.0 | +| uploaded Date | 07/05/2021 | 04/30/2021 | +| MindSpore Version | 1.3.0 | 1.3.0 | | Dataset | ImageNet, 1.2W | ImageNet, 1.2W | | batch_size | 130(8P) | | | outputs | probability | probability | diff --git a/model_zoo/official/cv/mobilenetv3/README_CN.md b/model_zoo/official/cv/mobilenetv3/README_CN.md index e9c2a9db20d..3170b25df27 100644 --- a/model_zoo/official/cv/mobilenetv3/README_CN.md +++ b/model_zoo/official/cv/mobilenetv3/README_CN.md @@ -17,7 +17,7 @@ - [用法](#用法-1) - [启动](#启动-1) - [结果](#结果-1) - - [导出MINDIR](#导出MINDIR) + - [导出MINDIR](#导出mindir) - [模型描述](#模型描述) - [性能](#性能) - [训练性能](#训练性能) @@ -161,8 +161,8 @@ python export.py --device_target [PLATFORM] --checkpoint_path [CKPT_PATH] | -------------------------- | ------------------------- | | 模型版本 | 大版本 | | 资源 | NV SMX2 V100-32G | -| 上传日期 | 2020-05-06 | -| MindSpore版本 | 0.3.0 | +| 上传日期 | 2021-07-05 | +| MindSpore版本 | 1.3.0 | | 数据集 | ImageNet | | 训练参数 | src/config.py | | 优化器 | Momentum | diff --git a/model_zoo/official/cv/mobilenetv3/Readme.md b/model_zoo/official/cv/mobilenetv3/Readme.md index 8ea910b8d21..90f28aa7ea8 100644 --- a/model_zoo/official/cv/mobilenetv3/Readme.md +++ b/model_zoo/official/cv/mobilenetv3/Readme.md @@ -1,19 +1,24 @@ # Contents +- [Contents](#contents) - [MobileNetV3 Description](#mobilenetv3-description) -- [Model Architecture](#model-architecture) +- [Model architecture](#model-architecture) - [Dataset](#dataset) - [Environment Requirements](#environment-requirements) -- [Script Description](#script-description) - - [Script and Sample Code](#script-and-sample-code) - - [Training Process](#training-process) - - [Evaluation Process](#evaluation-process) - - [Evaluation](#evaluation) +- [Script description](#script-description) + - [Script and sample code](#script-and-sample-code) + - [Training process](#training-process) + - [Usage](#usage) + - [Launch](#launch) + - [Result](#result) + - [Eval process](#eval-process) + - [Usage](#usage-1) + - [Launch](#launch-1) + - [Result](#result-1) - [Export MindIR](#export-mindir) -- [Model Description](#model-description) - - [Performance](#performance) - - [Training Performance](#evaluation-performance) - - [Inference Performance](#evaluation-performance) +- [Model description](#model-description) + - [Performance](#performance) + - [Training Performance](#training-performance) - [Description of Random Situation](#description-of-random-situation) - [ModelZoo Homepage](#modelzoo-homepage) @@ -152,8 +157,8 @@ python export.py --device_target [PLATFORM] --checkpoint_path [CKPT_PATH] | -------------------------- | ------------------------- | | Model Version | large | | Resource | NV SMX2 V100-32G | -| uploaded Date | 05/06/2020 | -| MindSpore Version | 0.3.0 | +| uploaded Date | 07/05/2021 | +| MindSpore Version | 1.3.0 | | Dataset | ImageNet | | Training Parameters | src/config.py | | Optimizer | Momentum | diff --git a/model_zoo/official/cv/openpose/README.md b/model_zoo/official/cv/openpose/README.md index c928176b514..077d62954d0 100644 --- a/model_zoo/official/cv/openpose/README.md +++ b/model_zoo/official/cv/openpose/README.md @@ -1,6 +1,7 @@ # Contents -- [Openpose Description](#googlenet-description) +- [Contents](#contents) +- [Openpose Description](#openpose-description) - [Model Architecture](#model-architecture) - [Dataset](#dataset) - [Features](#features) @@ -12,11 +13,10 @@ - [Script Parameters](#script-parameters) - [Training Process](#training-process) - [Training](#training) - - [Distributed Training](#distributed-training) - [Evaluation Process](#evaluation-process) - [Evaluation](#evaluation) - [Model Description](#model-description) - - [Performance](#performance) + - [Performance](#performance) - [Evaluation Performance](#evaluation-performance) # [Openpose Description](#contents) @@ -294,7 +294,7 @@ Data storage method is the same as training | Model Version | openpose | Resource | Ascend 910; CPU 2.60GHz, 192cores; Memory 755G; OS Euler2.8 | uploaded Date | 12/14/2020 (month/day/year) -| MindSpore Version | 1.0.1-alpha +| MindSpore Version | 1.0.1 | Training Parameters | epoch=60(1pcs)/80(8pcs), steps=30k(1pcs)/5k(8pcs), batch_size=10, init_lr=0.0001 | Optimizer | Adam(1pcs)/Momentum(8pcs) | Loss Function | MSE diff --git a/model_zoo/official/cv/posenet/README_CN.md b/model_zoo/official/cv/posenet/README_CN.md index 96050bafbdc..d309241be3b 100644 --- a/model_zoo/official/cv/posenet/README_CN.md +++ b/model_zoo/official/cv/posenet/README_CN.md @@ -19,15 +19,12 @@ - [模型描述](#模型描述) - [性能](#性能) - [评估性能](#评估性能) - - [KingsCollege上的PoseNet](#KingsCollege上的PoseNet) - - [StMarysChurch上的PoseNet](#StMarysChurch上的PoseNet) + - [KingsCollege上的PoseNet](#kingscollege上的posenet) + - [StMarysChurch上的PoseNet](#stmaryschurch上的posenet) - [推理性能](#推理性能) - - [KingsCollege上的PoseNet](#KingsCollege上的PoseNet) - - [StMarysChurch上的PoseNet](#StMarysChurch上的PoseNet) - - [使用流程](#使用流程) - - [推理](#推理) - - [继续训练预训练模型](#继续训练预训练模型) - - [迁移学习](#迁移学习) + - [KingsCollege上的PoseNet](#kingscollege上的posenet-1) + - [StMarysChurch上的PoseNet](#stmaryschurch上的posenet-1) + - [迁移学习](#迁移学习) - [随机情况说明](#随机情况说明) - [ModelZoo主页](#modelzoo主页) @@ -291,7 +288,7 @@ PoseNet是剑桥大学提出的一种鲁棒、实时的6DOF（单目六自由度 | -------------------------- | ----------------------------------------------------------- | ---------------------- | | 资源 | Ascend 910 ；CPU 2.60GHz，192核；内存：755G | NV SMX2 V100-32G | | 上传日期 | 2021-03-26 | 2021-05-20 | -| MindSpore版本 | 1.1.1-alpha | 1.2.1-alpha | +| MindSpore版本 | 1.1.1 | 1.2.1 | | 数据集 | KingsCollege | KingsCollege | | 训练参数 | max_steps=30000, batch_size=75, lr_init=0.001 | max_steps=30000, batch_size=75, lr_init=0.001 | | 优化器 | Adagrad | Adagrad | @@ -311,7 +308,7 @@ PoseNet是剑桥大学提出的一种鲁棒、实时的6DOF（单目六自由度 | -------------------------- | ----------------------------------------------------------- | ---------------------- | | 资源 | Ascend 910 ；CPU 2.60GHz，192核；内存：755G | NV SMX2 V100-32G | | 上传日期 | 2021-03-26 | 2021-05-20 | -| MindSpore版本 | 1.1.1-alpha | 1.2.1-alpha | +| MindSpore版本 | 1.1.1 | 1.2.1 | | 数据集 | StMarysChurch | StMarysChurch | | 训练参数 | max_steps=30000, batch_size=75, lr_init=0.001 | max_steps=30000, batch_size=75, lr_init=0.001 | | 优化器 | Adagrad | Adagrad | @@ -333,7 +330,7 @@ PoseNet是剑桥大学提出的一种鲁棒、实时的6DOF（单目六自由度 | ------------------- | --------------------------- | --------------------------- | | 资源 | Ascend 910 | GPU | | 上传日期 | 2021-03-26 | 2021-05-20 | -| MindSpore 版本 | 1.1.1-alpha | 1.2.1-alpha | +| MindSpore 版本 | 1.1.1 | 1.2.1 | | 数据集 | KingsCollege | KingsCollege | | batch_size | 1 | 1 | | 输出 | 距离、角度 |距离、角度 | @@ -346,7 +343,7 @@ PoseNet是剑桥大学提出的一种鲁棒、实时的6DOF（单目六自由度 | ------------------- | --------------------------- | --------------------------- | | 资源 | Ascend 910 | GPU | | 上传日期 | 2021-03-26 | 2021-05-20 | -| MindSpore 版本 | 1.1.1-alpha | 1.2.1-alpha | +| MindSpore 版本 | 1.1.1 | 1.2.1 | | 数据集 | StMarysChurch | StMarysChurch | | batch_size | 1 | 1 | | 输出 | 距离、角度 | 距离、角度 | diff --git a/model_zoo/official/cv/resnet/README.md b/model_zoo/official/cv/resnet/README.md index f83b39bda27..9ed240d047d 100644 --- a/model_zoo/official/cv/resnet/README.md +++ b/model_zoo/official/cv/resnet/README.md @@ -1,6 +1,9 @@ # Contents +- [Contents](#contents) - [ResNet Description](#resnet-description) + - [Description](#description) + - [Paper](#paper) - [Model Architecture](#model-architecture) - [Dataset](#dataset) - [Features](#features) @@ -11,15 +14,39 @@ - [Script and Sample Code](#script-and-sample-code) - [Script Parameters](#script-parameters) - [Training Process](#training-process) + - [Usage](#usage) + - [Running on Ascend](#running-on-ascend) + - [Running on GPU](#running-on-gpu) + - [Running parameter server mode training](#running-parameter-server-mode-training) + - [Evaluation while training](#evaluation-while-training) + - [Result](#result) - [Evaluation Process](#evaluation-process) -- [Inference Process](#inference-process) - - [Export MindIR](#export-mindir) - - [Infer on Ascend310](#infer-on-ascend310) - - [result](#result) + - [Usage](#usage-1) + - [Running on Ascend](#running-on-ascend-1) + - [Running on GPU](#running-on-gpu-1) + - [Result](#result-1) + - [Inference Process](#inference-process) + - [Export MindIR](#export-mindir) + - [Infer on Ascend310](#infer-on-ascend310) + - [result](#result-2) - [Model Description](#model-description) - [Performance](#performance) - [Evaluation Performance](#evaluation-performance) + - [ResNet18 on CIFAR-10](#resnet18-on-cifar-10) + - [ResNet18 on ImageNet2012](#resnet18-on-imagenet2012) + - [ResNet50 on CIFAR-10](#resnet50-on-cifar-10) + - [ResNet50 on ImageNet2012](#resnet50-on-imagenet2012) + - [ResNet34 on ImageNet2012](#resnet34-on-imagenet2012) + - [ResNet101 on ImageNet2012](#resnet101-on-imagenet2012) + - [SE-ResNet50 on ImageNet2012](#se-resnet50-on-imagenet2012) - [Inference Performance](#inference-performance) + - [ResNet18 on CIFAR-10](#resnet18-on-cifar-10-1) + - [ResNet18 on ImageNet2012](#resnet18-on-imagenet2012-1) + - [ResNet34 on ImageNet2012](#resnet34-on-imagenet2012-1) + - [ResNet50 on CIFAR-10](#resnet50-on-cifar-10-1) + - [ResNet50 on ImageNet2012](#resnet50-on-imagenet2012-1) + - [ResNet101 on ImageNet2012](#resnet101-on-imagenet2012-1) + - [SE-ResNet50 on ImageNet2012](#se-resnet50-on-imagenet2012-1) - [Description of Random Situation](#description-of-random-situation) - [ModelZoo Homepage](#modelzoo-homepage) @@ -690,7 +717,7 @@ Total data: 50000, top1 accuracy: 0.76844, top5 accuracy: 0.93522. | Model Version | ResNet18 | | Resource | Ascend 910; CPU 2.60GHz, 192cores; Memory 755G; OS Euler2.8 | | uploaded Date | 02/25/2021 (month/day/year) | -| MindSpore Version | 1.1.1-alpha | +| MindSpore Version | 1.1.1 | | Dataset | CIFAR-10 | | Training Parameters | epoch=90, steps per epoch=195, batch_size = 32 | | Optimizer | Momentum | @@ -710,7 +737,7 @@ Total data: 50000, top1 accuracy: 0.76844, top5 accuracy: 0.93522. | Model Version | ResNet18 | | Resource | Ascend 910; CPU 2.60GHz, 192cores; Memory 755G; OS Euler2.8 | | uploaded Date | 02/25/2021 (month/day/year) ； | -| MindSpore Version | 1.1.1-alpha | +| MindSpore Version | 1.1.1 | | Dataset | ImageNet2012 | | Training Parameters | epoch=90, steps per epoch=626, batch_size = 256 | | Optimizer | Momentum | @@ -729,8 +756,8 @@ Total data: 50000, top1 accuracy: 0.76844, top5 accuracy: 0.93522. | -------------------------- | -------------------------------------- |---------------------------------- | | Model Version | ResNet50-v1.5 |ResNet50-v1.5| | Resource | Ascend 910; CPU 2.60GHz, 192cores; Memory 755G; OS Euler2.8 | GPU(Tesla V100 SXM2)，CPU 2.1GHz 24cores，Memory 128G -| uploaded Date | 04/01/2020 (month/day/year) | 08/01/2020 (month/day/year) -| MindSpore Version | 0.1.0-alpha |0.6.0-alpha | +| uploaded Date | 07/05/2021 (month/day/year) | 07/05/2021 (month/day/year) +| MindSpore Version | 1.3.0 |1.3.0 | | Dataset | CIFAR-10 | CIFAR-10 | Training Parameters | epoch=90, steps per epoch=195, batch_size = 32 |epoch=90, steps per epoch=195, batch_size = 32 | | Optimizer | Momentum |Momentum| @@ -749,8 +776,8 @@ Total data: 50000, top1 accuracy: 0.76844, top5 accuracy: 0.93522. | -------------------------- | -------------------------------------- |---------------------------------- | | Model Version | ResNet50-v1.5 |ResNet50-v1.5| | Resource | Ascend 910; CPU 2.60GHz, 192cores; Memory 755G; OS Euler2.8 | GPU(Tesla V100 SXM2)，CPU 2.1GHz 24cores，Memory 128G -| uploaded Date | 04/01/2020 (month/day/year) ； | 08/01/2020 (month/day/year) -| MindSpore Version | 0.1.0-alpha |0.6.0-alpha | +| uploaded Date | 07/05/2021 (month/day/year) ； | 07/05/2021 (month/day/year) +| MindSpore Version | 1.3.0 |1.3.0 | | Dataset | ImageNet2012 | ImageNet2012| | Training Parameters | epoch=90, steps per epoch=626, batch_size = 256 |epoch=90, steps per epoch=626, batch_size = 256 | | Optimizer | Momentum |Momentum| @@ -769,8 +796,8 @@ Total data: 50000, top1 accuracy: 0.76844, top5 accuracy: 0.93522. | -------------------------- | -------------------------------------- |---------------------------------- | | Model Version | ResNet50-v1.5 | | Resource | Ascend 910; CPU 2.60GHz, 192cores; Memory 755G; OS Euler2.8 | -| uploaded Date | 04/01/2020 (month/day/year) ； | -| MindSpore Version | 0.1.0-alpha | +| uploaded Date | 07/05/2020 (month/day/year) ； | +| MindSpore Version | 1.3.0 | | Dataset | ImageNet2012 | | Training Parameters | epoch=90, steps per epoch=626, batch_size = 256 | | Optimizer | Momentum | @@ -789,8 +816,8 @@ Total data: 50000, top1 accuracy: 0.76844, top5 accuracy: 0.93522. | -------------------------- | -------------------------------------- |---------------------------------- | | Model Version | ResNet101 |ResNet101| | Resource | Ascend 910; CPU 2.60GHz, 192cores; Memory 755G; OS Euler2.8 | GPU(Tesla V100 SXM2)，CPU 2.1GHz 24cores，Memory 128G -| uploaded Date | 04/01/2020 (month/day/year) | 08/01/2020 (month/day/year) -| MindSpore Version | 0.1.0-alpha |0.6.0-alpha | +| uploaded Date | 07/05/2021 (month/day/year) | 07/05/2021 (month/day/year) +| MindSpore Version | 1.3.0 |1.3.0 | | Dataset | ImageNet2012 | ImageNet2012| | Training Parameters | epoch=120, steps per epoch=5004, batch_size = 32 |epoch=120, steps per epoch=5004, batch_size = 32 | | Optimizer | Momentum |Momentum| @@ -809,8 +836,8 @@ Total data: 50000, top1 accuracy: 0.76844, top5 accuracy: 0.93522. | -------------------------- | ------------------------------------------------------------------------ | | Model Version | SE-ResNet50 | | Resource | Ascend 910; CPU 2.60GHz, 192cores; Memory 755G; OS Euler2.8 | -| uploaded Date | 08/16/2020 (month/day/year) | -| MindSpore Version | 0.7.0-alpha | +| uploaded Date | 07/05/2021 (month/day/year) | +| MindSpore Version | 1.3.0 | | Dataset | ImageNet2012 | | Training Parameters | epoch=24, steps per epoch=5004, batch_size = 32 | | Optimizer | Momentum | @@ -832,7 +859,7 @@ Total data: 50000, top1 accuracy: 0.76844, top5 accuracy: 0.93522. | Model Version | ResNet18 | | Resource | Ascend 910; OS Euler2.8 | | Uploaded Date | 02/25/2021 (month/day/year) | -| MindSpore Version | 1.1.1-alpha | +| MindSpore Version | 1.1.1 | | Dataset | CIFAR-10 | | batch_size | 32 | | outputs | probability | @@ -846,7 +873,7 @@ Total data: 50000, top1 accuracy: 0.76844, top5 accuracy: 0.93522. | Model Version | ResNet18 | | Resource | Ascend 910; OS Euler2.8 | | Uploaded Date | 02/25/2021 (month/day/year) | -| MindSpore Version | 1.1.1-alpha | +| MindSpore Version | 1.1.1 | | Dataset | ImageNet2012 | | batch_size | 256 | | outputs | probability | @@ -860,7 +887,7 @@ Total data: 50000, top1 accuracy: 0.76844, top5 accuracy: 0.93522. | Model Version | ResNet18 | | Resource | Ascend 910; OS Euler2.8 | | Uploaded Date | 02/25/2021 (month/day/year) | -| MindSpore Version | 1.1.1-alpha | +| MindSpore Version | 1.1.1 | | Dataset | ImageNet2012 | | batch_size | 256 | | outputs | probability | @@ -873,8 +900,8 @@ Total data: 50000, top1 accuracy: 0.76844, top5 accuracy: 0.93522. | ------------------- | --------------------------- | --------------------------- | | Model Version | ResNet50-v1.5 | ResNet50-v1.5 | | Resource | Ascend 910; OS Euler2.8 | GPU | -| Uploaded Date | 04/01/2020 (month/day/year) | 08/01/2020 (month/day/year) | -| MindSpore Version | 0.1.0-alpha | 0.6.0-alpha | +| Uploaded Date | 07/05/2021 (month/day/year) | 07/05/2021 (month/day/year) | +| MindSpore Version | 1.3.0 | 1.3.0 | | Dataset | CIFAR-10 | CIFAR-10 | | batch_size | 32 | 32 | | outputs | probability | probability | @@ -887,8 +914,8 @@ Total data: 50000, top1 accuracy: 0.76844, top5 accuracy: 0.93522. | ------------------- | --------------------------- | --------------------------- | | Model Version | ResNet50-v1.5 | ResNet50-v1.5 | | Resource | Ascend 910; OS Euler2.8 | GPU | -| Uploaded Date | 04/01/2020 (month/day/year) | 08/01/2020 (month/day/year) | -| MindSpore Version | 0.1.0-alpha | 0.6.0-alpha | +| Uploaded Date | 07/05/2021 (month/day/year) | 07/05/2021 (month/day/year) | +| MindSpore Version | 1.3.0 | 1.3.0 | | Dataset | ImageNet2012 | ImageNet2012 | | batch_size | 256 | 256 | | outputs | probability | probability | @@ -900,9 +927,9 @@ Total data: 50000, top1 accuracy: 0.76844, top5 accuracy: 0.93522. | Parameters | Ascend | GPU | | ------------------- | --------------------------- | --------------------------- | | Model Version | ResNet101 | ResNet101 | -| Resource | Ascend 910; OS Euler2.8 | GPU | -| Uploaded Date | 04/01/2020 (month/day/year) | 08/01/2020 (month/day/year) | -| MindSpore Version | 0.1.0-alpha | 0.6.0-alpha | +| Resource | Ascend 910; OS Euler2.8 | GPU | +| Uploaded Date | 07/05/2021 (month/day/year) | 07/05/2021 (month/day/year) | +| MindSpore Version | 1.3.0 | 1.3.0 | | Dataset | ImageNet2012 | ImageNet2012 | | batch_size | 32 | 32 | | outputs | probability | probability | @@ -915,8 +942,8 @@ Total data: 50000, top1 accuracy: 0.76844, top5 accuracy: 0.93522. | ------------------- | --------------------------- | | Model Version | SE-ResNet50 | | Resource | Ascend 910; OS Euler2.8 | -| Uploaded Date | 08/16/2020 (month/day/year) | -| MindSpore Version | 0.7.0-alpha | +| Uploaded Date | 07/05/2021 (month/day/year) | +| MindSpore Version | 1.3.0 | | Dataset | ImageNet2012 | | batch_size | 32 | | outputs | probability | diff --git a/model_zoo/official/cv/resnet/README_CN.md b/model_zoo/official/cv/resnet/README_CN.md index f26e7ef7967..39e24056356 100755 --- a/model_zoo/official/cv/resnet/README_CN.md +++ b/model_zoo/official/cv/resnet/README_CN.md @@ -2,7 +2,10 @@ -- [ResNet描述](#ResNet描述) +- [目录](#目录) +- [ResNet描述](#resnet描述) + - [概述](#概述) + - [论文](#论文) - [模型架构](#模型架构) - [数据集](#数据集) - [特性](#特性) @@ -13,16 +16,33 @@ - [脚本及样例代码](#脚本及样例代码) - [脚本参数](#脚本参数) - [训练过程](#训练过程) + - [用法](#用法) + - [Ascend处理器环境运行](#ascend处理器环境运行) + - [GPU处理器环境运行](#gpu处理器环境运行) + - [运行参数服务器模式训练](#运行参数服务器模式训练) + - [训练时推理](#训练时推理) + - [结果](#结果) - [评估过程](#评估过程) + - [用法](#用法-1) + - [Ascend处理器环境运行](#ascend处理器环境运行-1) + - [GPU处理器环境运行](#gpu处理器环境运行-1) + - [结果](#结果-1) - [推理过程](#推理过程) - [导出MindIR](#导出mindir) - [在Ascend310执行推理](#在ascend310执行推理) - - [结果](#结果) + - [结果](#结果-2) - [模型描述](#模型描述) - [性能](#性能) - [评估性能](#评估性能) + - [CIFAR-10上的ResNet18](#cifar-10上的resnet18) + - [ImageNet2012上的ResNet18](#imagenet2012上的resnet18) + - [CIFAR-10上的ResNet50](#cifar-10上的resnet50) + - [ImageNet2012上的ResNet50](#imagenet2012上的resnet50) + - [ImageNet2012上的ResNet34](#imagenet2012上的resnet34) + - [ImageNet2012上的ResNet101](#imagenet2012上的resnet101) + - [ImageNet2012上的SE-ResNet50](#imagenet2012上的se-resnet50) - [随机情况说明](#随机情况说明) -- [ModelZoo主页](#ModelZoo主页) +- [ModelZoo主页](#modelzoo主页) @@ -658,7 +678,7 @@ Total data: 50000, top1 accuracy: 0.76844, top5 accuracy: 0.93522. | 模型版本 | ResNet18 | | 资源 | Ascend 910；CPU 2.60GHz，192核；内存 755G；系统 Euler2.8 | | 上传日期 | 2021-02-25 | -| MindSpore版本 | 1.1.1-alpha | +| MindSpore版本 | 1.1.1 | | 数据集 | CIFAR-10 | | 训练参数 | epoch=90, steps per epoch=195, batch_size = 32 | | 优化器 | Momentum | @@ -678,7 +698,7 @@ Total data: 50000, top1 accuracy: 0.76844, top5 accuracy: 0.93522. | 模型版本 | ResNet18 | | 资源 | Ascend 910；CPU 2.60GHz，192核；内存 755G；系统 Euler2.8 | | 上传日期 | 2020-04-01 ; | -| MindSpore版本 | 1.1.1-alpha | +| MindSpore版本 | 1.1.1 | | 数据集 | ImageNet2012 | | 训练参数 | epoch=90, steps per epoch=626, batch_size = 256 | | 优化器 | Momentum | @@ -697,8 +717,8 @@ Total data: 50000, top1 accuracy: 0.76844, top5 accuracy: 0.93522. | -------------------------- | -------------------------------------- |---------------------------------- | | 模型版本 | ResNet50-v1.5 |ResNet50-v1.5| | 资源 |Ascend 910；CPU 2.60GHz，192核；内存 755G；系统 Euler2.8 | GPU(Tesla V100 SXM2)；CPU：2.1GHz，24核；内存：128G -| 上传日期 | 2020-04-01 | 2020-08-01 -| MindSpore版本 | 0.1.0-alpha |0.6.0-alpha | +| 上传日期 | 2021-07-05 | 2021-07-05 +| MindSpore版本 | 1.3.0 |1.3.0 | | 数据集 | CIFAR-10 | CIFAR-10 | 训练参数 | epoch=90, steps per epoch=195, batch_size = 32 |epoch=90, steps per epoch=195, batch_size = 32 | | 优化器 | Momentum |Momentum| @@ -717,8 +737,8 @@ Total data: 50000, top1 accuracy: 0.76844, top5 accuracy: 0.93522. | -------------------------- | -------------------------------------- |---------------------------------- | | 模型版本 | ResNet50-v1.5 |ResNet50-v1.5| | 资源 | Ascend 910；CPU 2.60GHz，192核；内存 755G；系统 Euler2.8 | GPU(Tesla V100 SXM2)；CPU：2.1GHz，24核；内存：128G -| 上传日期 | 2020-04-01 ; | 2020-08-01 -| MindSpore版本 | 0.1.0-alpha |0.6.0-alpha | +| 上传日期 | 2021-07-05 ; | 2021-07-05 +| MindSpore版本 | 1.3.0 |1.3.0 | | 数据集 | ImageNet2012 | ImageNet2012| | 训练参数 | epoch=90, steps per epoch=626, batch_size = 256 |epoch=90, steps per epoch=5004, batch_size = 32 | | 优化器 | Momentum |Momentum| @@ -738,7 +758,7 @@ Total data: 50000, top1 accuracy: 0.76844, top5 accuracy: 0.93522. | 模型版本 | ResNet34 | | 资源 | Ascend 910；CPU 2.60GHz，192核；内存 755G；系统 Euler2.8 | | 上传日期 | 2021-05-08 ; | -| MindSpore版本 | 1.1.1-alpha | +| MindSpore版本 | 1.1.1 | | 数据集 | ImageNet2012 | | 训练参数 | epoch=90, steps per epoch=625, batch_size = 256 | | 优化器 | Momentum | @@ -757,8 +777,8 @@ Total data: 50000, top1 accuracy: 0.76844, top5 accuracy: 0.93522. | -------------------------- | -------------------------------------- |---------------------------------- | | 模型版本 | ResNet101 |ResNet101| | 资源 | Ascend 910；CPU 2.60GHz，192核；内存 755G；系统 Euler2.8 | GPU(Tesla V100 SXM2)；CPU：2.1GHz，24核；内存：128G -| 上传日期 | 2020-04-01 ; | 2020-08-01 -| MindSpore版本 | 0.1.0-alpha |0.6.0-alpha | +| 上传日期 | 2021-07-05 ; | 2021-07-05 +| MindSpore版本 | 1.3.0 |1.3.0 | | 数据集 | ImageNet2012 | ImageNet2012| | 训练参数 | epoch=120, steps per epoch=5004, batch_size = 32 |epoch=120, steps per epoch=5004, batch_size = 32 | | 优化器 | Momentum |Momentum| @@ -777,8 +797,8 @@ Total data: 50000, top1 accuracy: 0.76844, top5 accuracy: 0.93522. | -------------------------- | ------------------------------------------------------------------------ | | 模型版本 | SE-ResNet50 | | 资源 | Ascend 910；CPU 2.60GHz，192核；内存 755G；系统 Euler2.8 | -| 上传日期 | 2020-08-16 ； | -| MindSpore版本 | 0.7.0-alpha | +| 上传日期 | 2021-07-05 ； | +| MindSpore版本 | 1.3.0 | | 数据集 | ImageNet2012 | | 训练参数 | epoch=24, steps per epoch=5004, batch_size = 32 | | 优化器 | Momentum | diff --git a/model_zoo/official/cv/resnet50_quant/README.md b/model_zoo/official/cv/resnet50_quant/README.md index 3121326008d..aecbb276354 100644 --- a/model_zoo/official/cv/resnet50_quant/README.md +++ b/model_zoo/official/cv/resnet50_quant/README.md @@ -1,17 +1,26 @@ # Contents +- [Contents](#contents) - [ResNet50 Description](#resnet50-description) - [Model Architecture](#model-architecture) - [Dataset](#dataset) - [Features](#features) - [Mixed Precision](#mixed-precision) - [Environment Requirements](#environment-requirements) -- [Script Description](#script-description) - - [Script and Sample Code](#script-and-sample-code) +- [Script description](#script-description) + - [Script and sample code](#script-and-sample-code) - [Script Parameters](#script-parameters) - - [Training Process](#training-process) - - [Evaluation Process](#evaluation-process) -- [Model Description](#model-description) + - [Training process](#training-process) + - [Usage](#usage) + - [Launch](#launch) + - [Result](#result) + - [Evaluation process](#evaluation-process) + - [Usage](#usage-1) + - [Launch](#launch-1) + - [Result](#result-1) + - [Model Export](#model-export) + - [Ascend 310 inference](#ascend-310-inference) +- [Model description](#model-description) - [Performance](#performance) - [Evaluation Performance](#evaluation-performance) - [Inference Performance](#inference-performance) @@ -213,8 +222,8 @@ You can view the results through the file "acc.log". The accuracy of the test da | -------------------------- | ----------------------------------------------------------- | | Model Version | ResNet50 V1.5 | | Resource | Ascend 910; CPU 2.60GHz, 56cores; Memory 314G; OS Euler2.8 | -| uploaded Date | 06/06/2020 (month/day/year) | -| MindSpore Version | 0.3.0-alpha | +| uploaded Date | 07/05/2021 (month/day/year) | +| MindSpore Version | 1.3.0 | | Dataset | ImageNet | | Training Parameters | epoch=30(with pretrained) or 120, steps per epoch=5004, batch_size=32 | | Optimizer | Momentum | @@ -233,8 +242,8 @@ You can view the results through the file "acc.log". The accuracy of the test da | ------------------- | --------------------------- | | Model Version | ResNet50 V1.5 | | Resource | Ascend 910; CPU 2.60GHz, 56cores; Memory 314G; OS Euler2.8 | -| Uploaded Date | 06/06/2020 (month/day/year) | -| MindSpore Version | 0.3.0-alpha | +| Uploaded Date | 07/05/2021 (month/day/year) | +| MindSpore Version | 1.3.0 | | Dataset | ImageNet | | batch_size | 32 | | outputs | probability | diff --git a/model_zoo/official/cv/resnet50_quant/README_CN.md b/model_zoo/official/cv/resnet50_quant/README_CN.md index 90b5a560091..28c66cb9d30 100644 --- a/model_zoo/official/cv/resnet50_quant/README_CN.md +++ b/model_zoo/official/cv/resnet50_quant/README_CN.md @@ -7,25 +7,27 @@ - [模型架构](#模型架构) - [数据集](#数据集) - [特性](#特性) - - [混合精度](#混合精度) + - [混合精度](#混合精度) - [环境要求](#环境要求) - - [脚本说明](#脚本说明) - - [脚本和样例代码](#脚本和样例代码) - - [脚本参数](#脚本参数) - - [训练过程](#训练过程) - - [用法](#用法) - - [启动](#启动) - - [结果](#结果) - - [评估过程](#评估过程) - - [用法](#用法-1) - - [启动](#启动-1) - - [结果](#结果-1) + - [脚本说明](#脚本说明) + - [脚本和样例代码](#脚本和样例代码) + - [脚本参数](#脚本参数) + - [训练过程](#训练过程) + - [用法](#用法) + - [启动](#启动) + - [结果](#结果) + - [评估过程](#评估过程) + - [用法](#用法-1) + - [启动](#启动-1) + - [结果](#结果-1) + - [模型导出](#模型导出) + - [Ascend 310 推理](#ascend-310-推理) - [模型描述](#模型描述) - - [性能](#性能) - - [训练性能](#训练性能) - - [评估性能](#评估性能) - - [随机情况说明](#随机情况说明) -- [ModelZoo主页](#modelzoo主页) + - [性能](#性能) + - [训练性能](#训练性能) + - [评估性能](#评估性能) + - [随机情况说明](#随机情况说明) + - [ModelZoo主页](#modelzoo主页) @@ -221,8 +223,8 @@ bash run_infer_310.sh [AIR_PATH] [DATA_PATH] [LABEL_PATH] [DEVICE_ID] | -------------------------- | ---------------------------------------------------------- | | 模型版本 | V1 | | 资源 | Ascend 910； CPU 2.60GHz，192核；内存 755G；系统 Euler2.8 | -| 上传日期 | 2020-06-06 | -| MindSpore版本 | 0.3.0 | +| 上传日期 | 2021-07-05 | +| MindSpore版本 | 1.3.0 | | 数据集 | ImageNet | | 训练参数 | src/config.py | | 优化器 | Momentum | @@ -241,8 +243,8 @@ bash run_infer_310.sh [AIR_PATH] [DATA_PATH] [LABEL_PATH] [DEVICE_ID] | -------------------------- | ----------------------------- | | 模型版本 | V1 | | 资源 | Ascend 910；系统 Euler2.8 | -| 上传日期 | 2020-06-06 | -| MindSpore版本 | 0.3.0 | +| 上传日期 | 2021-07-05 | +| MindSpore版本 | 1.3.0 | | 数据集 | ImageNet, 1.2W | | batch_size | 130（8卡） | | 输出 | 概率 | diff --git a/model_zoo/official/cv/resnet_thor/README.md b/model_zoo/official/cv/resnet_thor/README.md index a565084e615..a8ae19c894d 100644 --- a/model_zoo/official/cv/resnet_thor/README.md +++ b/model_zoo/official/cv/resnet_thor/README.md @@ -1,21 +1,26 @@ # ResNet-50-THOR Example -- [Description](#Description) -- [Model Architecture](#Model-Architecture) -- [Dataset](#Dataset) -- [Features](#Features) -- [Environment Requirements](#Environment-Requirements) -- [Quick Start](#Quick-Start) -- [Script Description](#Script-Description) - - [Script and Sample Code](#Script-Code-Structure) - - [Script Parameters](#Script-Parameters) - - [Training Process](#Training-Process) - - [Evaluation Process](#Evaluation-Process) -- [Model Description](#Model-Description) - - [Evaluation Performance](#Evaluation-Performance) - - [Inference Performance](#Inference-Performance) -- [Description of Random Situation](#Description-of-Random-Situation) -- [ModelZoo Homepage](#ModelZoo-Homepage) +- [ResNet-50-THOR Example](#resnet-50-thor-example) + - [Description](#description) + - [Model Architecture](#model-architecture) + - [Dataset](#dataset) + - [Features](#features) + - [Environment Requirements](#environment-requirements) + - [Quick Start](#quick-start) + - [Script Description](#script-description) + - [Script Code Structure](#script-code-structure) + - [Script Parameters](#script-parameters) + - [Training Process](#training-process) + - [Ascend 910](#ascend-910) + - [GPU](#gpu) + - [Evaluation Process](#evaluation-process) + - [Ascend 910](#ascend-910-1) + - [GPU](#gpu-1) + - [Model Description](#model-description) + - [Evaluation Performance](#evaluation-performance) + - [Inference Performance](#inference-performance) + - [Description of Random Situation](#description-of-random-situation) + - [ModelZoo HomePage](#modelzoo-homepage) ## Description @@ -259,8 +264,8 @@ Inference result will be stored in the example path, whose folder name is "eval" | -------------------------- | -------------------------------------- |---------------------------------- | | Model Version | ResNet50-v1.5 |ResNet50-v1.5| | Resource | Ascend 910; CPU 2.60GHz, 192cores; Memory 755G; OS Euler2.8 | GPU(Tesla V100 SXM2)，CPU 2.1GHz 24cores，Memory 128G -| uploaded Date | 06/01/2020 (month/day/year) | 09/23/2020(month/day/year) -| MindSpore Version | 0.3.0-alpha | 1.0.0 | +| uploaded Date | 07/05/2021 (month/day/year) | 07/05/2021(month/day/year) +| MindSpore Version | 1.3.0 | 1.3.0 | | Dataset | ImageNet2012 | ImageNet2012| | Training Parameters | epoch=45, steps per epoch=5004, batch_size = 32 |epoch=40, steps per epoch=5004, batch_size = 32 | | Optimizer | THOR |THOR| @@ -279,8 +284,8 @@ Inference result will be stored in the example path, whose folder name is "eval" | ------------------- | --------------------------- | --------------------------- | | Model Version | ResNet50-v1.5 | ResNet50-v1.5 | | Resource | Ascend 910; OS Euler2.8 | GPU | -| Uploaded Date | 06/01/2020 (month/day/year) | 09/23/2020(month/day/year) | -| MindSpore Version | 0.3.0-alpha | 1.0.0 | +| Uploaded Date | 07/05/2021 (month/day/year) | 07/05/2021(month/day/year) | +| MindSpore Version | 1.3.0 | 1.3.0 | | Dataset | ImageNet2012 | ImageNet2012 | | batch_size | 32 | 32 | | outputs | probability | probability | diff --git a/model_zoo/official/cv/resnet_thor/README_CN.md b/model_zoo/official/cv/resnet_thor/README_CN.md index 6fe49c79277..0cf733375fe 100644 --- a/model_zoo/official/cv/resnet_thor/README_CN.md +++ b/model_zoo/official/cv/resnet_thor/README_CN.md @@ -13,12 +13,16 @@ - [脚本代码结构](#脚本代码结构) - [脚本参数](#脚本参数) - [训练过程](#训练过程) + - [Ascend 910](#ascend-910) + - [GPU](#gpu) - [推理过程](#推理过程) + - [Ascend 910](#ascend-910-1) + - [GPU](#gpu-1) - [模型描述](#模型描述) - [训练性能](#训练性能) - [推理性能](#推理性能) - [随机情况说明](#随机情况说明) - - [ModelZoo首页](#ModelZoo首页) + - [ModelZoo首页](#modelzoo首页) @@ -265,8 +269,8 @@ epoch： 36 step: 5004，loss is 1.645802 | -------------------------- | -------------------------------------- | ---------------------------------- | | 模型版本 | ResNet50-v1.5 | ResNet50-v1.5 | | 资源 |Ascend 910；CPU 2.60GHz，192核；内存 755G；系统 Euler2.8 | GPU(Tesla V100 SXM2)-CPU 2.1GHz 24核-内存128G | -| 上传日期 | 2020-06-01 | 2020-09-23 | -| MindSpore版本 | 0.3.0-alpha | 1.0.0| +| 上传日期 | 2021-07-05 | 2021-07-05 | +| MindSpore版本 | 1.3.0 | 1.3.0| | 数据集 | ImageNet2012 | ImageNet2012 | | 训练参数 | epoch=45, steps per epoch=5004, batch_size = 32 |epoch=40, steps per epoch=5004, batch_size = 32 | | 优化器 |THOR|THOR | @@ -285,8 +289,8 @@ epoch： 36 step: 5004，loss is 1.645802 | ------------------- | --------------------------- | --------------------------- | | 模型版本 | ResNet50-v1.5 | ResNet50-v1.5 | | 资源 | Ascend 910；系统 Euler2.8 | GPU | -| 上传日期 | 2020-06-01 | 2020-09-23 | -| MindSpore版本 | 0.3.0-alpha | 1.0.0 | +| 上传日期 | 2021-07-05 | 2021-07-05 | +| MindSpore版本 | 1.3.0 | 1.3.0 | | 数据集 | ImageNet2012 | ImageNet2012 | | 批大小 | 32 | 32 | | 输出 | 概率 | 概率 | diff --git a/model_zoo/official/cv/resnext/README.md b/model_zoo/official/cv/resnext/README.md index c3661de4220..3b2d549830e 100644 --- a/model_zoo/official/cv/resnext/README.md +++ b/model_zoo/official/cv/resnext/README.md @@ -1,23 +1,30 @@ # Contents +- [Contents](#contents) - [ResNeXt Description](#resnext-description) -- [Model Architecture](#model-architecture) +- [Model architecture](#model-architecture) - [Dataset](#dataset) - [Features](#features) -- [Mixed Precision](#mixed-precision) + - [Mixed Precision](#mixed-precision) - [Environment Requirements](#environment-requirements) -- [Quick Start](#quick-start) -- [Script Description](#script-description) - - [Script and Sample Code](#script-and-sample-code) +- [Script description](#script-description) + - [Script and sample code](#script-and-sample-code) - [Script Parameters](#script-parameters) - [Training Process](#training-process) + - [Usage](#usage) + - [Launch](#launch) - [Evaluation Process](#evaluation-process) + - [Usage](#usage-1) + - [Launch](#launch-1) + - [Result](#result) - [Model Export](#model-export) - [Inference Process](#inference-process) -- [Model Description](#model-description) - - [Performance](#performance) - - [Training Performance](#evaluation-performance) - - [Inference Performance](#evaluation-performance) + - [Usage](#usage-2) + - [result](#result-1) +- [Model description](#model-description) + - [Performance](#performance) + - [Training Performance](#training-performance) + - [Inference Performance](#inference-performance) - [Description of Random Situation](#description-of-random-situation) - [ModelZoo Homepage](#modelzoo-homepage) @@ -311,8 +318,8 @@ Total data:50000, top1 accuracy:0.79858, top5 accuracy:0.94716 | Parameters | ResNeXt50 | | | -------------------------- | ---------------------------------------------------------- | ------------------------- | | Resource | Ascend 910; cpu 2.60GHz, 192cores; memory 755G; OS Euler2.8 | NV SMX2 V100-32G | -| uploaded Date | 06/30/2020 | 07/23/2020 | -| MindSpore Version | 0.5.0 | 0.6.0 | +| uploaded Date | 07/05/2021 | 07/05/2021 | +| MindSpore Version | 1.3.0 | 1.3.0 | | Dataset | ImageNet | ImageNet | | Training Parameters | default_config.yaml | default_config.yaml | | Optimizer | Momentum | Momentum | @@ -339,8 +346,8 @@ Total data:50000, top1 accuracy:0.79858, top5 accuracy:0.94716 | Parameters | ResNeXt50 | | | | -------------------------- | ----------------------------- | ------------------------- | -------------------- | | Resource | Ascend 910; OS Euler2.8 | NV SMX2 V100-32G | Ascend 310 | -| uploaded Date | 06/30/2020 | 07/23/2020 | 07/23/2020 | -| MindSpore Version | 0.5.0 | 0.6.0 | 0.6.0 | +| uploaded Date | 07/05/2021 | 07/05/2021 | 07/05/2021 | +| MindSpore Version | 1.3.0 | 1.3.0 | 1.3.0 | | Dataset | ImageNet, 1.2W | ImageNet, 1.2W | ImageNet, 1.2W | | batch_size | 1 | 1 | 1 | | outputs | probability | probability | probability | diff --git a/model_zoo/official/cv/resnext/README_CN.md b/model_zoo/official/cv/resnext/README_CN.md index 635dcfdd709..56ac89e55fa 100644 --- a/model_zoo/official/cv/resnext/README_CN.md +++ b/model_zoo/official/cv/resnext/README_CN.md @@ -20,7 +20,7 @@ - [模型导出](#模型导出) - [推理过程](#推理过程) - [用法](#用法-2) - - [结果](#结果-2) + - [结果](#结果-1) - [模型描述](#模型描述) - [性能](#性能) - [训练性能](#训练性能) @@ -323,8 +323,8 @@ Total data:50000, top1 accuracy:0.79858, top5 accuracy:0.94716 | 参数 | ResNeXt50 | | | -------------------------- | ---------------------------------------------------------- | ------------------------- | | 资源 | Ascend 910；CPU 2.60GHz，192核；内存 755GB；系统 Euler2.8 | NV SMX2 V100-32G | -| 上传日期 | 2020-6-30 | 2020-7-23 | -| MindSpore版本 | 0.5.0 | 0.6.0 | +| 上传日期 | 2021-7-05 | 2021-07-05 | +| MindSpore版本 | 1.3.0 | 1.3.0 | | 数据集 | ImageNet | ImageNet | | 训练参数 | src/config.py | src/config.py | | 优化器 | Momentum | Momentum | @@ -339,8 +339,8 @@ Total data:50000, top1 accuracy:0.79858, top5 accuracy:0.94716 | 参数 |ResNeXt50 | | | | -------------------------- | ----------------------------- | ------------------------- | -------------------- | | 资源 | Ascend 910；系统 Euler2.8 | NV SMX2 V100-32G | Ascend 310 | -| 上传日期 | 2020-6-30 | 2020-7-23 | 2020-7-23 | -| MindSpore版本 | 0.5.0 | 0.6.0 | 0.6.0 | +| 上传日期 | 2021-7-05 | 2021-07-05 | 2021-07-05 | +| MindSpore版本 | 1.3.0 | 1.3.0 | 1.3.0 | | 数据集 | ImageNet， 1.2万 | ImageNet， 1.2万 | ImageNet， 1.2万 | | batch_size | 1 | 1 | 1 | | 输出 | 概率 | 概率 | 概率 | @@ -349,7 +349,7 @@ Total data:50000, top1 accuracy:0.79858, top5 accuracy:0.94716 | 参数 | ResNeXt101 | | ------------------- | --------------------------- | | 资源 | Ascend 310; OS Euler2.8 | -| 上传日期 | 22/06/2021 (month/day/year) | +| 上传日期 | 06/22/2021 (month/day/year) | | MindSpore版本 | 1.2.0 | | 数据集 | ImageNet | | batch_size | 1 | diff --git a/model_zoo/official/cv/ssd/README.md b/model_zoo/official/cv/ssd/README.md index 421c2bfea97..a17c4a694ae 100644 --- a/model_zoo/official/cv/ssd/README.md +++ b/model_zoo/official/cv/ssd/README.md @@ -14,6 +14,7 @@ - [Training Process](#training-process) - [Training on Ascend](#training-on-ascend) - [Training on GPU](#training-on-gpu) + - [Evaluation while training](#evaluation-while-training) - [Transfer Training](#transfer-training) - [Evaluation Process](#evaluation-process) - [Evaluation on Ascend](#evaluation-on-ascend) @@ -545,8 +546,8 @@ mAP: 0.33880018942412393 | ------------------- | ----------------------------------------------------------------------------- | ----------------------------------------------------------------------------- | ----------------------------------------------------------------------------- | | Model Version | SSD V1 | SSD V1 | SSD-Mobilenet-V1-Fpn | | Resource | Ascend 910; CPU 2.60GHz, 192cores; Memory 755G; OS Euler2.8 | NV SMX2 V100-16G | Ascend 910; CPU 2.60GHz, 192cores; Memory 755G; OS Euler2.8 | -| uploaded Date | 09/15/2020 (month/day/year) | 09/24/2020 (month/day/year) | 01/13/2021 (month/day/year) | -| MindSpore Version | 1.0.0 | 1.0.0 | 1.1.0 | +| uploaded Date | 07/05/2021 (month/day/year) | 09/24/2020 (month/day/year) | 01/13/2021 (month/day/year) | +| MindSpore Version | 1.3.0 | 1.0.0 | 1.1.0 | | Dataset | COCO2017 | COCO2017 | COCO2017 | | Training Parameters | epoch = 500, batch_size = 32 | epoch = 800, batch_size = 32 | epoch = 60, batch_size = 32 | | Optimizer | Momentum | Momentum | Momentum | @@ -562,8 +563,8 @@ mAP: 0.33880018942412393 | ------------------- | --------------------------- | --------------------------- | --------------------------- | | Model Version | SSD V1 | SSD V1 | SSD-Mobilenet-V1-Fpn | | Resource | Ascend 910; OS Euler2.8 | GPU |Ascend 910; OS Euler2.8 | -| Uploaded Date | 09/15/2020 (month/day/year) | 09/24/2020 (month/day/year) | 09/24/2020 (month/day/year) | -| MindSpore Version | 1.0.0 | 1.0.0 | 1.1.0 | +| Uploaded Date | 07/05/2020 (month/day/year) | 09/24/2020 (month/day/year) | 09/24/2020 (month/day/year) | +| MindSpore Version | 1.3.0 | 1.0.0 | 1.1.0 | | Dataset | COCO2017 | COCO2017 | COCO2017 | | batch_size | 1 | 1 | 1 | | outputs | mAP | mAP | mAP | diff --git a/model_zoo/official/cv/ssd/README_CN.md b/model_zoo/official/cv/ssd/README_CN.md index 039d496292b..2bf7e1f1f9d 100644 --- a/model_zoo/official/cv/ssd/README_CN.md +++ b/model_zoo/official/cv/ssd/README_CN.md @@ -468,8 +468,8 @@ mAP: 0.33880018942412393 | -------------------------- | -------------------------------------------------------------| -------------------------------------------------------------| | 模型版本 | SSD V1 | SSD V1 | | 资源 | Ascend 910；CPU 2.60GHz，192核；内存 755GB；系统 Euler2.8 | NV SMX2 V100-16G | -| 上传日期 | 2020-06-01 | 2020-09-24 | -| MindSpore版本 | 0.3.0-alpha | 1.0.0 | +| 上传日期 | 2021-07-05 | 2020-09-24 | +| MindSpore版本 | 1.3.0 | 1.0.0 | | 数据集 | COCO2017 | COCO2017 | | 训练参数 | epoch = 500, batch_size = 32 | epoch = 800, batch_size = 32 | | 优化器 | Momentum | Momentum | @@ -485,8 +485,8 @@ mAP: 0.33880018942412393 | ------------------- | ----------------------------| ----------------------------| | 模型版本 | SSD V1 | SSD V1 | | 资源 | Ascend 910；系统 Euler2.8 | GPU | -| 上传日期 | 2020-06-01 | 2020-09-24 | -| MindSpore版本 | 0.3.0-alpha | 1.0.0 | +| 上传日期 | 2021-07-05 | 2020-09-24 | +| MindSpore版本 | 1.3.0 | 1.0.0 | | 数据集 | COCO2017 | COCO2017 | | batch_size | 1 | 1 | | 输出 | mAP | mAP | diff --git a/model_zoo/official/cv/vgg16/README.md b/model_zoo/official/cv/vgg16/README.md index 87ccec30949..d7ffcea64f3 100644 --- a/model_zoo/official/cv/vgg16/README.md +++ b/model_zoo/official/cv/vgg16/README.md @@ -1,30 +1,38 @@ # Contents -- [VGG Description](#vgg-description) -- [Model Architecture](#model-architecture) -- [Dataset](#dataset) -- [Features](#features) - - [Mixed Precision](#mixed-precision) -- [Environment Requirements](#environment-requirements) -- [Quick Start](#quick-start) -- [Script Description](#script-description) - - [Script and Sample Code](#script-and-sample-code) - - [Script Parameters](#script-parameters) - - [Parameter configuration](#parameter-configuration) - - [Training Process](#training-process) - - [Training](#training) - - [Evaluation Process](#evaluation-process) - - [Evaluation](#evaluation) +- [Contents](#contents) + - [VGG Description](#vgg-description) + - [Model Architecture](#model-architecture) + - [Dataset](#dataset) + - [Dataset used: CIFAR-10](#dataset-used-cifar-10) + - [Dataset used: ImageNet2012](#dataset-used-imagenet2012) + - [Dataset organize way](#dataset-organize-way) + - [Features](#features) + - [Mixed Precision](#mixed-precision) + - [Environment Requirements](#environment-requirements) + - [Quick Start](#quick-start) + - [Script Description](#script-description) + - [Script and Sample Code](#script-and-sample-code) + - [Script Parameters](#script-parameters) + - [Training](#training) + - [Evaluation](#evaluation) + - [Parameter configuration](#parameter-configuration) + - [Training Process](#training-process) + - [Training](#training-1) + - [Run vgg16 on Ascend](#run-vgg16-on-ascend) + - [Run vgg16 on GPU](#run-vgg16-on-gpu) + - [Evaluation Process](#evaluation-process) + - [Evaluation](#evaluation-1) - [Inference Process](#inference-process) - [Export MindIR](#export-mindir) - [Infer on Ascend310](#infer-on-ascend310) - [result](#result) -- [Model Description](#model-description) - - [Performance](#performance) - - [Training Performance](#training-performance) - - [Evaluation Performance](#evaluation-performance) -- [Description of Random Situation](#description-of-random-situation) -- [ModelZoo Homepage](#modelzoo-homepage) + - [Model Description](#model-description) + - [Performance](#performance) + - [Training Performance](#training-performance) + - [Evaluation Performance](#evaluation-performance) + - [Description of Random Situation](#description-of-random-situation) + - [ModelZoo Homepage](#modelzoo-homepage) ## [VGG Description](#contents) @@ -532,8 +540,8 @@ Inference result is saved in current path, you can find result like this in acc. | -------------------------- | ---------------------------------------------- |------------------------------------| | Model Version | VGG16 | VGG16 | | Resource | Ascend 910; CPU 2.60GHz, 192cores; Memory 755G; OS Euler2.8 |NV SMX2 V100-32G | -| uploaded Date | 10/28/2020 | 10/28/2020 | -| MindSpore Version | 1.0.0 | 1.0.0 | +| uploaded Date | 07/05/2021 | 07/05/2021 | +| MindSpore Version | 1.3.0 | 1.3.0 | | Dataset | CIFAR-10 |ImageNet2012 | | Training Parameters | epoch=70, steps=781, batch_size = 64, lr=0.1 |epoch=150, steps=40036, batch_size = 32, lr=0.1 | | Optimizer | Momentum |Momentum | @@ -551,8 +559,8 @@ Inference result is saved in current path, you can find result like this in acc. | ------------------- | --------------------------- |--------------------- | Model Version | VGG16 | VGG16 | | Resource | Ascend 910; OS Euler2.8 | GPU | -| Uploaded Date | 10/28/2020 | 10/28/2020 | -| MindSpore Version | 1.0.0 | 1.0.0 | +| Uploaded Date | 07/05/2021 | 07/05/2021 | +| MindSpore Version | 1.3.0 | 1.3.0 | | Dataset | CIFAR-10, 10,000 images |ImageNet2012, 5000 images | | batch_size | 64 | 32 | | outputs | probability | probability | diff --git a/model_zoo/official/cv/vgg16/README_CN.md b/model_zoo/official/cv/vgg16/README_CN.md index 294ceee5c2f..b0a7f79d164 100644 --- a/model_zoo/official/cv/vgg16/README_CN.md +++ b/model_zoo/official/cv/vgg16/README_CN.md @@ -3,31 +3,38 @@ - [目录](#目录) -- [VGG描述](#vgg描述) -- [模型架构](#模型架构) -- [数据集](#数据集) -- [特性](#特性) - - [混合精度](#混合精度) -- [环境要求](#环境要求) -- [快速入门](#快速入门) -- [脚本说明](#脚本说明) - - [脚本及样例代码](#脚本及样例代码) - - [脚本参数](#脚本参数) - - [训练](#训练) - - [评估](#评估) - - [参数配置](#参数配置) - - [训练过程](#训练过程) - - [训练](#训练-1) - - [Ascend处理器环境运行VGG16](#ascend处理器环境运行vgg16) - - [GPU处理器环境运行VGG16](#gpu处理器环境运行vgg16) - - [评估过程](#评估过程) - - [评估](#评估-1) -- [模型描述](#模型描述) - - [性能](#性能) - - [训练性能](#训练性能) - - [评估性能](#评估性能) -- [随机情况说明](#随机情况说明) -- [ModelZoo主页](#modelzoo主页) + - [VGG描述](#vgg描述) + - [模型架构](#模型架构) + - [数据集](#数据集) + - [使用的数据集：CIFAR-10](#使用的数据集cifar-10) + - [使用的数据集：ImageNet2012](#使用的数据集imagenet2012) + - [数据集组织方式](#数据集组织方式) + - [特性](#特性) + - [混合精度](#混合精度) + - [环境要求](#环境要求) + - [快速入门](#快速入门) + - [脚本说明](#脚本说明) + - [脚本及样例代码](#脚本及样例代码) + - [脚本参数](#脚本参数) + - [训练](#训练) + - [评估](#评估) + - [参数配置](#参数配置) + - [训练过程](#训练过程) + - [训练](#训练-1) + - [Ascend处理器环境运行VGG16](#ascend处理器环境运行vgg16) + - [GPU处理器环境运行VGG16](#gpu处理器环境运行vgg16) + - [评估过程](#评估过程) + - [评估](#评估-1) + - [推理过程](#推理过程) + - [导出MindIR](#导出mindir) + - [在Ascend310执行推理](#在ascend310执行推理) + - [结果](#结果) + - [模型描述](#模型描述) + - [性能](#性能) + - [训练性能](#训练性能) + - [评估性能](#评估性能) + - [随机情况说明](#随机情况说明) + - [ModelZoo主页](#modelzoo主页) @@ -536,8 +543,8 @@ bash run_infer_310.sh [MINDIR_PATH] [DATASET_NAME] [DATASET_PATH] [NEED_PREPROCE | -------------------------- | ---------------------------------------------- |------------------------------------| | 模型版本 | VGG16 | VGG16 | | 资源 | Ascend 910；CPU 2.60GHz，192核；内存 755GB；系统 Euler2.8 |NV SMX2 V100-32G | -| 上传日期 | 2020-08-20 | 2020-08-20 | -| MindSpore版本 | 0.5.0-alpha |0.5.0-alpha | +| 上传日期 | 2021-07-05 | 2021-07-05 | +| MindSpore版本 | 1.3.0 |1.3.0 | | 数据集 | CIFAR-10 |ImageNet2012 | | 训练参数 | epoch=70, steps=781, batch_size = 64, lr=0.1 |epoch=150, steps=40036, batch_size = 32, lr=0.1 | | 优化器 | Momentum | Momentum | @@ -555,8 +562,8 @@ bash run_infer_310.sh [MINDIR_PATH] [DATASET_NAME] [DATASET_PATH] [NEED_PREPROCE | ------------------- | --------------------------- |--------------------- | 模型版本 | VGG16 | VGG16 | | 资源 | Ascend 910；系统 Euler2.8 | GPU | -| 上传日期 | 2020-08-20 | 2020-08-20 | -| MindSpore版本 | 0.5.0-alpha |0.5.0-alpha | +| 上传日期 | 2021-07-05 | 2021-07-05 | +| MindSpore版本 | 1.3.0 |1.3.0 | | 数据集 | CIFAR-10，10000张图像 | ImageNet2012，5000张图像 | | batch_size | 64 | 32 | | 输出 | 概率 | 概率 | diff --git a/model_zoo/official/cv/warpctc/README.md b/model_zoo/official/cv/warpctc/README.md index 5d8b392a39d..d5e9ed7a9ec 100644 --- a/model_zoo/official/cv/warpctc/README.md +++ b/model_zoo/official/cv/warpctc/README.md @@ -1,32 +1,33 @@ # Contents -- [WarpCTC Description](#warpctc-description) -- [Model