Nigel
/
mindspore
forked from mindspore-Ecosystem/mindspore
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

update README at model_zoo

This commit is contained in:
dinglinhe 2021-04-12 15:26:54 +08:00
parent 0df1ef53bf
commit 31ea6fc7f7
110 changed files with 253 additions and 225 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
model_zoo/official/cv/FCN8s/README.md
View File

@ -192,7 +192,7 @@ Dataset used:
| Parameters | Ascend
| -------------------------- | -----------------------------------------------------------
| Model Version | FCN-8s
| Resource | Ascend 910 ；CPU 2.60GHz，192cores；Memory，755G
| Resource | Ascend 910; CPU 2.60GHz, 192cores; Memory 755G; OS Euler2.8
| uploaded Date | 12/30/2020 (month/day/year)
| MindSpore Version | 1.1.0-alpha
| Dataset | PASCAL VOC 2012 and SBD
@ -211,7 +211,7 @@ Dataset used:
| Parameters | Ascend
| ------------------- | ---------------------------
| Model Version | FCN-8s
| Resource | Ascend 910
| Resource | Ascend 910; OS Euler2.8
| Uploaded Date | 10/29/2020 (month/day/year)
| MindSpore Version | 1.1.0-alpha
| Dataset | PASCAL VOC 2012

2
model_zoo/official/cv/alexnet/README.md
View File

@ -193,7 +193,7 @@ Before running the command below, please check the checkpoint path used for eval
| Parameters | Ascend | GPU |
| -------------------------- | ------------------------------------------------------------| -------------------------------------------------|
| Resource | Ascend 910; CPU 2.60GHz, 192cores; Memory, 755G | NV SMX2 V100-32G |
| 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 |
| Dataset | CIFAR-10 | CIFAR-10 |

2
model_zoo/official/cv/alexnet/README_CN.md
View File

@ -197,7 +197,7 @@ train.py和config.py中主要参数如下：
| 参数 | Ascend | GPU |
| -------------------------- | ------------------------------------------------------------| -------------------------------------------------|
| 资源 | Ascend 910；CPU 2.60GHz, 192核；内存：755G | NV SMX2 V100-32G |
| 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 |
| 数据集 | CIFAR-10 | CIFAR-10 |

4
model_zoo/official/cv/centerface/README.md
View File

@ -521,7 +521,7 @@ CenterFace on 13K images(The annotation and data format must be the same as wide
| Parameters | CenterFace |
| -------------------------- | ----------------------------------------------------------- |
| Resource | Ascend 910; CPU 2.60GHz, 192cores; Memory, 755G |
| Resource | Ascend 910; CPU 2.60GHz, 192cores; Memory 755G; OS Euler2.8 |
| uploaded Date | 10/29/2020 (month/day/year) |
| MindSpore Version | 1.0.0 |
| Dataset | 13K images |
@ -541,7 +541,7 @@ CenterFace on 3.2K images(The annotation and data format must be the same as wid
| Parameters | CenterFace |
| -------------------------- | ----------------------------------------------------------- |
| Resource | Ascend 910; CPU 2.60GHz, 192cores; Memory, 755G |
| Resource | Ascend 910; CPU 2.60GHz, 192cores; Memory 755G; OS Euler2.8 |
| uploaded Date | 10/29/2020 (month/day/year) |
| MindSpore Version | 1.0.0 |
| Dataset | 3.2K images |

2
model_zoo/official/cv/cnn_direction_model/README.md
View File

@ -151,7 +151,7 @@ Results of evaluation will be printed after evaluation process is completed.
| Parameters | Ascend |
| -------------------------- | ------------------------------------------------------------|
| Resource | Ascend 910; CPU 2.60GHz, 192cores; Memory, 755G |
| Resource | Ascend 910; CPU 2.60GHz, 192cores; Memory 755G; OS Euler2.8 |
| uploaded Date | 01/15/2021 (month/day/year) |
| MindSpore Version | 1.1 |
| Dataset | FSNS |

4
model_zoo/official/cv/cnnctc/README.md
View File

@ -260,7 +260,7 @@ The model will be evaluated on the IIIT dataset, sample results and overall accu
| Parameters | CNNCTC |
| -------------------------- | ----------------------------------------------------------- |
| Model Version | V1 |
| Resource | Ascend 910 ；CPU 2.60GHz，192cores；Memory，755G |
| Resource | Ascend 910; CPU 2.60GHz, 192cores; Memory 755G; OS Euler2.8 |
| uploaded Date | 09/28/2020 (month/day/year) |
| MindSpore Version | 1.0.0 |
| Dataset | MJSynth,SynthText |
@ -277,7 +277,7 @@ The model will be evaluated on the IIIT dataset, sample results and overall accu
| Parameters | CNNCTC |
| ------------------- | --------------------------- |
| Model Version | V1 |
| Resource | Ascend 910 |
| Resource | Ascend 910; OS Euler2.8 |
| Uploaded Date | 09/28/2020 (month/day/year) |
| MindSpore Version | 1.0.0 |
| Dataset | IIIT5K |