Architecture](#model-architecture) -- [Dataset](#dataset) -- [Environment Requirements](#environment-requirements) -- [Quick Start](#quick-start) -- [Script Description](#script-description) - - [Script and Sample Code](#script-and-sample-code) - - [Script Parameters](#script-parameters) - - [Training Script Parameters](#training-script-parameters) - - [Parameters Configuration](#parameters-configuration) +- [Contents](#contents) + - [WarpCTC Description](#warpctc-description) + - [Model Architecture](#model-architecture) + - [Dataset](#dataset) + - [Environment Requirements](#environment-requirements) + - [Quick Start](#quick-start) + - [Script Description](#script-description) + - [Script and Sample Code](#script-and-sample-code) + - [Script Parameters](#script-parameters) + - [Training Script Parameters](#training-script-parameters) + - [Parameters Configuration](#parameters-configuration) - [Dataset Preparation](#dataset-preparation) - - [Training Process](#training-process) - - [Training](#training) - - [Distributed Training](#distributed-training) - - [Evaluation Process](#evaluation-process) - - [Evaluation](#evaluation) + - [Training Process](#training-process) + - [Training](#training) + - [Distributed Training](#distributed-training) + - [Evaluation Process](#evaluation-process) + - [Evaluation](#evaluation) - [Inference Process](#inference-process) - [Export MindIR](#export-mindir) - [Infer on Ascend310](#infer-on-ascend310) - [result](#result) -- [Model Description](#model-description) - - [Performance](#performance) - - [Training Performance](#training-performance) - - [Evaluation Performance](#evaluation-performance) - - [Inference Performance](#inference-performance) -- [Description of Random Situation](#description-of-random-situation) -- [ModelZoo Homepage](#modelzoo-homepage) + - [Model Description](#model-description) + - [Performance](#performance) + - [Training Performance](#training-performance) + - [Evaluation Performance](#evaluation-performance) + - [Inference Performance](#inference-performance) + - [Description of Random Situation](#description-of-random-situation) + - [ModelZoo Homepage](#modelzoo-homepage) ## [WarpCTC Description](#contents) @@ -348,8 +349,8 @@ Inference result is saved in current path, you can find result like this in acc. | -------------------------- | --------------------------------------------- |---------------------------------- | | Model Version | v1.0 | v1.0 | | Resource | Ascend 910; CPU 2.60GHz, 192cores; Memory 755G; OS Euler2.8 | GPU(Tesla V100 SXM2)，CPU 2.1GHz 24cores，Memory 128G / -| uploaded Date | 07/01/2020 (month/day/year) | 08/01/2020 (month/day/year) | -| MindSpore Version | 0.5.0-alpha | 0.6.0-alpha | +| uploaded Date | 07/05/2021 (month/day/year) | 07/05/2021 (month/day/year) | +| MindSpore Version | 1.3.0 | 1.3.0 | | Dataset | Captcha | Captcha | | Training Parameters | epoch=30, steps per epoch=98, batch_size = 64 | epoch=30, steps per epoch=98, batch_size = 64 | | Optimizer | SGD | SGD | @@ -368,8 +369,8 @@ Inference result is saved in current path, you can find result like this in acc. | ------------------- | --------------------------- | | Model Version | V1.0 | | Resource | Ascend 910; OS Euler2.8 | -| Uploaded Date | 08/01/2020 (month/day/year) | -| MindSpore Version | 0.6.0-alpha | +| Uploaded Date | 07/05/2021 (month/day/year) | +| MindSpore Version | 1.3.0 | | Dataset | Captcha | | batch_size | 64 | | outputs | ACC | diff --git a/model_zoo/official/cv/warpctc/README_CN.md b/model_zoo/official/cv/warpctc/README_CN.md index 37727c6ea3f..718f0a188f7 100644 --- a/model_zoo/official/cv/warpctc/README_CN.md +++ b/model_zoo/official/cv/warpctc/README_CN.md @@ -3,15 +3,15 @@ - [目录](#目录) -- [WarpCTC描述](#warpctc描述) -- [模型架构](#模型架构) -- [数据集](#数据集) -- [环境要求](#环境要求) -- [快速入门](#快速入门) -- [脚本说明](#脚本说明) - - [脚本及样例代码](#脚本及样例代码) - - [脚本参数](#脚本参数) - - [训练脚本参数](#训练脚本参数) + - [WarpCTC描述](#warpctc描述) + - [模型架构](#模型架构) + - [数据集](#数据集) + - [环境要求](#环境要求) + - [快速入门](#快速入门) + - [脚本说明](#脚本说明) + - [脚本及样例代码](#脚本及样例代码) + - [脚本参数](#脚本参数) + - [训练脚本参数](#训练脚本参数) - [参数配置](#参数配置) - [数据集准备](#数据集准备) - [训练过程](#训练过程) @@ -23,13 +23,13 @@ - [导出MindIR](#导出mindir) - [在Ascend310执行推理](#在ascend310执行推理) - [结果](#结果) -- [模型描述](#模型描述) - - [性能](#性能) - - [训练性能](#训练性能) - - [评估性能](#评估性能) + - [模型描述](#模型描述) + - [性能](#性能) + - [训练性能](#训练性能) + - [评估性能](#评估性能) - [推理性能](#推理性能) -- [随机情况说明](#随机情况说明) -- [ModelZoo主页](#modelzoo主页) + - [随机情况说明](#随机情况说明) + - [ModelZoo主页](#modelzoo主页) @@ -352,8 +352,8 @@ bash run_infer_310.sh [MINDIR_PATH] [DATA_PATH] [DEVICE_ID] | -------------------------- | --------------------------------------------- |---------------------------------- | | 模型版本 | v1.0 | v1.0 | | 资源 | Ascend 910；CPU 2.60GHz，192核；内存 755G；系统 Euler2.8 | GPU(Tesla V100 SXM2)，CPU 2.1GHz 24核，内存： 128G -| 上传日期 | 2020-07-01 | 2020-08-01 | -| MindSpore版本 | 0.5.0-alpha | 0.6.0-alpha | +| 上传日期 | 2021-07-05 | 2021-07-05 | +| MindSpore版本 | 1.3.0 | 1.3.0 | | 数据集 | Captcha | Captcha | | 训练参数 | epoch=30, steps per epoch=98, batch_size = 64 | epoch=30, steps per epoch=98, batch_size = 64 | | 优化器 | SGD | SGD | @@ -372,8 +372,8 @@ bash run_infer_310.sh [MINDIR_PATH] [DATA_PATH] [DEVICE_ID] | ------------------- | --------------------------- | | 模型版本 | V1.0 | | 资源 |Ascend 910；系统 Euler2.8 | -| 上传日期 | 2020-08-01 | -| MindSpore版本 | 0.6.0-alpha | +| 上传日期 | 2021-07-05 | +| MindSpore版本 | 1.3.0 | | 数据集 | Captcha | | batch_size | 64 | | 输出 | ACC | diff --git a/model_zoo/official/cv/yolov3_darknet53_quant/README_CN.md b/model_zoo/official/cv/yolov3_darknet53_quant/README_CN.md index ca272df73c0..26e0469ce8a 100644 --- a/model_zoo/official/cv/yolov3_darknet53_quant/README_CN.md +++ b/model_zoo/official/cv/yolov3_darknet53_quant/README_CN.md @@ -3,25 +3,27 @@ - [目录](#目录) -- [YOLOv3-DarkNet53-Quant描述](#yolov3-darknet53-quant描述) -- [模型架构](#模型架构) -- [数据集](#数据集) -- [环境要求](#环境要求) -- [快速入门](#快速入门) -- [脚本说明](#脚本说明) - - [脚本及样例代码](#脚本及样例代码) - - [脚本参数](#脚本参数) - - [训练过程](#训练过程) - - [Ascend上训练](#ascend上训练) - - [分布式训练](#分布式训练) - - [评估过程](#评估过程) - - [Ascend评估](#ascend评估) -- [模型描述](#模型描述) - - [性能](#性能) - - [评估性能](#评估性能) - - [推理性能](#推理性能) -- [随机情况说明](#随机情况说明) -- [ModelZoo主页](#modelzoo主页) + - [YOLOv3-DarkNet53-Quant描述](#yolov3-darknet53-quant描述) + - [模型架构](#模型架构) + - [数据集](#数据集) + - [环境要求](#环境要求) + - [快速入门](#快速入门) + - [脚本说明](#脚本说明) + - [脚本及样例代码](#脚本及样例代码) + - [脚本参数](#脚本参数) + - [训练过程](#训练过程) + - [Ascend上训练](#ascend上训练) + - [分布式训练](#分布式训练) + - [评估过程](#评估过程) + - [Ascend评估](#ascend评估) + - [模型导出](#模型导出) + - [Ascend 310 推理](#ascend-310-推理) + - [模型描述](#模型描述) + - [性能](#性能) + - [评估性能](#评估性能) + - [推理性能](#推理性能) + - [随机情况说明](#随机情况说明) + - [ModelZoo主页](#modelzoo主页) diff --git a/model_zoo/official/cv/yolov3_resnet18/README.md b/model_zoo/official/cv/yolov3_resnet18/README.md index 5d420840b32..4e630b17652 100644 --- a/model_zoo/official/cv/yolov3_resnet18/README.md +++ b/model_zoo/official/cv/yolov3_resnet18/README.md @@ -1,5 +1,6 @@ # Contents +- [Contents](#contents) - [YOLOv3_ResNet18 Description](#yolov3_resnet18-description) - [Model Architecture](#model-architecture) - [Dataset](#dataset) @@ -9,15 +10,17 @@ - [Script and Sample Code](#script-and-sample-code) - [Script Parameters](#script-parameters) - [Training Process](#training-process) - - [Training](#training) + - [Training on Ascend](#training-on-ascend) - [Evaluation Process](#evaluation-process) - - [Evaluation](#evaluation) + - [Evaluation on Ascend](#evaluation-on-ascend) - [Export MindIR](#export-mindir) - [Inference Process](#inference-process) + - [Usage](#usage) + - [result](#result) - [Model Description](#model-description) - - [Performance](#performance) + - [Performance](#performance) - [Evaluation Performance](#evaluation-performance) - - [Inference Performance](#evaluation-performance) + - [Inference Performance](#inference-performance) - [Description of Random Situation](#description-of-random-situation) - [ModelZoo Homepage](#modelzoo-homepage) @@ -365,8 +368,8 @@ Inference result is saved in current path, you can find result in acc.log file. | -------------------------- | ----------------------------------------------------------- | | Model Version | YOLOv3_Resnet18 V1 | | Resource | Ascend 910; CPU 2.60GHz, 192cores; Memory 755G; OS Euler2.8 | -| uploaded Date | 09/15/2020 (month/day/year) | -| MindSpore Version | 1.0.0 | +| uploaded Date | 07/05/2021 (month/day/year) | +| MindSpore Version | 1.3.0 | | Dataset | COCO2017 | | Training Parameters | epoch = 160, batch_size = 32, lr = 0.005 | | Optimizer | Adam | @@ -383,8 +386,8 @@ Inference result is saved in current path, you can find result in acc.log file. | ------------------- | ----------------------------------------------- | | Model Version | YOLOv3_Resnet18 V1 | | Resource | Ascend 910; OS Euler2.8 | -| Uploaded Date | 09/15/2020 (month/day/year) | -| MindSpore Version | 1.0.0 | +| Uploaded Date | 07/05/2021 (month/day/year) | +| MindSpore Version | 1.3.0 | | Dataset | COCO2017 | | batch_size | 1 | | outputs | presion and recall | diff --git a/model_zoo/official/cv/yolov3_resnet18/README_CN.md b/model_zoo/official/cv/yolov3_resnet18/README_CN.md index 8dd749eb65c..f4f9e9eadcf 100644 --- a/model_zoo/official/cv/yolov3_resnet18/README_CN.md +++ b/model_zoo/official/cv/yolov3_resnet18/README_CN.md @@ -17,8 +17,8 @@ - [Ascend评估](#ascend评估) - [导出mindir模型](#导出mindir模型) - [推理过程](#推理过程) - - [用法](#用法-2) - - [结果](#结果-2) + - [用法](#用法) + - [结果](#结果) - [模型描述](#模型描述) - [性能](#性能) - [评估性能](#评估性能) @@ -365,8 +365,8 @@ bash run_infer_310.sh [MINDIR_PATH] [DATA_PATH] [ANNO_PATH] [DEVICE_ID] | -------------------------- | ----------------------------------------------------------- | | 模型版本 | YOLOv3_Resnet18 V1 | | 资源 | Ascend 910；CPU 2.60GHz，192核；内存 755G；系统 Euler2.8 | -| 上传日期 | 2020-06-01 | -| MindSpore版本 | 0.2.0-alpha | +| 上传日期 | 2021-07-05 | +| MindSpore版本 | 1.3.0 | | 数据集 | COCO2017 | | 训练参数 | epoch = 150, batch_size = 32, lr = 0.001 | | 优化器 | Adam | @@ -383,8 +383,8 @@ bash run_infer_310.sh [MINDIR_PATH] [DATA_PATH] [ANNO_PATH] [DEVICE_ID] | ------------------- | ----------------------------------------------- | | 模型版本 | YOLOv3_Resnet18 V1 | | 资源 | Ascend 910；系统 Euler2.8 | -| 上传日期 | 2020-06-01 | -| MindSpore版本 | 0.2.0-alpha | +| 上传日期 | 2021-07-05 | +| MindSpore版本 | 1.3.0 | | 数据集 | COCO2017 | | batch_size | 1 | | 输出 | 精度和召回 | diff --git a/model_zoo/official/cv/yolov4/README_CN.md b/model_zoo/official/cv/yolov4/README_CN.md index 1aa90cca9d5..d14e2133f49 100644 --- a/model_zoo/official/cv/yolov4/README_CN.md +++ b/model_zoo/official/cv/yolov4/README_CN.md @@ -1,5 +1,6 @@ # 目录 +- [目录](#目录) - [YOLOv4说明](#yolov4说明) - [模型架构](#模型架构) - [预训练模型](#预训练模型) @@ -7,18 +8,25 @@ - [环境要求](#环境要求) - [快速入门](#快速入门) - [脚本说明](#脚本说明) -- [脚本和示例代码](#脚本和示例代码) + - [脚本和示例代码](#脚本和示例代码) - [脚本参数](#脚本参数) - [训练过程](#训练过程) - [训练](#训练) + - [分布式训练](#分布式训练) + - [迁移学习](#迁移学习) - [评估过程](#评估过程) - - [评估](#评估) + - [验证](#验证) + - [Test-dev](#test-dev) - [转换过程](#转换过程) - [转换](#转换) + - [推理过程](#推理过程) + - [用法](#用法) + - [结果](#结果) - [模型说明](#模型说明) - [性能](#性能) - [评估性能](#评估性能) - [推理性能](#推理性能) +- [随机情况说明](#随机情况说明) - [ModelZoo主页](#modelzoo主页) # [YOLOv4说明](#目录) diff --git a/model_zoo/official/gnn/gat/README.md b/model_zoo/official/gnn/gat/README.md index af2de31d569..7369204321e 100644 --- a/model_zoo/official/gnn/gat/README.md +++ b/model_zoo/official/gnn/gat/README.md @@ -2,28 +2,27 @@ -- [Graph Attention Networks Description](#graph-attention-networks-description) -- [Model architecture](#model-architecture) -- [Dataset](#dataset) -- [Features](#features) - - [Mixed Precision](#mixed-precision) -- [Environment Requirements](#environment-requirements) -- [Quick Start](#quick-start) -- [Script Description](#script-description) +- [Contents](#contents) + - [Graph Attention Networks Description](#graph-attention-networks-description) + - [Model architecture](#model-architecture) + - [Dataset](#dataset) + - [Features](#features) + - [Mixed Precision](#mixed-precision) + - [Environment Requirements](#environment-requirements) + - [Quick Start](#quick-start) + - [Script Description](#script-description) - [Script and Sample Code](#script-and-sample-code) - [Script Parameters](#script-parameters) - [Training Process](#training-process) - - [Training](#training) + - [Training](#training) - [Inference Process](#inference-process) - [Export MindIR](#export-mindir) - [Infer on Ascend310](#infer-on-ascend310) - [result](#result) -- [Model Description](#model-description) - - [Performance](#performance) - - [Evaluation Performance](#evaluation-performance) - - [Inference Performance](#evaluation-performance) -- [Description of random situation](#description-of-random-situation) -- [ModelZoo Homepage](#modelzoo-homepage) + - [Model Description](#model-description) + - [Performance](#performance) + - [Description of random situation](#description-of-random-situation) + - [ModelZoo Homepage](#modelzoo-homepage) @@ -273,8 +272,8 @@ test acc=0.84199995 | Parameter | GAT | | ------------------------------------ | ----------------------------------------- | | Resource | Ascend 910; OS Euler2.8 | -| uploaded Date | 06/16/2020(month/day/year) | -| MindSpore Version | 1.0.0 | +| uploaded Date | 07/05/2021(month/day/year) | +| MindSpore Version | 1.3.0 | | Dataset | Cora/Citeseer | | Training Parameter | epoch=200 | | Optimizer | Adam | diff --git a/model_zoo/official/gnn/gat/README_CN.md b/model_zoo/official/gnn/gat/README_CN.md index 800cb6b21a4..c277fe48ae5 100644 --- a/model_zoo/official/gnn/gat/README_CN.md +++ b/model_zoo/official/gnn/gat/README_CN.md @@ -3,26 +3,26 @@ - [目录](#目录) -- [图注意力网络描述](#图注意力网络描述) -- [模型架构](#模型架构) -- [数据集](#数据集) -- [特性](#特性) - - [混合精度](#混合精度) -- [环境要求](#环境要求) -- [快速入门](#快速入门) -- [脚本说明](#脚本说明) - - [脚本及样例代码](#脚本及样例代码) - - [脚本参数](#脚本参数) - - [训练过程](#训练过程) - - [训练](#训练) + - [图注意力网络描述](#图注意力网络描述) + - [模型架构](#模型架构) + - [数据集](#数据集) + - [特性](#特性) + - [混合精度](#混合精度) + - [环境要求](#环境要求) + - [快速入门](#快速入门) + - [脚本说明](#脚本说明) + - [脚本及样例代码](#脚本及样例代码) + - [脚本参数](#脚本参数) + - [训练过程](#训练过程) + - [训练](#训练) - [推理过程](#推理过程) - [导出MindIR](#导出mindir) - [在Ascend310执行推理](#在ascend310执行推理) - - [结果](#结果) -- [模型描述](#模型描述) - - [性能](#性能) -- [随机情况说明](#随机情况说明) -- [ModelZoo主页](#modelzoo主页) + - [result](#result) + - [模型描述](#模型描述) + - [性能](#性能) + - [随机情况说明](#随机情况说明) + - [ModelZoo主页](#modelzoo主页) @@ -269,8 +269,8 @@ test acc=0.84199995 | 参数 | GAT | | ------------------------------------ | ----------------------------------------- | | 资源 | Ascend 910；系统 Euler2.8 | -| 上传日期 | 2020-06-16 | -| MindSpore版本 | 0.5.0-beta | +| 上传日期 | 2021-07-05 | +| MindSpore版本 | 1.3.0 | | 数据集 | Cora/Citeseer | | 训练参数 | epoch=200 | | 优化器 | Adam | diff --git a/model_zoo/official/gnn/gcn/README.md b/model_zoo/official/gnn/gcn/README.md index 6edb8e84f71..a95d00492d3 100644 --- a/model_zoo/official/gnn/gcn/README.md +++ b/model_zoo/official/gnn/gcn/README.md @@ -1,22 +1,28 @@ # Contents -- [GCN Description](#gcn-description) -- [Model Architecture](#model-architecture) -- [Dataset](#dataset) -- [Environment Requirements](#environment-requirements) -- [Quick Start](#quick-start) -- [Script Description](#script-description) - - [Script and Sample Code](#script-and-sample-code) +- [Contents](#contents) + - [GCN Description](#gcn-description) + - [Model Architecture](#model-architecture) + - [Dataset](#dataset) + - [Environment Requirements](#environment-requirements) + - [Quick Start](#quick-start) + - [Usage](#usage) + - [Launch](#launch) + - [Script