4
model_zoo/official/cv/crnn/README.md
View File

@ -275,7 +275,7 @@ result CRNNAccuracy is: 0.806666666666
| Parameters | Ascend 910 |
| -------------------------- | --------------------------------------------------|
| Model Version | v1.0 |
| Resource | Ascend 910, CPU 2.60GHz 192cores, Memory 755G |
| Resource | Ascend 910; CPU 2.60GHz, 192cores; Memory 755G; OS Euler2.8 |
| uploaded Date | 12/15/2020 (month/day/year) |
| MindSpore Version | 1.0.1 |
| Dataset | Synth |
@ -295,7 +295,7 @@ result CRNNAccuracy is: 0.806666666666
| Parameters | SVT | IIIT5K |
| ------------------- | --------------------------- | --------------------------- |
| Model Version | V1.0 | V1.0 |
| Resource | Ascend 910 | Ascend 910 |
| Resource | Ascend 910; OS Euler2.8 | Ascend 910 |
| Uploaded Date | 12/15/2020 (month/day/year) | 12/15/2020 (month/day/year) |
| MindSpore Version | 1.0.1 | 1.0.1 |
| Dataset | SVT | IIIT5K |

2
model_zoo/official/cv/crnn_seq2seq_ocr/README.md
View File

@ -169,7 +169,7 @@ Annotation precision precision = 0.635204
| Parameters | Ascend |
| -------------------------- | ----------------------------------------------------------- |
| Model Version | V1 |
| Resource | Ascend 910 ；CPU 2.60GHz，192cores；Memory，755G |
| Resource | Ascend 910; CPU 2.60GHz, 192cores; Memory 755G; OS Euler2.8 |
| uploaded Date | 02/11/2021 (month/day/year) |
| MindSpore Version | 1.2.0 |
| Dataset | FSNS |

4
model_zoo/official/cv/ctpn/README.md
View File

@ -301,7 +301,7 @@ Evaluation result will be stored in the example path, you can find result like t
| Parameters | Ascend |
| -------------------------- | ------------------------------------------------------------ |
| Model Version | CTPN |
| Resource | Ascend 910, cpu:2.60GHz 192cores, memory:755G |
| Resource | Ascend 910; cpu 2.60GHz, 192cores; memory 755G; OS Euler2.8 |
| uploaded Date | 02/06/2021 |
| MindSpore Version | 1.1.1 |
| Dataset | 16930 images |
@ -318,7 +318,7 @@ Evaluation result will be stored in the example path, you can find result like t
| Parameters | Ascend |
| ------------------- | --------------------------- |
| Model Version | CTPN |
| Resource | Ascend 910, cpu:2.60GHz 192cores, memory:755G |
| Resource | Ascend 910; cpu 2.60GHz, 192cores; memory 755G; OS Euler2.8 |
| Uploaded Date | 02/06/2020 |
| MindSpore Version | 1.1.1 |
| Dataset | 229 images |

4
model_zoo/official/cv/deeplabv3/README.md
View File

@ -530,7 +530,7 @@ Inference result is saved in current path, you can find result in acc.log file.
| Parameters | Ascend 910
| -------------------------- | -------------------------------------- |
| Model Version | DeepLabV3
| Resource | Ascend 910 |
| Resource | Ascend 910; OS Euler2.8 |
| Uploaded Date | 09/04/2020 (month/day/year) |
| MindSpore Version | 0.7.0-alpha |
| Dataset | PASCAL VOC2012 + SBD |
@ -551,7 +551,7 @@ Inference result is saved in current path, you can find result in acc.log file.
| Parameters | Ascend |
| ------------------- | --------------------------- |
| Model Version | DeepLabV3 V1 |
| Resource | Ascend 910 |
| Resource | Ascend 910; OS Euler2.8 |
| Uploaded Date | 09/04/2020 (month/day/year) |
| MindSpore Version | 0.7.0-alpha |
| Dataset | VOC datasets |