Description](#script-description) + - [Script and Sample Code](#script-and-sample-code) - [Script Parameters](#script-parameters) - - [Training, Evaluation, Test Process](#training-evaluation-test-process) + - [Training, Evaluation, Test Process](#training-evaluation-test-process) + - [Usage](#usage-1) + - [Launch](#launch-1) + - [Result](#result) - [Inference Process](#inference-process) - [Export MindIR](#export-mindir) - [Infer on Ascend310](#infer-on-ascend310) - - [result](#result) -- [Model Description](#model-description) - - [Performance](#performance) -- [Description of Random Situation](#description-of-random-situation) -- [ModelZoo Homepage](#modelzoo-homepage) + - [result](#result-1) + - [Model Description](#model-description) + - [Performance](#performance) + - [Description of Random Situation](#description-of-random-situation) + - [ModelZoo Homepage](#modelzoo-homepage) ## [GCN Description](#contents) @@ -253,8 +259,8 @@ Test set results: accuracy= 0.81300 | Parameters | GCN | | -------------------------- | -------------------------------------------------------------- | | Resource | Ascend 910; OS Euler2.8 | -| uploaded Date | 06/09/2020 (month/day/year) | -| MindSpore Version | 1.0.0 | +| uploaded Date | 07/05/2021 (month/day/year) | +| MindSpore Version | 1.3.0 | | Dataset | Cora/Citeseer | | Training Parameters | epoch=200 | | Optimizer | Adam | diff --git a/model_zoo/official/gnn/gcn/README_CN.md b/model_zoo/official/gnn/gcn/README_CN.md index 0d849a46372..b87a1536208 100644 --- a/model_zoo/official/gnn/gcn/README_CN.md +++ b/model_zoo/official/gnn/gcn/README_CN.md @@ -3,28 +3,28 @@ - [目录](#目录) -- [图卷积网络描述](#图卷积网络描述) -- [模型架构](#模型架构) -- [数据集](#数据集) -- [环境要求](#环境要求) -- [快速入门](#快速入门) - - [用法](#用法) - - [启动](#启动) -- [脚本说明](#脚本说明) - - [脚本及样例代码](#脚本及样例代码) - - [脚本参数](#脚本参数) - - [培训、评估、测试过程](#培训评估测试过程) - - [用法](#用法-1) - - [启动](#启动-1) - - [结果](#结果) + - [图卷积网络描述](#图卷积网络描述) + - [模型架构](#模型架构) + - [数据集](#数据集) + - [环境要求](#环境要求) + - [快速入门](#快速入门) + - [用法](#用法) + - [启动](#启动) + - [脚本说明](#脚本说明) + - [脚本及样例代码](#脚本及样例代码) + - [脚本参数](#脚本参数) + - [培训、评估、测试过程](#培训评估测试过程) + - [用法](#用法-1) + - [启动](#启动-1) + - [结果](#结果) - [推理过程](#推理过程) - [导出MindIR](#导出mindir) - [在Ascend310执行推理](#在ascend310执行推理) - - [结果](#结果) -- [模型描述](#模型描述) - - [性能](#性能) -- [随机情况说明](#随机情况说明) -- [ModelZoo主页](#modelzoo主页) + - [result](#result) + - [模型描述](#模型描述) + - [性能](#性能) + - [随机情况说明](#随机情况说明) + - [ModelZoo主页](#modelzoo主页) @@ -261,8 +261,8 @@ Test set results: accuracy= 0.81300 | 参数 | GCN | | -------------------------- | -------------------------------------------------------------- | | 资源 | Ascend 910；系统 Euler2.8 | -| 上传日期 | 2020-06-09 | -| MindSpore版本 | 0.5.0-beta | +| 上传日期 | 2021-07-05 | +| MindSpore版本 | 1.3.0 | | 数据集 | Cora/Citeseer | | 训练参数 | epoch=200 | | 优化器 | Adam | diff --git a/model_zoo/official/nlp/bert/README.md b/model_zoo/official/nlp/bert/README.md index 4cf07cc7cdf..ff091011be9 100644 --- a/model_zoo/official/nlp/bert/README.md +++ b/model_zoo/official/nlp/bert/README.md @@ -29,8 +29,10 @@ - [evaluation on cluener dataset when running on Ascend](#evaluation-on-cluener-dataset-when-running-on-ascend) - [evaluation on msra dataset when running on Ascend](#evaluation-on-msra-dataset-when-running-on-ascend) - [evaluation on squad v1.1 dataset when running on Ascend](#evaluation-on-squad-v11-dataset-when-running-on-ascend) - - [Export MindIR](#export-mindir) - - [Inference Process](#inference-process) + - [Export MindIR](#export-mindir) + - [Inference Process](#inference-process) + - [Usage](#usage) + - [result](#result) - [Model Description](#model-description) - [Performance](#performance) - [Pretraining Performance](#pretraining-performance) @@ -720,18 +722,18 @@ F1 0.931243 | -------------------------- | ---------------------------------------------------------- | ------------------------- | | Model Version | BERT_base | BERT_base | | Resource | Ascend 910; cpu 2.60GHz, 192cores; memory 755G; OS Euler2.8 | NV SMX2 V100-16G, cpu: Intel(R) Xeon(R) Platinum 8160 CPU @2.10GHz, memory: 256G | -| uploaded Date | 08/22/2020 | 05/06/2020 | -| MindSpore Version | 1.0.0 | 1.0.0 | +| uploaded Date | 07/05/2021 | 07/05/2021 | +| MindSpore Version | 1.3.0 | 1.3.0 | | Dataset | cn-wiki-128(4000w) | cn-wiki-128(4000w) | -| Training Parameters | src/config.py | src/config.py | +| Training Parameters | pretrain_config.yaml | pretrain_config.yaml | | Optimizer | Lamb | AdamWeightDecay | | Loss Function | SoftmaxCrossEntropy | SoftmaxCrossEntropy | | outputs | probability | probability | | Epoch | 40 | 40 | | Batch_size | 256*8 | 32*8 | | Loss | 1.7 | 1.7 | -| Speed | 340ms/step | 290ms/step | -| Total time | 73h | 610H | +| Speed | 284ms/step | 180ms/step | +| Total time | 63H | 610H | | Params (M) | 110M | 110M | | Checkpoint for Fine tuning | 1.2G(.ckpt file) | 1.2G(.ckpt file) | | Scripts | [BERT_base](https://gitee.com/mindspore/mindspore/tree/master/model_zoo/official/nlp/bert) | [BERT_base](https://gitee.com/mindspore/mindspore/tree/master/model_zoo/official/nlp/bert) | @@ -740,8 +742,8 @@ F1 0.931243 | -------------------------- | ---------------------------------------------------------- | | Model Version | BERT_NEZHA | | Resource | Ascend 910; cpu 2.60GHz, 192cores; memory 755G; OS Euler2.8 | -| uploaded Date | 08/20/2020 | -| MindSpore Version | 1.0.0 | +| uploaded Date | 07/05/2021 | +| MindSpore Version | 1.3.0 | | Dataset | cn-wiki-128(4000w) | | Training Parameters | src/config.py | | Optimizer | Lamb | @@ -750,8 +752,8 @@ F1 0.931243 | Epoch | 40 | | Batch_size | 96*8 | | Loss | 1.7 | -| Speed | 360ms/step | -| Total time | 200h | +| Speed | 320ms/step | +| Total time | 180h | | Params (M) | 340M | | Checkpoint for Fine tuning | 3.2G(.ckpt file) | | Scripts | [BERT_NEZHA](https://gitee.com/mindspore/mindspore/tree/master/model_zoo/official/nlp/bert) | @@ -762,8 +764,8 @@ F1 0.931243 | -------------------------- | ----------------------------- | | Model Version | | | Resource | Ascend 910; OS Euler2.8 | -| uploaded Date | 08/22/2020 | -| MindSpore Version | 1.0.0 | +| uploaded Date | 07/05/2021 | +| MindSpore Version | 1.3.0 | | Dataset | cola, 1.2W | | batch_size | 32(1P) | | Accuracy | 0.588986 | diff --git a/model_zoo/official/nlp/bert/README_CN.md b/model_zoo/official/nlp/bert/README_CN.md index 764eea4fdba..76718d870fb 100644 --- a/model_zoo/official/nlp/bert/README_CN.md +++ b/model_zoo/official/nlp/bert/README_CN.md @@ -33,7 +33,7 @@ - [导出mindir模型](#导出mindir模型) - [推理过程](#推理过程) - [用法](#用法-2) - - [结果](#结果-2) + - [结果](#结果) - [模型描述](#模型描述) - [性能](#性能) - [预训练性能](#预训练性能) @@ -682,54 +682,54 @@ F1 0.931243 | -------------------------- | ---------------------------------------------------------- | ------------------------- | | 模型版本 | BERT_base | BERT_base | | 资源 |Ascend 910；CPU 2.60GHz，192核；内存 755GB；系统 Euler2.8 || NV SMX2 V100-32G | -| 上传日期 | 2020-08-22 | 2020-05-06 | -| MindSpore版本 | 0.6.0 | 0.3.0 | -| 数据集 | cn-wiki-128(4000w) | ImageNet | -| 训练参数 | src/gd_config.py | src/gd_config.py | -| 优化器 | Lamb | Momentum | +| 上传日期 | 2021-07-05 | 2021-07-05 | +| MindSpore版本 | 1.3.0 | 1.3.0 | +| 数据集 | cn-wiki-128(4000w) | cn-wiki-128 | +| 训练参数 | pretrain_config.yaml | pretrain_config.yaml | +| 优化器 | Lamb | Lamb | | 损失函数 | SoftmaxCrossEntropy | SoftmaxCrossEntropy | | 输出 | 概率 | | | 轮次 | 40 | | | -| Batch_size | 256*8 | 130（8卡） | | +| Batch_size | 256*8 | 32*8 | | 损失 | 1.7 | 1.913 | -| 速度 | 340毫秒/步 | 1.913 | -| 总时长 | 73小时 | | +| 速度 | 284毫秒/步 |180毫秒/步 | +| 总时长 | 63小时 | | | 参数（M） | 110 | | | 微调检查点 | 1.2G（.ckpt文件） | | -| 参数 | Ascend | GPU | -| -------------------------- | ---------------------------------------------------------- | ------------------------- | -| 模型版本 | BERT_NEZHA | BERT_NEZHA | -| 资源 | Ascend 910；CPU 2.60GHz，192核；内存 755GB；系统 Euler2.8 || NV SMX2 V100-32G | -| 上传日期 | 2020-08-20 | 2020-05-06 | -| MindSpore版本 | 0.6.0 | 0.3.0 | -| 数据集 | cn-wiki-128(4000w) | ImageNet | -| 训练参数 | src/config.py | src/config.py | -| 优化器 | Lamb | Momentum | -| 损失函数 | SoftmaxCrossEntropy | SoftmaxCrossEntropy | -| 输出 | 概率 | | -| 轮次 | 40 | | | -| Batch_size | 96*8 | 130（8卡） | -| 损失 | 1.7 | 1.913 | -| 速度 | 360毫秒/步 | 1.913 | -| 总时长 | 200小时 | -| 参数（M） | 340 | | -| 微调检查点 | 3.2G（.ckpt文件） | | +| 参数 | Ascend | +| -------------------------- | ---------------------------------------------------------- | +| 模型版本 | BERT_NEZHA | +| 资源 | Ascend 910；CPU 2.60GHz，192核；内存 755GB；系统 Euler2.8 | +| 上传日期 | 2021-07-05 | +| MindSpore版本 | 1.3.0 | +| 数据集 | cn-wiki-128(4000w) | +| 训练参数 | pretrain_config.yaml | +| 优化器 | Lamb | +| 损失函数 | SoftmaxCrossEntropy | +| 输出 | 概率 | +| 轮次 | 40 | +| Batch_size | 96*8 | +| 损失 | 1.7 | +| 速度 | 320毫秒/步 | +| 总时长 | 180小时 | +| 参数（M） | 340 | +| 微调检查点 | 3.2G（.ckpt文件） | #### 推理性能 -| 参数 | Ascend | GPU | -| -------------------------- | ----------------------------- | ------------------------- | -| 模型版本 | | | -| 资源 | Ascend 910；系统 Euler2.8 | NV SMX2 V100-32G | -| 上传日期 | 2020-08-22 | 2020-05-22 | -| MindSpore版本 | 0.6.0 | 0.2.0 | -| 数据集 | cola，1.2W | ImageNet, 1.2W | -| batch_size | 32（单卡） | 130（8卡） | -| 准确率 | 0.588986 | ACC1[72.07%] ACC5[90.90%] | -| 速度 | 59.25毫秒/步 | | -| 总时长 | 15分钟 | | -| 推理模型 | 1.2G（.ckpt文件） | | +| 参数 | Ascend | +| -------------------------- | ----------------------------- | +| 模型版本 | | +| 资源 | Ascend 910；系统 Euler2.8 | +| 上传日期 | 2021-07-05 | +| MindSpore版本 | 1.3.0 | +| 数据集 | cola，1.2W | +| batch_size | 32（单卡） | +| 准确率 | 0.588986 | +| 速度 | 59.25毫秒/步 | +| 总时长 | 15分钟 | +| 推理模型 | 1.2G（.ckpt文件） | # 随机情况说明 diff --git a/model_zoo/official/nlp/bert_thor/README.md b/model_zoo/official/nlp/bert_thor/README.md index 4e65e24d1d4..2adaec4fdf6 100644 --- a/model_zoo/official/nlp/bert_thor/README.md +++ b/model_zoo/official/nlp/bert_thor/README.md @@ -1,20 +1,23 @@ # Bert-THOR Example -- [Description](#Description) -- [Model Architecture](#Model-Architecture) -- [Dataset](#Dataset) -- [Features](#Features) -- [Environment Requirements](#Environment-Requirements) -- [Quick Start](#Quick-Start) -- [Script Description](#Script-Description) - - [Script and Sample Code](#Script-Code-Structure) - - [Script Parameters](#Script-Parameters) - - [Training Process](#Training-Process) - - [Evaluation Process](#Evaluation-Process) -- [Model Description](#Model-Description) - - [Evaluation Performance](#Evaluation-Performance) -- [Description of Random Situation](#Description-of-Random-Situation) -- [ModelZoo Homepage](#ModelZoo-Homepage) +- [Bert-THOR Example](#bert-thor-example) + - [Description](#description) + - [Model Architecture](#model-architecture) + - [Dataset](#dataset) + - [Features](#features) + - [Environment Requirements](#environment-requirements) + - [Quick Start](#quick-start) + - [Script Description](#script-description) + - [Script Code Structure](#script-code-structure) + - [Script Parameters](#script-parameters) + - [Training Process](#training-process) + - [Ascend 910](#ascend-910) + - [Evaluation Process](#evaluation-process) + - [Ascend910](#ascend910) + - [Model Description](#model-description) + - [Evaluation Performance](#evaluation-performance) + - [Description of Random Situation](#description-of-random-situation) + - [ModelZoo Homepage](#modelzoo-homepage) ## Description @@ -205,16 +208,16 @@ step: 3000 Accuracy: [0.71377236] | -------------------------- | -------------------------------------- | | Model Version | BERT-LARGE | | Resource | Ascend 910; cpu 2.60GHz, 192cores; memory 755G; OS Euler2.8 | -| uploaded Date | 08/20/2020 (month/day/year) | -| MindSpore Version | 0.6.0-alpha | +| uploaded Date | 07/05/2021 (month/day/year) | +| MindSpore Version | 1.3.0 | | Dataset | MLPerf v0.7 dataset | -| Training Parameters | total steps=3000, batch_size = 12 | +| Training Parameters | total steps=3000, batch_size = 12*8 | | Optimizer | THOR | | Loss Function | Softmax Cross Entropy | | outputs | probability | | Loss |1.5654222 | -| Speed | 275ms/step（8pcs） | -| Total time | 14 mins | +| Speed | 218ms/step（8pcs） | +| Total time | 11 mins | | Parameters (M) | 330 | | Checkpoint for Fine tuning | 4.5G(.ckpt file) | | Scripts | https://gitee.com/mindspore/mindspore/tree/master/model_zoo/official/nlp/bert_thor | diff --git a/model_zoo/official/nlp/bert_thor/README_CN.md b/model_zoo/official/nlp/bert_thor/README_CN.md index 17f43540ccb..8ceb53e5d9d 100644 --- a/model_zoo/official/nlp/bert_thor/README_CN.md +++ b/model_zoo/official/nlp/bert_thor/README_CN.md @@ -14,8 +14,8 @@ - [训练过程](#训练过程) - [Ascend 910](#ascend-910) - [评估过程](#评估过程) - - [Ascend 910](#ascend-910-1) -- [模型描述](#模型描述) + - [Ascend910](#ascend910) + - [模型描述](#模型描述) - [评估性能](#评估性能) - [随机情况说明](#随机情况说明) - [ModelZoo首页](#modelzoo首页) @@ -212,16 +212,16 @@ step: 3000 Accuracy: [0.71377236] | -------------------------- | -------------------------------------- | | 模型版本 | BERT-LARGE | | 资源 | Ascend 910；CPU 2.60GHz，192核；内存 755GB；系统 Euler2.8 | -| 上传日期 | 2020-08-20 | -| MindSpore版本 | 0.6.0-beta | +| 上传日期 | 2021-07-05 | +| MindSpore版本 | 1.3.0 | | 数据集 | MLPerf v0.7 | -| 训练参数 |总步数=3000，batch_size=12 | +| 训练参数 |总步数=3000，batch_size=12*8 | | 优化器 | THOR | | 损失函数 | Softmax Cross Entropy | | 输出 | 概率 | | 损失 | 1.5654222 | -| 速度 | 275毫秒/步| -| 总时长 | 14分钟 | +| 速度 | 218毫秒/步| +| 总时长 | 11分钟 | | 参数（M） | 330 | | 微调检查点 | 4.5G （.ckpt文件） | | 脚本 | https://gitee.com/mindspore/mindspore/tree/master/model_zoo/official/nlp/bert_thor | diff --git a/model_zoo/official/nlp/lstm/README.md b/model_zoo/official/nlp/lstm/README.md index 39717562c09..3454f28b9bc 100644 --- a/model_zoo/official/nlp/lstm/README.md +++ b/model_zoo/official/nlp/lstm/README.md @@ -1,6 +1,7 @@ [查看中文](./README_CN.md) # Contents +- [Contents](#contents) - [LSTM Description](#lstm-description) - [Model Architecture](#model-architecture) - [Dataset](#dataset) @@ -9,11 +10,16 @@ - [Script Description](#script-description) - [Script and Sample Code](#script-and-sample-code) - [Script Parameters](#script-parameters) + - [Training Script Parameters](#training-script-parameters) + - [Running Options](#running-options) + - [Network Parameters](#network-parameters) - [Dataset Preparation](#dataset-preparation) - [Training Process](#training-process) - [Evaluation Process](#evaluation-process) - [Export MindIR](#export-mindir) - [Inference Process](#inference-process) + - [Usage](#usage) + - [result](#result) - [Model Description](#model-description) - [Performance](#performance) - [Training Performance](#training-performance) @@ -427,8 +433,8 @@ Inference result is saved in current path, you can find result in acc.log file. | Parameters | LSTM (Ascend) | LSTM (GPU) | LSTM (CPU) | | -------------------------- | -------------------------- | -------------------------------------------------------------- | -------------------------- | | Resource | Ascend 910; OS Euler2.8 | Tesla V100-SMX2-16GB | Ubuntu X86-i7-8565U-16GB | -| uploaded Date | 12/21/2020 (month/day/year)| 10/28/2020 (month/day/year) | 10/28/2020 (month/day/year)| -| MindSpore Version | 1.1.0 | 1.0.0 | 1.0.0 | +| uploaded Date | 12/21/2020 (month/day/year)| 07/05/2021 (month/day/year) | 07/05/2021 (month/day/year)| +| MindSpore Version | 1.1.0 | 1.3.0 | 1.3.0 | | Dataset | aclimdb_v1 | aclimdb_v1 | aclimdb_v1 | | Training Parameters | epoch=20, batch_size=64 | epoch=20, batch_size=64 | epoch=20, batch_size=64 | | Optimizer | Momentum | Momentum | Momentum | @@ -444,8 +450,8 @@ Inference result is saved in current path, you can find result in acc.log file. | Parameters | LSTM (Ascend) | LSTM (GPU) | LSTM (CPU) | | ------------------- | ---------------------------- | --------------------------- | ---------------------------- | | Resource | Ascend 910; OS Euler2.8 | Tesla V100-SMX2-16GB | Ubuntu X86-i7-8565U-16GB | -| uploaded Date | 12/21/2020 (month/day/year) | 10/28/2020 (month/day/year) | 10/28/2020 (month/day/year) | -| MindSpore Version | 1.1.0 | 1.0.0 | 1.0.0 | +| uploaded Date | 12/21/2020 (month/day/year) | 07/05/2021 (month/day/year) | 07/05/2021 (month/day/year) | +| MindSpore Version | 1.1.0 | 1.3.0 | 1.3.0 | | Dataset | aclimdb_v1 | aclimdb_v1 | aclimdb_v1 | | batch_size | 64 | 64 | 64 | | Accuracy | 85% | 84% | 83% | diff --git a/model_zoo/official/nlp/lstm/README_CN.md b/model_zoo/official/nlp/lstm/README_CN.md index dc3515d59db..9da950bbf84 100644 --- a/model_zoo/official/nlp/lstm/README_CN.md +++ b/model_zoo/official/nlp/lstm/README_CN.md @@ -19,8 +19,8 @@ - [评估过程](#评估过程) - [导出mindir模型](#导出mindir模型) - [推理过程](#推理过程) - - [用法](#用法-2) - - [结果](#结果-2) + - [用法](#用法) + - [结果](#结果) - [模型描述](#模型描述) - [性能](#性能) - [训练性能](#训练性能) @@ -433,8 +433,8 @@ bash run_infer_310.sh [MINDIR_PATH] [DATASET_PATH] [NEED_PREPROCESS] [DEVICE_TAR | 参数 | LSTM (Ascend) | LSTM (GPU) | LSTM (CPU) | | -------------------------- | -------------------------- | -------------------------------------------------------------- | -------------------------- | | 资源 | Ascend 910 | Tesla V100-SMX2-16GB | Ubuntu X86-i7-8565U-16GB | -| 上传日期 | 2020-12-21 | 2020-08-06 | 2020-08-06 | -| MindSpore版本 | 1.1.0 | 0.6.0-beta | 0.6.0-beta | +| 上传日期 | 2020-12-21 | 2021-07-05 | 2021-07-05 | +| MindSpore版本 | 1.1.0 | 1.3.0 | 1.3.0 | | 数据集 | aclimdb_v1 | aclimdb_v1 | aclimdb_v1 | | 训练参数 | epoch=20, batch_size=64 | epoch=20, batch_size=64 | epoch=20, batch_size=64 | | 优化器 | Momentum | Momentum | Momentum | @@ -450,8 +450,8 @@ bash run_infer_310.sh [MINDIR_PATH] [DATASET_PATH] [NEED_PREPROCESS] [DEVICE_TAR | 参数 | LSTM (Ascend) | LSTM (GPU) | LSTM (CPU) | | ------------------- | ---------------------------- | --------------------------- | ---------------------------- | | 资源 | Ascend 910；系统 Euler2.8 | Tesla V100-SMX2-16GB | Ubuntu X86-i7-8565U-16GB | -| 上传日期 | 2020-12-21 | 2020-08-06 | 2020-08-06 | -| MindSpore版本 | 1.1.0 | 0.6.0-beta | 0.6.0-beta | +| 上传日期 | 2020-12-21 | 2021-07-05 | 2021-07-05 | +| MindSpore版本 | 1.1.0 | 1.3.0 | 1.3.0 | | 数据集 | aclimdb_v1 | aclimdb_v1 | aclimdb_v1 | | batch_size | 64 | 64 | 64 | | 准确率 | 85% | 84% | 83% | diff --git a/model_zoo/official/nlp/mass/README.md b/model_zoo/official/nlp/mass/README.md index bb7dced6ef2..041e802c86c 100644 --- a/model_zoo/official/nlp/mass/README.md +++ b/model_zoo/official/nlp/mass/README.md @@ -2,6 +2,7 @@ +- [Contexts](#contexts) - [MASS: Masked Sequence to Sequence Pre-training for Language Generation Description](#mass-masked-sequence-to-sequence-pre-training-for-language-generation-description) - [Model Architecture](#model-architecture) - [Dataset](#dataset) @@ -694,8 +695,8 @@ The comparisons between MASS and other baseline methods in terms of PPL on Corne |:---------------------------|:--------------------------------------------------------------------------| | Model Version | v1 | | Resource | Ascend 910; cpu 2.60GHz, 192cores; memory 755G; OS Euler2.8 | -| uploaded Date | 05/24/2020 | -| MindSpore Version | 1.0.0 | +| uploaded Date | 06/21/2021 | +| MindSpore Version | 1.2.1 | | Dataset | News Crawl 2007-2017 English monolingual corpus, Gigaword corpus, Cornell Movie Dialog corpus | | Training Parameters | Epoch=50, steps=XXX, batch_size=192, lr=1e-4 | | Optimizer | Adam | @@ -713,8 +714,8 @@ The comparisons between MASS and other baseline methods in terms of PPL on Corne |:---------------------------|:-----------------------------------------------------------| | Model Version | V1 | | Resource | Ascend 910; OS Euler2.8 | -| uploaded Date | 05/24/2020 | -| MindSpore Version | 1.0.0 | +| uploaded Date | 06/21/2021 | +| MindSpore Version | 1.2.1 | | Dataset | Gigaword corpus, Cornell Movie Dialog corpus | | batch_size | --- | | outputs | Sentence and probability | diff --git a/model_zoo/official/nlp/mass/README_CN.md b/model_zoo/official/nlp/mass/README_CN.md index 9f3866447a9..22823166263 100644 --- a/model_zoo/official/nlp/mass/README_CN.md +++ b/model_zoo/official/nlp/mass/README_CN.md @@ -27,12 +27,12 @@ - [预训练](#预训练) - [微调](#微调) - [推理](#推理) - - [Mindir推理](#Mindir推理) + - [Mindir推理](#mindir推理) - [导出模型](#导出模型) - - [在Ascend310执行推理](#在Ascend310执行推理) + - [在Ascend310执行推理](#在ascend310执行推理) - [结果](#结果) - [性能](#性能) - - [结果](#结果) + - [结果](#结果-1) - [文本摘要微调](#文本摘要微调) - [会话应答微调](#会话应答微调) - [训练性能](#训练性能) @@ -696,8 +696,8 @@ bash run_infer_310.sh [MINDIR_PATH] [CONFIG] [VOCAB] [OUTPUT] [NEED_PREPROCESS] |:---------------------------|:--------------------------------------------------------------------------| | 模型版本 | v1 | | 资源 | Ascend 910；CPU 2.60GHz，192核；内存 755GB；系统 Euler2.8 | -| 上传日期 | 2020-05-24 | -| MindSpore版本 | 0.2.0 | +| 上传日期 | 2021-06-21 | +| MindSpore版本 | 1.2.1 | | 数据集 | News Crawl 2007-2017英语单语语料库、Gigaword语料库、Cornell电影对白语料库 | | 训练参数 | Epoch=50, steps=XXX, batch_size=192, lr=1e-4 | | 优化器 | Adam | @@ -715,8 +715,8 @@ bash run_infer_310.sh [MINDIR_PATH] [CONFIG] [VOCAB] [OUTPUT] [NEED_PREPROCESS] |:---------------------------|:-----------------------------------------------------------| |模型版本| V1 | | 资源 | Ascend 910；系统 Euler2.8 | -| 上传日期 | 2020-05-24 | -| MindSpore版本 | 0.2.0 | +| 上传日期 | 2020-06-21 | +| MindSpore版本 | 1.2.1 | | 数据集 | Gigaword语料库、Cornell电影对白语料库 | | batch_size | --- | | 输出 | 句子及概率 | diff --git a/model_zoo/official/nlp/tinybert/README.md b/model_zoo/official/nlp/tinybert/README.md index 9960621e83e..9de774dd4c6 100644 --- a/model_zoo/official/nlp/tinybert/README.md +++ b/model_zoo/official/nlp/tinybert/README.md @@ -12,8 +12,8 @@ - [General Distill](#general-distill) - [Task Distill](#task-distill) - [Options and Parameters](#options-and-parameters) - - [Options:](#options) - - [Parameters:](#parameters) + - [Options](#options) + - [Parameters](#parameters) - [Training Process](#training-process) - [Training](#training) - [running on Ascend](#running-on-ascend) @@ -557,8 +557,8 @@ Inference result is saved in current path, you can find result like this in acc. | -------------------------- | ---------------------------------------------------------- | ------------------------- | | Model Version | TinyBERT | TinyBERT | | Resource |Ascend 910; cpu 2.60GHz, 192cores; memory 755G; OS Euler2.8 | NV SMX2 V100-32G, cpu:2.10GHz 64cores, memory:251G | -| uploaded Date | 08/20/2020 | 08/24/2020 | -| MindSpore Version | 1.0.0 | 1.0.0 | +| uploaded Date | 07/05/2021 | 07/05/2021 | +| MindSpore Version | 1.3.0 | 1.3.0 | | Dataset | en-wiki-128 | en-wiki-128 | | Training Parameters | src/gd_config.yaml | src/gd_config.yaml | | Optimizer | AdamWeightDecay | AdamWeightDecay | @@ -577,8 +577,8 @@ Inference result is saved in current path, you can find result like this in acc. | -------------------------- | ----------------------------- | ------------------------- | | Model Version | | | | Resource | Ascend 910; OS Euler2.8 | NV SMX2 V100-32G | -| uploaded Date | 08/20/2020 | 08/24/2020 | -| MindSpore Version | 1.0.0 | 1.0.0 | +| uploaded Date | 07/05/2021 | 07/05/2021 | +| MindSpore Version | 1.3.0 | 1.3.0 | | Dataset | SST-2, | SST-2 | | batch_size | 32 | 32 | | Accuracy | 0.902777 | 0.9086 | diff --git a/model_zoo/official/nlp/tinybert/README_CN.md b/model_zoo/official/nlp/tinybert/README_CN.md index 480cf772080..2036f380fb2 100644 --- a/model_zoo/official/nlp/tinybert/README_CN.md +++ b/model_zoo/official/nlp/tinybert/README_CN.md @@ -556,8 +556,8 @@ bash run_infer_310.sh [MINDIR_PATH] [DATASET_PATH] [SCHEMA_DIR] [DATASET_TYPE] [ | -------------------------- | ---------------------------------------------------------- | ------------------------- | | 模型版本 | TinyBERT | TinyBERT | | 资源 | Ascend 910；cpu 2.60GHz，192核；内存 755G；系统 Euler2.8 | NV SMX2 V100-32G, cpu:2.10GHz 64核, 内存:251G | -| 上传日期 | 2020-08-20 | 2020-08-24 | -| MindSpore版本 | 0.6.0 | 0.7.0 | +| 上传日期 | 2021-07-05 | 2021-07-05 | +| MindSpore版本 | 1.3.0 | 1.3.0 | | 数据集 | en-wiki-128 | en-wiki-128 | | 训练参数 | src/gd_config.yaml | src/gd_config.yaml | | 优化器| AdamWeightDecay | AdamWeightDecay | @@ -575,8 +575,8 @@ bash run_infer_310.sh [MINDIR_PATH] [DATASET_PATH] [SCHEMA_DIR] [DATASET_TYPE] [ | -------------------------- | ----------------------------- | ------------------------- | | 模型版本 | | | | 资源 | Ascend 910；系统 Euler2.8 | NV SMX2 V100-32G | -| 上传日期 | 2020-08-20 | 2020-08-24 | -| MindSpore版本 | 0.6.0 | 0.7.0 | +| 上传日期 | 2021-07-05 | 2021-07-05 | +| MindSpore版本 | 1.3.0 | 1.3.0 | | 数据集 | SST-2, | SST-2 | | batch_size | 32 | 32 | | 准确率 | 0.902777 | 0.9086 | diff --git a/model_zoo/official/nlp/transformer/README.md b/model_zoo/official/nlp/transformer/README.md index 7fb17d2586a..b14c8387c8a 100644 --- a/model_zoo/official/nlp/transformer/README.md +++ b/model_zoo/official/nlp/transformer/README.md @@ -2,14 +2,18 @@ [查看中文](./README_CN.md) -- [Transformer Description](#transformer-description) -- [Model Architecture](#model-architecture) -- [Dataset](#dataset) -- [Environment Requirements](#environment-requirements) -- [Quick Start](#quick-start) -- [Script Description](#script-description) - - [Script and Sample Code](#script-and-sample-code) - - [Script Parameters](#script-parameters) +- [Contents](#contents) + - [Transformer Description](#transformer-description) + - [Model Architecture](#model-architecture) + - [Dataset](#dataset) + - [Environment Requirements](#environment-requirements) + - [Quick Start](#quick-start) + - [Script Description](#script-description) + - [Script and Sample Code](#script-and-sample-code) + - [Script Parameters](#script-parameters) + - [Training Script Parameters](#training-script-parameters) + - [Running Options](#running-options) + - [Network Parameters](#network-parameters) - [Dataset Preparation](#dataset-preparation) - [Training Process](#training-process) - [Evaluation Process](#evaluation-process) @@ -17,12 +21,12 @@ - [Export MindIR](#export-mindir) - [Infer on Ascend310](#infer-on-ascend310) - [result](#result) -- [Model Description](#model-description) - - [Performance](#performance) - - [Training Performance](#training-performance) - - [Evaluation Performance](#evaluation-performance) -- [Description of Random Situation](#description-of-random-situation) -- [ModelZoo Homepage](#modelzoo-homepage) + - [Model Description](#model-description) + - [Performance](#performance) + - [Training Performance](#training-performance) + - [Evaluation Performance](#evaluation-performance) + - [Description of Random Situation](#description-of-random-situation) + - [ModelZoo Homepage](#modelzoo-homepage) ## [Transformer Description](#contents) @@ -385,8 +389,8 @@ Inference result is saved in current path, 'output_file' will generate in path s | Parameters | Ascend | | -------------------------- | -------------------------------------------------------------- | | Resource | Ascend 910; OS Euler2.8 | -| uploaded Date | 09/15/2020 (month/day/year) | -| MindSpore Version | 1.0.0 | +| uploaded Date | 07/05/2021 (month/day/year) | +| MindSpore Version | 1.3.0 | | Dataset | WMT Englis-German | | Training Parameters | epoch=52, batch_size=96 | | Optimizer | Adam | @@ -403,8 +407,8 @@ Inference result is saved in current path, 'output_file' will generate in path s | Parameters | Ascend | | ------------------- | --------------------------- | | Resource | Ascend 910; OS Euler2.8 | -| Uploaded Date | 09/15/2020 (month/day/year) | -| MindSpore Version | 1.0.0 | +| Uploaded Date | 07/05/2021 (month/day/year) | +| MindSpore Version | 1.3.0 | | Dataset | WMT newstest2014 | | batch_size | 1 | | outputs | BLEU score | diff --git a/model_zoo/official/nlp/transformer/README_CN.md b/model_zoo/official/nlp/transformer/README_CN.md index aecf3cf4dc4..224af26ac21 100644 --- a/model_zoo/official/nlp/transformer/README_CN.md +++ b/model_zoo/official/nlp/transformer/README_CN.md @@ -5,30 +5,30 @@ - [目录](#目录) -- [Transformer 概述](#transfomer-概述) -- [模型架构](#模型架构) -- [数据集](#数据集) -- [环境要求](#环境要求) -- [快速入门](#快速入门) -- [脚本说明](#脚本说明) - - [脚本和样例代码](#脚本和样例代码) - - [脚本参数](#脚本参数) - - [训练脚本参数](#训练脚本参数) - - [运行选项](#运行选项) - - [网络参数](#网络参数) - - [准备数据集](#准备数据集) - - [训练过程](#训练过程) - - [评估过程](#评估过程) + - [Transformer 概述](#transformer-概述) + - [模型架构](#模型架构) + - [数据集](#数据集) + - [环境要求](#环境要求) + - [快速入门](#快速入门) + - [脚本说明](#脚本说明) + - [脚本和样例代码](#脚本和样例代码) + - [脚本参数](#脚本参数) + - [训练脚本参数](#训练脚本参数) + - [运行选项](#运行选项) + - [网络参数](#网络参数) + - [准备数据集](#准备数据集) + - [训练过程](#训练过程) + - [评估过程](#评估过程) - [推理过程](#推理过程) - [导出MindIR](#导出mindir) - [在Ascend310执行推理](#在ascend310执行推理) - [结果](#结果) -- [模型描述](#模型描述) - - [性能](#性能) - - [训练性能](#训练性能) - - [评估性能](#评估性能) -- [随机情况说明](#随机情况说明) -- [ModelZoo主页](#modelzoo主页) + - [模型描述](#模型描述) + - [性能](#性能) + - [训练性能](#训练性能) + - [评估性能](#评估性能) + - [随机情况说明](#随机情况说明) + - [ModelZoo主页](#modelzoo主页) @@ -392,8 +392,8 @@ bash run_infer_310.sh [MINDIR_PATH] [NEED_PREPROCESS] [DEVICE_ID] | 参数 | Ascend | | -------------------------- | -------------------------------------------------------------- | | 资源 | Ascend 910；系统 Euler2.8 | -| 上传日期 | 2020-06-09 | -| MindSpore版本 | 0.5.0-beta | +| 上传日期 | 2021-07-05 | +| MindSpore版本 | 1.3.0 | | 数据集 | WMT英-德翻译数据集 | | 训练参数 | epoch=52, batch_size=96 | | 优化器 | Adam | @@ -410,8 +410,8 @@ bash run_infer_310.sh [MINDIR_PATH] [NEED_PREPROCESS] [DEVICE_ID] | 参数 | Ascend | | ------------------- | --------------------------- | |资源| Ascend 910；系统 Euler2.8 | -| 上传日期 | 2020-06-09 | -| MindSpore版本 | 0.5.0-beta | +| 上传日期 | 2021-07-05 | +| MindSpore版本 | 1.3.0 | | 数据集 | WMT newstest2014 | | batch_size | 1 | | 输出 | BLEU score | diff --git a/model_zoo/official/recommend/deepfm/README.md b/model_zoo/official/recommend/deepfm/README.md index 3e7ea5e28fc..bd5c8feae0d 100644 --- a/model_zoo/official/recommend/deepfm/README.md +++ b/model_zoo/official/recommend/deepfm/README.md @@ -1,5 +1,6 @@ # Contents +- [Contents](#contents) - [DeepFM Description](#deepfm-description) - [Model Architecture](#model-architecture) - [Dataset](#dataset) @@ -10,7 +11,7 @@ - [Script Parameters](#script-parameters) - [Training Process](#training-process) - [Training](#training) - - [Distributed Training](#distributed-training) + - [Distributed Training](#distributed-training) - [Evaluation Process](#evaluation-process) - [Evaluation](#evaluation) - [Inference Process](#inference-process) @@ -19,8 +20,8 @@ - [result](#result) - [Model Description](#model-description) - [Performance](#performance) - - [Evaluation Performance](#evaluation-performance) - - [Inference Performance](#evaluation-performance) + - [Training Performance](#training-performance) + - [Inference Performance](#inference-performance) - [Description of Random Situation](#description-of-random-situation) - [ModelZoo Homepage](#modelzoo-homepage) @@ -417,15 +418,15 @@ auc : 0.8057789065281104 | -------------------------- | ----------------------------------------------------------- | ---------------------- | | Model Version | DeepFM | To do | | Resource | Ascend 910; CPU 2.60GHz, 192cores; Memory 755G; OS Euler2.8 | To do | -| uploaded Date | 09/15/2020 (month/day/year) | To do | +| uploaded Date | 07/05/2021 (month/day/year) | To do | | MindSpore Version | 1.0.0 | To do | | Dataset | [1] | To do | -| Training Parameters | epoch=15, batch_size=1000, lr=1e-5 | To do | +| Training Parameters | epoch=15, batch_size=16000, lr=1e-5 | To do | | Optimizer | Adam | To do | | Loss Function | Sigmoid Cross Entropy With Logits | To do | | outputs | Accuracy | To do | | Loss | 0.45 | To do | -| Speed | 1pc: 8.16 ms/step; | To do | +| Speed | 1pc: 21 ms/step; | To do | | Total time | 1pc: 90 mins; | To do | | Parameters (M) | 16.5 | To do | | Checkpoint for Fine tuning | 190M (.ckpt file) | To do | @@ -437,8 +438,8 @@ auc : 0.8057789065281104 | ------------------- | --------------------------- | --------------------------- | | Model Version | DeepFM | To do | | Resource | Ascend 910; OS Euler2.8 | To do | -| Uploaded Date | 05/27/2020 (month/day/year) | To do | -| MindSpore Version | 0.3.0-alpha | To do | +| Uploaded Date | 07/05/2021 (month/day/year) | To do | +| MindSpore Version | 1.3.0 | To do | | Dataset | [1] | To do | | batch_size | 1000 | To do | | outputs | accuracy | To do | diff --git a/model_zoo/official/recommend/deepfm/README_CN.md b/model_zoo/official/recommend/deepfm/README_CN.md index a42aaedb9b8..04e77810d1e 100644 --- a/model_zoo/official/recommend/deepfm/README_CN.md +++ b/model_zoo/official/recommend/deepfm/README_CN.md @@ -3,11 +3,11 @@ - [目录](#目录) -- [DeepFM概述](#deepfm概述) -- [模型架构](#模型架构) -- [数据集](#数据集) -- [环境要求](#环境要求) -- [快速入门](#快速入门) + - [DeepFM概述](#deepfm概述) + - [模型架构](#模型架构) + - [数据集](#数据集) + - [环境要求](#环境要求) + - [快速入门](#快速入门) - [脚本说明](#脚本说明) - [脚本和样例代码](#脚本和样例代码) - [脚本参数](#脚本参数) @@ -20,7 +20,7 @@ - [导出MindIR](#导出mindir) - [在Ascend310执行推理](#在ascend310执行推理) - [结果](#结果) -- [模型描述](#模型描述) + - [模型描述](#模型描述) - [性能](#性能) - [评估性能](#评估性能) - [推理性能](#推理性能) @@ -399,15 +399,15 @@ auc : 0.8057789065281104 | -------------------------- | ----------------------------------------------------------- | ---------------------- | | 模型版本 | DeepFM | 待运行 | | 资源 |Ascend 910；CPU 2.60GHz，192核；内存 755G；系统 Euler2.8 | 待运行 | -| 上传日期 | 2020-05-17 | 待运行 | -| MindSpore版本 | 0.3.0-alpha | 待运行 | +| 上传日期 | 2021-07-05 | 待运行 | +| MindSpore版本 | 1.3.0 | 待运行 | | 数据集 | [1] | 待运行 | -| 训练参数 | epoch=15, batch_size=1000, lr=1e-5 | 待运行 | +| 训练参数 | epoch=15, batch_size=16000, lr=1e-5 | 待运行 | | 优化器 | Adam | 待运行 | | 损失函数 | Sigmoid Cross Entropy With Logits | 待运行 | | 输出 | 准确率 | 待运行 | | 损失 | 0.45 | 待运行 | -| 速度| 单卡：8.16毫秒/步; | 待运行 | +| 速度| 单卡：21毫秒/步; | 待运行 | | 总时长| 单卡：90 分钟; | 待运行 | | 参数(M) | 16.5 | 待运行 | | 微调检查点 | 190M (.ckpt 文件) | 待运行 | @@ -419,8 +419,8 @@ auc : 0.8057789065281104 | ------------------- | --------------------------- | --------------------------- | | 模型版本 | DeepFM | 待运行 | | 资源 | Ascend 910；系统 Euler2.8 | 待运行 | -| 上传日期 | 2020-05-27 | 待运行 | -| MindSpore版本 | 0.3.0-alpha | 待运行 | +| 上传日期 | 2021-07-05 | 待运行 | +| MindSpore版本 | 1.3.0 | 待运行 | | 数据集 | [1] | 待运行 | | batch_size | 1000 | 待运行 | | 输出 | 准确率 | 待运行 | diff --git a/model_zoo/official/recommend/wide_and_deep/README.md b/model_zoo/official/recommend/wide_and_deep/README.md index cd92eaf863d..f29fa236be5 100644 --- a/model_zoo/official/recommend/wide_and_deep/README.md +++ b/model_zoo/official/recommend/wide_and_deep/README.md @@ -9,15 +9,16 @@ - [Script Description](#script-description) - [Script and Sample Code](#script-and-sample-code) - [Script Parameters](#script-parameters) - - [Training Script Parameters](#training-script-parameters) - - [Preprocess Script Parameters](#preprocess-script-parameters) + - [Training Script Parameters](#training-script-parameters) + - [Preprocess Script Parameters](#preprocess-script-parameters) - [Dataset Preparation](#dataset-preparation) - - [Process the Real World Data](#process-the-real-world-data) - - [Generate and Process the Synthetic Data](#generate-and-process-the-synthetic-data) + - [Process the Real World Data](#process-the-real-world-data) + - [Generate and Process the Synthetic Data](#generate-and-process-the-synthetic-data) - [Training Process](#training-process) - - [SingleDevice](#singledevice) - - [Distribute Training](#distribute-training) - - [Parameter Server](#parameter-server) + - [SingleDevice](#singledevice) + - [SingleDevice For Cache Mode](#singledevice-for-cache-mode) + - [Distribute Training](#distribute-training) + - [Parameter Server](#parameter-server) - [Evaluation Process](#evaluation-process) - [Inference Process](#inference-process) - [Export MindIR](#export-mindir) @@ -25,8 +26,9 @@ - [result](#result) - [Model Description](#model-description) - [Performance](#performance) - - [Training Performance](#training-performance) - - [Evaluation Performance](#evaluation-performance) + - [Training Performance](#training-performance) + - [Evaluation Performance](#evaluation-performance) + - [Ultimate performance experience](#ultimate-performance-experience) - [Description of Random Situation](#description-of-random-situation) - [ModelZoo Homepage](#modelzoo-homepage) @@ -444,8 +446,8 @@ Inference result is saved in current path, you can find result like this in acc. | Parameters | Single
Ascend | Single
GPU | Data-Parallel-8P | Host-Device-mode-8P | | ------------------------ | ------------------------------- | ------------------------------- | ------------------------------- | ------------------------------- | | Resource | Ascend 910; OS Euler2.8 | Tesla V100-PCIE 32G | Ascend 910; OS Euler2.8 | Ascend 910; OS Euler2.8 | -| Uploaded Date | 08/21/2020 (month/day/year) | 08/21/2020 (month/day/year) | 08/21/2020 (month/day/year) | 08/21/2020 (month/day/year) | -| MindSpore Version | 1.0 | 1.0 | 1.0 | 1.0 | +| Uploaded Date | 07/05/2021 (month/day/year) | 07/05/2021 (month/day/year) | 07/05/2021 (month/day/year) | 07/05/2021 (month/day/year) | +| MindSpore Version | 1.3.0 | 1.3.0 | 1.3.0 | 1.3.0 | | Dataset | [1] | [1] | [1] | [1] | | Training Parameters | Epoch=15,
batch_size=16000 | Epoch=15,
batch_size=16000 | Epoch=15,
batch_size=16000 | Epoch=15,
batch_size=16000 | | Optimizer | FTRL,Adam | FTRL,Adam | FTRL,Adam | FTRL,Adam | @@ -465,8 +467,8 @@ Note: The result of GPU is tested under the master version. The parameter server | Parameters | Wide&Deep | | ----------------- | --------------------------- | | Resource | Ascend 910; OS Euler2.8 | -| Uploaded Date | 10/27/2020 (month/day/year) | -| MindSpore Version | 1.0 | +| Uploaded Date | 07/05/2021 (month/day/year) | +| MindSpore Version | 1.3.0 | | Dataset | [1] | | Batch Size | 16000 | | Outputs | AUC | diff --git a/model_zoo/official/recommend/wide_and_deep/README_CN.md b/model_zoo/official/recommend/wide_and_deep/README_CN.md index 5e79b0e3776..199cf3d3a7d 100644 --- a/model_zoo/official/recommend/wide_and_deep/README_CN.md +++ b/model_zoo/official/recommend/wide_and_deep/README_CN.md @@ -16,17 +16,20 @@ - [生成和处理合成数据](#生成和处理合成数据) - [训练过程](#训练过程) - [单机训练](#单机训练) + - [单机训练缓存模式](#单机训练缓存模式) - [分布式训练](#分布式训练) - [参数服务器](#参数服务器) - [评估过程](#评估过程) + - [Evaluation Process](#evaluation-process) - [推理过程](#推理过程) - [导出MindIR](#导出mindir) - [在Ascend310执行推理](#在ascend310执行推理) - - [结果](#结果) + - [result](#result) - [模型描述](#模型描述) - [性能](#性能) - [训练性能](#训练性能) - [评估性能](#评估性能) + - [极致性能体验](#极致性能体验) - [随机情况说明](#随机情况说明) - [ModelZoo主页](#modelzoo主页) @@ -455,8 +458,8 @@ bash run_infer_310.sh [MINDIR_PATH] [DATASET_PATH] [DATA_TYPE] [NEED_PREPROCESS] | 参数 | Ascend单机 | GPU单机 | 数据并行模式-8卡 | 主机设备模式-8卡 | | ------------------------ | ------------------------------- | ------------------------------- | ------------------------------- | ------------------------------- | | 资源 |Ascend 910；系统 Euler2.8 | Tesla V100-PCIE 32G | Ascend 910；系统 Euler2.8 | Ascend 910；系统 Euler2.8 | -| 上传日期 | 2020-08-21 | 2020-08-21 | 2020-08-21 | 2020-08-21 | -| MindSpore版本 | 0.6.0-beta | master | 0.6.0-beta | 0.6.0-beta | +| 上传日期 | 2021-07-05 | 2021-07-05 | 2021-07-05 | 2021-07-05 | +| MindSpore版本 | 1.3.0 | 1.3.0 | 1.3.0 | 1.3.0 | | 数据集 | [1] | [1] | [1] | [1] | | 训练参数 | Epoch=15,
batch_size=16000 | Epoch=15,
batch_size=16000 | Epoch=15,
batch_size=16000 | Epoch=15,
batch_size=16000 | | 优化器 | FTRL,Adam | FTRL,Adam | FTRL,Adam | FTRL,Adam | @@ -476,8 +479,8 @@ bash run_infer_310.sh [MINDIR_PATH] [DATASET_PATH] [DATA_TYPE] [NEED_PREPROCESS] | 参数 | Wide&Deep | | ----------------- | --------------------------- | | 资源 | Ascend 910；系统 Euler2.8 | -| 上传日期 | 2020-08-21 | -| MindSpore版本 | 0.6.0-beta | +| 上传日期 | 2021-07-05 | +| MindSpore版本 | 1.3.0 | | 数据集 | [1] | | 批次大小 | 16000 | | 输出 | AUC | diff --git a/model_zoo/official/recommend/wide_and_deep_multitable/README.md b/model_zoo/official/recommend/wide_and_deep_multitable/README.md index 3e4b682ae2e..1363fea560b 100644 --- a/model_zoo/official/recommend/wide_and_deep_multitable/README.md +++ b/model_zoo/official/recommend/wide_and_deep_multitable/README.md @@ -1,24 +1,25 @@ # Contents -- [Wide&Deep Description](#widedeep-description) -- [Model Architecture](#model-architecture) -- [Dataset](#dataset) -- [Environment Requirements](#environment-requirements) -- [Quick Start](#quick-start) -- [Script Description](#script-description) - - [Script and Sample Code](#script-and-sample-code) - - [Script Parameters](#script-parameters) - - [Training Script Parameters](#training-script-parameters) - - [Training Process](#training-process) - - [SingleDevice](#singledevice) - - [Distribute Training](#distribute-training) - - [Evaluation Process](#evaluation-process) -- [Model Description](#model-description) - - [Performance](#performance) - - [Training Performance](#training-performance) - - [Evaluation Performance](#evaluation-performance) -- [Description of Random Situation](#description-of-random-situation) -- [ModelZoo Homepage](#modelzoo-homepage) +- [Contents](#contents) + - [Wide&Deep Description](#widedeep-description) + - [Model Architecture](#model-architecture) + - [Dataset](#dataset) + - [Environment Requirements](#environment-requirements) + - [Quick Start](#quick-start) + - [Script Description](#script-description) + - [Script and Sample Code](#script-and-sample-code) + - [Script Parameters](#script-parameters) + - [Training Script Parameters](#training-script-parameters) + - [Training Process](#training-process) + - [SingleDevice](#singledevice) + - [Distribute Training](#distribute-training) + - [Evaluation Process](#evaluation-process) + - [Model Description](#model-description) + - [Performance](#performance) + - [Training Performance](#training-performance) + - [Evaluation Performance](#evaluation-performance) + - [Description of Random Situation](#description-of-random-situation) + - [ModelZoo Homepage](#modelzoo-homepage) ## [Wide&Deep Description](#contents) @@ -168,8 +169,8 @@ python eval.py | Parameters | Single
Ascend | Data-Parallel-8P | | ------------------------ | ------------------------------- | ------------------------------- | | Resource | Ascend 910; OS Euler2.8 | Ascend 910 | -| Uploaded Date | 08/21/2020 (month/day/year) | 08/21/2020 (month/day/year) | -| MindSpore Version | 1.0 | 1.0 | +| Uploaded Date | 07/05/2021 (month/day/year) | 07/05/2021 (month/day/year) | +| MindSpore Version | 1.3.0 | 1.3.0 | | Dataset | [1] | [1] | | Training Parameters | Epoch=3,
batch_size=131072 | Epoch=8,
batch_size=131072 | | Optimizer | FTRL,Adam | FTRL,Adam | @@ -188,8 +189,8 @@ All executable scripts can be found in [here](https://gitee.com/mindspore/mindsp | Parameters | Wide&Deep | | ----------------- | --------------------------- | | Resource | Ascend 910; OS Euler2.8 | -| Uploaded Date | 10/27/2020 (month/day/year) | -| MindSpore Version | 1.0 | +| Uploaded Date | 07/05/2021 (month/day/year) | +| MindSpore Version | 1.3.0 | | Dataset | [1] | | Batch Size | 131072 | | Outputs | AUC，MAP | diff --git a/model_zoo/official/recommend/wide_and_deep_multitable/README_CN.md b/model_zoo/official/recommend/wide_and_deep_multitable/README_CN.md index a3449828f3c..ba7194a5e2b 100644 --- a/model_zoo/official/recommend/wide_and_deep_multitable/README_CN.md +++ b/model_zoo/official/recommend/wide_and_deep_multitable/README_CN.md @@ -1,11 +1,11 @@ # 目录 - [目录](#目录) -- [Wide&Deep概述](#widedeep概述) -- [模型架构](#模型架构) -- [数据集](#数据集) -- [环境要求](#环境要求) -- [快速入门](#快速入门) + - [Wide&Deep概述](#widedeep概述) + - [模型架构](#模型架构) + - [数据集](#数据集) + - [环境要求](#环境要求) + - [快速入门](#快速入门) - [脚本说明](#脚本说明) - [脚本和样例代码](#脚本和样例代码) - [脚本参数](#脚本参数) @@ -14,10 +14,10 @@ - [单机训练](#单机训练) - [分布训练](#分布训练) - [评估过程](#评估过程) -- [模型描述](#模型描述) - - [性能](#性能) - - [训练性能](#训练性能) - - [评估性能](#评估性能) + - [模型描述](#模型描述) + - [性能](#性能) + - [训练性能](#训练性能) + - [评估性能](#评估性能) - [随机情况说明](#随机情况说明) - [ModelZoo主页](#modelzoo主页) @@ -170,8 +170,8 @@ python eval.py | 参数 | 单Ascend | 数据并行-8卡 | | ------------------------ | ------------------------------- | ------------------------------- | | 资源 | Ascend 910 | Ascend 910 | -| 上传日期 | 2020-08-21 | 2020-08-21 | -| MindSpore版本 | 0.7.0-beta | 0.7.0-beta | +| 上传日期 | 2021-07-05 | 2021-07-05 | +| MindSpore版本 | 1.3.0 | 1.3.0 | | 数据集 | [1] | [1] | | 训练参数 | Epoch=3,
batch_size=131072 | Epoch=8,
batch_size=131072 | | 优化器 | FTRL,Adam | FTRL,Adam | @@ -190,8 +190,8 @@ python eval.py | 参数 | Wide&Deep | | ----------------- | --------------------------- | | 资源 | Ascend 910 | -| 上传日期 | 2020-08-21 | -| MindSpore 版本 | 0.7.0-beta | +| 上传日期 | 2021-07-05 | +| MindSpore 版本 | 1.3.0 | | 数据集 | [1] | | 批次大小 | 131072 | | 输出 | AUC，MAP | diff --git a/model_zoo/research/audio/fcn-4/README.md b/model_zoo/research/audio/fcn-4/README.md index cf2407d491f..29778cb5b39 100644 --- a/model_zoo/research/audio/fcn-4/README.md +++ b/model_zoo/research/audio/fcn-4/README.md @@ -1,26 +1,31 @@ # Contents -- [FCN-4 Description](#fcn-4-description) -- [Model Architecture](#model-architecture) -- [Features](#features) - - [Mixed Precision](#mixed-precision) -- [Environment Requirements](#environment-requirements) -- [Quick Start](#quick-start) -- [Script Description](#script-description) - - [Script and Sample Code](#script-and-sample-code) - - [Script Parameters](#script-parameters) - - [Training Process](#training-process) - - [Training](#training) - - [Evaluation Process](#evaluation-process) - - [Evaluation](#evaluation) +- [Contents](#contents) + - [FCN-4 Description](#fcn-4-description) + - [Model Architecture](#model-architecture) + - [Features](#features) + - [Mixed Precision](#mixed-precision) + - [Environment Requirements](#environment-requirements) + - [Quick Start](#quick-start) + - [1. Download and preprocess the dataset](#1-download-and-preprocess-the-dataset) + - [2. setup parameters (src/model_utils/default_config.yaml)](#2-setup-parameters-srcmodel_utilsdefault_configyaml) + - [3. Train](#3-train) + - [4. Test](#4-test) + - [Script Description](#script-description) + - [Script and Sample Code](#script-and-sample-code) + - [Script Parameters](#script-parameters) + - [Training Process](#training-process) + - [Training](#training) + - [Evaluation Process](#evaluation-process) + - [Evaluation](#evaluation) - [Inference Process](#inference-process) - [Export MindIR](#export-mindir) - [Infer on Ascend310](#infer-on-ascend310) - [result](#result) -- [Model Description](#model-description) - - [Performance](#performance) - - [Evaluation Performance](#evaluation-performance) -- [ModelZoo Homepage](#modelzoo-homepage) + - [Model Description](#model-description) + - [Performance](#performance) + - [Evaluation Performance](#evaluation-performance) + - [ModelZoo Homepage](#modelzoo-homepage) ## [FCN-4 Description](#contents) @@ -309,8 +314,8 @@ AUC: 0.90995 | -------------------------- | ----------------------------------------------------------- | | Model Version | FCN-4 | | Resource | Ascend 910; CPU 2.60GHz, 56cores; Memory 314G; OS Euler2.8 | -| uploaded Date | 09/11/2020 (month/day/year) | -| MindSpore Version | r0.7.0 | +| uploaded Date | 07/05/2021 (month/day/year) | +| MindSpore Version | 1.3.0 | | Training Parameters | epoch=10, steps=534, batch_size = 32, lr=0.005 | | Optimizer | Adam | | Loss Function | Binary cross entropy | diff --git a/model_zoo/research/cv/ManiDP/Readme.md b/model_zoo/research/cv/ManiDP/Readme.md index dc2ffdde050..6160486525f 100755 --- a/model_zoo/research/cv/ManiDP/Readme.md +++ b/model_zoo/research/cv/ManiDP/Readme.md @@ -1,19 +1,22 @@ # Contents +- [Contents](#contents) - [Manifold Dynamic Pruning Description](#manifold-dynamic-pruning-description) - [Dataset](#dataset) - [Features](#features) - - [Mixed Precision](#mixed-precision(Ascend)) + - [Mixed Precision(Ascend)](#mixed-precisionascend) - [Environment Requirements](#environment-requirements) -- [Script Description](#script-description) - - [Script and Sample Code](#script-and-sample-code) - - [Training Process](#training-process) - - [Evaluation Process](#evaluation-process) - - [Evaluation](#evaluation) +- [Script description](#script-description) + - [Script and sample code](#script-and-sample-code) + - [Training process](#training-process) + - [Eval process](#eval-process) + - [Usage](#usage) + - [Launch](#launch) + - [Result](#result) - [Model Description](#model-description) - - [Performance](#performance) - - [Training Performance](#evaluation-performance) - - [Inference Performance](#evaluation-performance) + - [Performance](#performance) + - [Evaluation Performance](#evaluation-performance) + - [ResNet20 on CIFAR-10](#resnet20-on-cifar-10) - [Description of Random Situation](#description-of-random-situation) - [ModelZoo Homepage](#modelzoo-homepage) @@ -105,7 +108,7 @@ result: {'acc': 0.9204727564102564} | -------------------------- | -------------------------------------- | | Model Version | ResNet20 | | uploaded Date | 03/27/2021 (month/day/year) ； | -| MindSpore Version | 0.6.0-alpha | +| MindSpore Version | 1.2.1 | | Dataset | CIFAR-10 | | Parameters (M) | 0.27 | | FLOPs (M) | 18.74 | diff --git a/model_zoo/research/cv/SE-Net/README.md b/model_zoo/research/cv/SE-Net/README.md index dcbe1e62ceb..55af03da92d 100644 --- a/model_zoo/research/cv/SE-Net/README.md +++ b/model_zoo/research/cv/SE-Net/README.md @@ -1,6 +1,9 @@ # Contents +- [Contents](#contents) - [SE-Net Description](#se-net-description) + - [Description](#description) + - [Paper](#paper) - [Model Architecture](#model-architecture) - [Dataset](#dataset) - [Features](#features) @@ -11,16 +14,27 @@ - [Script and Sample Code](#script-and-sample-code) - [Script Parameters](#script-parameters) - [Training Process](#training-process) + - [Usage](#usage) + - [Running on Ascend](#running-on-ascend) + - [Running on GPU](#running-on-gpu) + - [Result](#result) - [Evaluation Process](#evaluation-process) + - [Usage](#usage-1) + - [Running on Ascend](#running-on-ascend-1) + - [Running on GPU](#running-on-gpu-1) + - [Result](#result-1) - [Inference Process](#inference-process) - - [Export MindIR](#export-mindir) - - [Infer on Ascend310](#infer-on-ascend310) - - [result](#result) + - [Export MindIR](#export-mindir) + - [Infer on Ascend310](#infer-on-ascend310) + - [result](#result-2) - [Model Description](#model-description) - [Performance](#performance) - [Evaluation Performance](#evaluation-performance) + - [SE-ResNet50 on ImageNet2012](#se-resnet50-on-imagenet2012) - [Inference Performance](#inference-performance) + - [SE-ResNet50 on ImageNet2012](#se-resnet50-on-imagenet2012-1) - [310Inference Performance](#310inference-performance) + - [SE-ResNet50 on ImageNet2012](#se-resnet50-on-imagenet2012-2) - [Description of Random Situation](#description-of-random-situation) - [ModelZoo Homepage](#modelzoo-homepage) @@ -284,8 +298,8 @@ result: {'top_5_accuracy': 93.86%, 'top_1_accuracy': 77.80%} | -------------------------- | ---------------------------------------------------------- | ---------------------------------------------------------- | | Model Version | SE-ResNet50 | SE-ResNet50 | | Resource | CentOs 8.2, Ascend 910，CPU 2.60GHz 192cores，Memory 755G | V100-PCIE 32G | -| uploaded Date | 03/19/2021 (month/day/year) | 07/14/2021 (month/day/year) | -| MindSpore Version | 0.7.0-alpha | 1.3.0 | +| uploaded Date | 07/05/2021 (month/day/year) | 07/14/2021 (month/day/year) | +| MindSpore Version | 1.3.0 | 1.3.0 | | Dataset | ImageNet2012 | ImageNet2012 | | Training Parameters | epoch=90, steps per epoch=5004, batch_size = 256 | epoch=90, steps per epoch=5004, batch_size = 256 | | Optimizer | Momentum | Momentum | @@ -306,8 +320,8 @@ result: {'top_5_accuracy': 93.86%, 'top_1_accuracy': 77.80%} | ------------------- | --------------------------- | --------------------------- | | Model Version | SE-ResNet50 | SE-ResNet50 | | Resource | Ascend 910 | V100-PCIE 32G | -| Uploaded Date | 03/19/2021 (month/day/year) | 07/14/2021 (month/day/year) | -| MindSpore Version | 0.7.0-alpha | 1.3.0 | +| Uploaded Date | 07/05/2021 (month/day/year) | 07/14/2021 (month/day/year) | +| MindSpore Version | 1.3.0 | 1.3.0 | | Dataset | ImageNet2012 | ImageNet2012 | | batch_size | 256 | 256 | | Accuracy | 77.74% | 77.66% | diff --git a/model_zoo/research/cv/glore_res200/README_CN.md b/model_zoo/research/cv/glore_res200/README_CN.md index b555915ae9e..1d416371b5b 100644 --- a/model_zoo/research/cv/glore_res200/README_CN.md +++ b/model_zoo/research/cv/glore_res200/README_CN.md @@ -3,7 +3,10 @@ -- [Glore_resnet200描述](#Glore_resnet200描述) +- [目录](#目录) +- [Glore_resnet200描述](#glore_resnet200描述) + - [概述](#概述) + - [论文](#论文) - [模型架构](#模型架构) - [数据集](#数据集) - [特性](#特性) @@ -14,19 +17,23 @@ - [脚本及样例代码](#脚本及样例代码) - [脚本参数](#脚本参数) - [训练过程](#训练过程) + - [用法](#用法) + - [Ascend处理器环境运行](#ascend处理器环境运行) + - [GPU处理器环境运行](#gpu处理器环境运行) - [训练结果](#训练结果) - [推理过程](#推理过程) + - [用法](#用法-1) + - [Ascend处理器环境运行](#ascend处理器环境运行-1) + - [GPU处理器环境运行](#gpu处理器环境运行-1) - [推理结果](#推理结果) - [模型描述](#模型描述) - [性能](#性能) - [训练性能](#训练性能) - - [Imagenet2012上的Glore_resnet200](#Imagenet2012上的Glore_resnet200) + - [ImageNet2012上的Glore_resnet200](#imagenet2012上的glore_resnet200) - [推理性能](#推理性能) - - [Imagenet2012上的Glore_resnet200](#Imagenet2012上的Glore_resnet200) - - [使用流程](#使用流程) - - [推理](#推理) + - [ImageNet2012上的Glore_resnet200](#imagenet2012上的glore_resnet200-1) - [随机情况说明](#随机情况说明) -- [ModelZoo主页](#ModelZoo主页) +- [ModelZoo主页](#modelzoo主页) @@ -285,7 +292,7 @@ result:{'top_1 acc':0.802303685897436} | 模型版本 | Glore_resnet200 |Glore_resnet200 | | 资源 | Ascend 910；CPU：2.60GHz，192核；内存：2048G |GPU-V100(SXM2) | | 上传日期 | 2021-03-34 |2021-05-25 | -| MindSpore版本 | 1.1.1-c76 |1.2.0-rc1 | +| MindSpore版本 | 1.1.1 |1.2.0 | | 数据集 | ImageNet2012 | ImageNet2012 | | 训练参数 | epoch=150, steps per epoch=1251, batch_size = 128 |epoch=150, steps per epoch=2502, batch_size = 64 | | 优化器 | NAG | NAG | @@ -307,7 +314,7 @@ result:{'top_1 acc':0.802303685897436} | 模型版本 | Glore_resnet200 | Glore_resnet200 | | 资源 | Ascend 910 | GPU | | 上传日期 | 2021-3-24 |2021-05-25 | -| MindSpore版本 | 1.1.1-c76 |1.2.0-rc1 | +| MindSpore版本 | 1.1.1 |1.2.0 | | 数据集 | 12万张图像 |12万张图像 | | batch_size | 128 |64 | | 输出 | 概率 |概率 | diff --git a/model_zoo/research/cv/renas/Readme.md b/model_zoo/research/cv/renas/Readme.md index 6bb56593ca7..619c430ea32 100755 --- a/model_zoo/research/cv/renas/Readme.md +++ b/model_zoo/research/cv/renas/Readme.md @@ -1,19 +1,22 @@ # Contents +- [Contents](#contents) - [ReNAS Description](#renas-description) - [Dataset](#dataset) - [Features](#features) - - [Mixed Precision](#mixed-precision) + - [Mixed Precision(Ascend)](#mixed-precisionascend) - [Environment Requirements](#environment-requirements) -- [Script Description](#script-description) - - [Script and Sample Code](#script-and-sample-code) - - [Training Process](#training-process) - - [Evaluation Process](#evaluation-process) - - [Evaluation](#evaluation) +- [Script description](#script-description) + - [Script and sample code](#script-and-sample-code) + - [Training process](#training-process) + - [Eval process](#eval-process) + - [Usage](#usage) + - [Launch](#launch) + - [Result](#result) - [Model Description](#model-description) - - [Performance](#performance) - - [Training Performance](#evaluation-performance) - - [Inference Performance](#evaluation-performance) + - [Performance](#performance) + - [Evaluation Performance](#evaluation-performance) + - [NASBench101-Net on CIFAR-10](#nasbench101-net-on-cifar-10) - [Description of Random Situation](#description-of-random-situation) - [ModelZoo Homepage](#modelzoo-homepage) @@ -104,7 +107,7 @@ result: {'acc': 0.9411057692307693} ckpt= ./resnet50-imgnet-0.65x-80.24.ckpt | -------------------------- | -------------------------------------- | | Model Version | NASBench101-Net | | uploaded Date | 03/27/2021 (month/day/year) ； | -| MindSpore Version | 0.6.0-alpha | +| MindSpore Version | 1.2.0 | | Dataset | CIFAR-10 | | Parameters (M) | 4.44 | | FLOPs (G) | 1.9 | diff --git a/model_zoo/research/cv/ssd_ghostnet/README.md b/model_zoo/research/cv/ssd_ghostnet/README.md index fa0b9f39e6e..5c63754dad9 100644 --- a/model_zoo/research/cv/ssd_ghostnet/README.md +++ b/model_zoo/research/cv/ssd_ghostnet/README.md @@ -1,26 +1,26 @@ # Contents - [Contents](#contents) - - [SSD Description](#ssd-description) - - [Model Architecture](#model-architecture) - - [Dataset](#dataset) - - [Environment Requirements](#environment-requirements) - - [Quick Start](#quick-start) - - [Script Description](#script-description) - - [Script and Sample Code](#script-and-sample-code) - - [Script Parameters](#script-parameters) - - [Training Process](#training-process) - - [Training on Ascend](#training-on-ascend) - - [Evaluation Process](#evaluation-process) - - [Evaluation on Ascend](#evaluation-on-ascend) +- [SSD Description](#ssd-description) +- [Model Architecture](#model-architecture) +- [Dataset](#dataset) +- [Environment Requirements](#environment-requirements) +- [Quick Start](#quick-start) +- [Script Description](#script-description) + - [Script and Sample Code](#script-and-sample-code) + - [Script Parameters](#script-parameters) + - [Training Process](#training-process) + - [Training on Ascend](#training-on-ascend) + - [Evaluation Process](#evaluation-process) + - [Evaluation on Ascend](#evaluation-on-ascend) - [Inference Process](#inference-process) - - [Export MindIR](#export-mindir) - - [Infer on Ascend310](#infer-on-ascend310) - - [result](#result) - - [Model Description](#model-description) - - [Performance](#performance) - - [Evaluation Performance](#evaluation-performance) - - [Inference Performance](#inference-performance) + - [Export MindIR](#export-mindir) + - [Infer on Ascend310](#infer-on-ascend310) + - [result](#result) +- [Model Description](#model-description) + - [Performance](#performance) + - [Evaluation Performance](#evaluation-performance) + - [Inference Performance](#inference-performance) - [310Inference Performance](#310inference-performance) # [SSD Description](#contents) @@ -312,7 +312,7 @@ mAP: 0.24270569394180577 | -------------------------- | -------------------------------------------------------------| | Model Version | SSD ghostnet | | Resource | Ascend 910; CPU 2.60GHz, 192cores; Memory 755G; OS Euler2.8 | -| MindSpore Version | 0.7.0 | +| MindSpore Version | 1.3.0 | | Dataset | COCO2017 | | Training Parameters | epoch = 500, batch_size = 32 | | Optimizer | Momentum | @@ -325,8 +325,8 @@ mAP: 0.24270569394180577 | ------------------- | ----------------------------| | Model Version | SSD ghostnet | | Resource | Ascend 910; OS Euler2.8 | -| Uploaded Date | 09/08/2020 (month/day/year) | -| MindSpore Version | 0.7.0 | +| Uploaded Date | 07/05/2021 (month/day/year) | +| MindSpore Version | 1.3.0 | | Dataset | COCO2017 | | batch_size | 1 | | outputs | mAP | @@ -339,8 +339,8 @@ mAP: 0.24270569394180577 | ------------------- | --------------------------- | | Model Version | SSD ghostnet | | Resource | Ascend 310; OS Euler2.8 | -| Uploaded Date | 06/01/2021 (month/day/year) | -| MindSpore Version | 1.2.0 | +| Uploaded Date | 07/05/2021 (month/day/year) | +| MindSpore Version | 1.3.0 | | Dataset | COCO2017 | | batch_size | 1 | | outputs | mAP | diff --git a/model_zoo/research/cv/wgan/README_CN.md b/model_zoo/research/cv/wgan/README_CN.md index dc01521b8f8..99dc1b438fb 100644 --- a/model_zoo/research/cv/wgan/README_CN.md +++ b/model_zoo/research/cv/wgan/README_CN.md @@ -3,7 +3,7 @@ - [目录](#目录) -- [WGAN描述](#WGAN描述) +- [WGAN描述](#wgan描述) - [模型架构](#模型架构) - [数据集](#数据集) - [环境要求](#环境要求) @@ -22,9 +22,10 @@ - [模型描述](#模型描述) - [性能](#性能) - [训练性能](#训练性能) - - [第一种情况（选用标准卷积DCGAN的生成器结构）](#第一种情况（选用标准卷积DCGAN的生成器结构）) - - [第二种情况（选用没有BatchNorm的卷积DCGAN的生成器结构）](#第二种情况（选用没有BatchNorm的卷积DCGAN的生成器结构）) + - [第一种情况（选用标准卷积DCGAN的生成器结构）](#第一种情况选用标准卷积dcgan的生成器结构) + - [第二种情况（选用没有BatchNorm的卷积DCGAN的生成器结构）](#第二种情况选用没有batchnorm的卷积dcgan的生成器结构) - [推理性能](#推理性能) + - [推理](#推理-1) - [随机情况说明](#随机情况说明) - [ModelZoo主页](#modelzoo主页) @@ -238,7 +239,7 @@ bash run_infer_310.sh [MINDIR_PATH] [CONFIG_PATH] [NEED_PREPROCESS] [NIMAGES] [D | -------------------------- | ----------------------------------------------------------- | | 资源 | Ascend 910 ；CPU 2.60GHz，192核；内存：755G | | 上传日期 | 2021-05-14 | -| MindSpore版本 | 1.2.0-alpha | +| MindSpore版本 | 1.2.0 | | 数据集 | LSUN-Bedrooms | | 训练参数 | max_epoch=25, batch_size=64, lr_init=0.00005 | | 优化器 | RMSProp | @@ -261,7 +262,7 @@ bash run_infer_310.sh [MINDIR_PATH] [CONFIG_PATH] [NEED_PREPROCESS] [NIMAGES] [D | -------------------------- | ----------------------------------------------------------- | | 资源 | Ascend 910 ；CPU 2.60GHz，192核；内存：755G | | 上传日期 | 2021-05-14 | -| MindSpore版本 | 1.2.0-alpha | +| MindSpore版本 | 1.2.0 | | 数据集 | LSUN-Bedrooms | | 训练参数 | max_epoch=25, batch_size=64, lr_init=0.00005 | | 优化器 | RMSProp | @@ -286,7 +287,7 @@ bash run_infer_310.sh [MINDIR_PATH] [CONFIG_PATH] [NEED_PREPROCESS] [NIMAGES] [D | ------------------- | --------------------------- | | 资源 | Ascend 910 | | 上传日期 | 2021-05-14 | -| MindSpore 版本 | 1.2.0-alpha | +| MindSpore 版本 | 1.2.0 | | 数据集 | LSUN-Bedrooms | | batch_size | 1 | | 输出 | 生成的图片 | diff --git a/model_zoo/research/recommend/autodis/README.md b/model_zoo/research/recommend/autodis/README.md index cb1afa21ec2..6b941b7fe1b 100644 --- a/model_zoo/research/recommend/autodis/README.md +++ b/model_zoo/research/recommend/autodis/README.md @@ -1,6 +1,7 @@ # Contents -- [AutoDis Description](#AutoDis-description) +- [Contents](#contents) +- [AutoDis Description](#autodis-description) - [Model Architecture](#model-architecture) - [Dataset](#dataset) - [Environment Requirements](#environment-requirements) @@ -17,9 +18,9 @@ - [Infer on Ascend310](#infer-on-ascend310) - [result](#result) - [Model Description](#model-description) - - [Performance](#performance) - - [Evaluation Performance](#evaluation-performance) - - [Inference Performance](#evaluation-performance) + - [Performance](#performance) + - [Training Performance](#training-performance) + - [Inference Performance](#inference-performance) - [Description of Random Situation](#description-of-random-situation) - [ModelZoo Homepage](#modelzoo-homepage) @@ -312,7 +313,7 @@ Inference result is saved in current path, you can find result in acc.log file. | Model Version | AutoDis | | Resource | Ascend 910 | | Uploaded Date | 12/12/2020 (month/day/year) | -| MindSpore Version | 0.3.0-alpha | +| MindSpore Version | 1.1.0 | | Dataset | [1] | | batch_size | 1000 | | outputs | accuracy |