18
model_zoo/official/cv/deeplabv3/README_CN.md
View File

@ -537,12 +537,12 @@ bash run_infer_310.sh [MINDIR_PATH] [DATA_PATH] [DATA_ROOT] [DATA_LIST] [DEVICE_
## 性能
### 评估性能
### 训练性能
| 参数 | Ascend 910
| -------------------------- | -------------------------------------- |
| 模型版本 | DeepLabV3
| 资源 | Ascend 910 |
| 资源 | Ascend 910；系统 Euler2.8 |
| 上传日期 | 2020-09-04 |
| MindSpore版本 | 0.7.0-alpha |
| 数据集 | PASCAL VOC2012 + SBD |
@ -555,6 +555,20 @@ bash run_infer_310.sh [MINDIR_PATH] [DATA_PATH] [DATA_ROOT] [DATA_LIST] [DEVICE_
| 微调检查点 | 443M （.ckpt文件） |
| 脚本 | [链接](https://gitee.com/mindspore/mindspore/tree/master/model_zoo/official/cv/deeplabv3) |
## 推理性能
| 参数 | Ascend |
| ------------------- | --------------------------- |
| 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 |
| 数据集 | VOC 数据集 |
| batch_size | 32 (s16); 16 (s8) |
| 输出 | 概率 |
| 准确率 | 8pcs: <br> s16: 77.37 <br> s8: 78.84% <br> s8_multiscale: 79.70% <br> s8_Flip: 79.89% |
| 推理模型 | 443M (.ckpt 文件) |
# 随机情况说明
dataset.py中设置了“create_dataset”函数内的种子，同时还使用了train.py中的随机种子。

4
model_zoo/official/cv/deeptext/README.md
View File

@ -210,7 +210,7 @@ class 1 precision is 84.24%, recall is 87.40%, F1 is 85.79%
| Parameters | Ascend |
| -------------------------- | ------------------------------------------------------------ |
| Model Version | Deeptext |
| Resource | Ascend 910, cpu:2.60GHz 192cores, memory:755G, OS:Euler2.8 |
| Resource | Ascend 910; cpu 2.60GHz, 192cores; memory 755G; OS Euler2.8 |
| uploaded Date | 12/26/2020 |
| MindSpore Version | 1.1.0 |
| Dataset | 66040 images |
@ -227,7 +227,7 @@ class 1 precision is 84.24%, recall is 87.40%, F1 is 85.79%
| Parameters | Ascend |
| ------------------- | --------------------------- |
| Model Version | Deeptext |
| Resource | Ascend 910, cpu:2.60GHz 192cores, memory:755G |
| Resource | Ascend 910; cpu 2.60GHz, 192cores; memory 755G; OS Euler2.8 |
| Uploaded Date | 12/26/2020 |
| MindSpore Version | 1.1.0 |
| Dataset | 229 images |

4
model_zoo/official/cv/densenet/README.md
View File

@ -330,7 +330,7 @@ You can modify the training behaviour through the various flags in the `train.py
| Parameters | Ascend | GPU |
| ------------------- | --------------------------- | --------------------------- |
| Model Version | DenseNet121 | DenseNet121 |
| Resource | Ascend 910 | Tesla V100-PCIE |
| Resource | Ascend 910; OS Euler2.8 | Tesla V100-PCIE |
| Uploaded Date | 09/15/2020 (month/day/year) | 01/27/2021 (month/day/year) |
| MindSpore Version | 1.0.0 | 1.1.0 |
| Dataset | ImageNet | ImageNet |
@ -343,7 +343,7 @@ You can modify the training behaviour through the various flags in the `train.py
| Parameters | Ascend | GPU |
| ------------------- | --------------------------- | ---------------------------- |
| Model Version | DenseNet121 | DenseNet121 |
| Resource | Ascend 910 | Tesla V100-PCIE |
| Resource | Ascend 910; OS Euler2.8 | Tesla V100-PCIE |
| Uploaded Date | 09/15/2020 (month/day/year) | 02/04/2021 (month/day/year) |
| MindSpore Version | 1.0.0 | 1.1.1 |
| Dataset | ImageNet | ImageNet |

4
model_zoo/official/cv/dpn/README.md
View File

@ -274,7 +274,7 @@ All results are validated at image size of 224x224. The dataset preprocessing an
| Parameters | Ascend |
| ----------------- | --------------------------- |
| Model Version | DPN92 (Train) |
| Resource | Ascend 910 |
| Resource | Ascend 910; OS Euler2.8 |
| Uploaded Date | 12/20/2020 (month/day/year) |
| MindSpore Version | 1.1.0 |
| Dataset | ImageNet-1K |
@ -289,7 +289,7 @@ All results are validated at image size of 224x224. The dataset preprocessing an
| Parameters | Ascend |
| ----------------- | --------------------------------- |
| Model Version | DPN92 |
| Resource | Ascend 910 |
| Resource | Ascend 910; OS Euler2.8 |
| Uploaded Date | 12/20/2020 (month/day/year) |
| MindSpore Version | 1.1.0 |
| Dataset | ImageNet-1K |

4
model_zoo/official/cv/faster_rcnn/README.md
View File

@ -380,7 +380,7 @@ Inference result is saved in current path, you can find result like this in acc.
| Parameters | Ascend | GPU |
| -------------------------- | ----------------------------------------------------------- |----------------------------------------------------------- |
| Model Version | V1 | V1 |
| Resource | Ascend 910 ；CPU 2.60GHz，192cores；Memory，755G |V100-PCIE 32G |
| Resource | Ascend 910; CPU 2.60GHz, 192cores; Memory 755G; OS Euler2.8 |V100-PCIE 32G |
| uploaded Date | 08/31/2020 (month/day/year) |02/10/2021 (month/day/year) |
| MindSpore Version | 1.0.0 |1.2.0 |
| Dataset | COCO2017 |COCO2017 |
@ -397,7 +397,7 @@ Inference result is saved in current path, you can find result like this in acc.
| Parameters | Ascend |GPU |
| ------------------- | --------------------------- |--------------------------- |
| Model Version | V1 | V1 |
| Resource | Ascend 910 |GPU |
| Resource | Ascend 910; OS Euler2.8 |GPU |
| Uploaded Date | 08/31/2020 (month/day/year) |02/10/2021 (month/day/year) |
| MindSpore Version | 1.0.0 | 1.2.0 |
| Dataset | COCO2017 |COCO2017 |

8
model_zoo/official/cv/googlenet/README.md
View File

@ -332,7 +332,7 @@ For more configuration details, please refer the script `config.py`.
| Parameters | Ascend | GPU |
| -------------------------- | ----------------------------------------------------------- | ---------------------- |
| Model Version | Inception V1 | Inception V1 |
| Resource | Ascend 910 ；CPU 2.60GHz，192cores；Memory，755G | NV SMX2 V100-32G |
| 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 |
| Dataset | CIFAR-10 | CIFAR-10 |
@ -353,7 +353,7 @@ For more configuration details, please refer the script `config.py`.
| Parameters | Ascend |
| -------------------------- | ----------------------------------------------------------- |
| Model Version | Inception V1 |
| Resource | Ascend 910, CPU 2.60GHz, 56cores, Memory 314G |
| 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 |
| Dataset | 1200k images |
@ -375,7 +375,7 @@ For more configuration details, please refer the script `config.py`.
| Parameters | Ascend | GPU |
| ------------------- | --------------------------- | --------------------------- |
| Model Version | Inception V1 | Inception V1 |
| Resource | Ascend 910 | GPU |
| 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 |
| Dataset | CIFAR-10, 10,000 images | CIFAR-10, 10,000 images |
@ -389,7 +389,7 @@ For more configuration details, please refer the script `config.py`.
| Parameters | Ascend |
| ------------------- | --------------------------- |
| Model Version | Inception V1 |
| Resource | Ascend 910 |
| Resource | Ascend 910; OS Euler2.8 |
| Uploaded Date | 10/28/2020 (month/day/year) |
| MindSpore Version | 1.0.0 |
| Dataset | 1200k images |

8
model_zoo/official/cv/googlenet/README_CN.md
View File

@ -307,7 +307,7 @@ GoogleNet由多个inception模块串联起来，可以更加深入。 降维的
| 参数 | Ascend | GPU |
| -------------------------- | ----------------------------------------------------------- | ---------------------- |
| 模型版本 | Inception V1 | Inception V1 |
| 资源 | Ascend 910 ；CPU 2.60GHz，192核；内存：755G | NV SMX2 V100-32G |
| 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 |
| 数据集 | CIFAR-10 | CIFAR-10 |
@ -328,7 +328,7 @@ GoogleNet由多个inception模块串联起来，可以更加深入。 降维的
| 参数 | Ascend |
| -------------------------- | ----------------------------------------------------------- |
| 模型版本 | Inception V1 |
| 资源 | Ascend 910, CPU 2.60GHz, 56核, 内存：314G |
| 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 |
| 数据集 | 120万张图像 |
@ -350,7 +350,7 @@ GoogleNet由多个inception模块串联起来，可以更加深入。 降维的
| 参数 | Ascend | GPU |
| ------------------- | --------------------------- | --------------------------- |
| 模型版本 | Inception V1 | Inception V1 |
| 资源 | Ascend 910 | GPU |
| 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 |
| 数据集 | CIFAR-10, 1万张图像 | CIFAR-10, 1万张图像 |
@ -364,7 +364,7 @@ GoogleNet由多个inception模块串联起来，可以更加深入。 降维的
| 参数 | Ascend |
| ------------------- | --------------------------- |
| 模型版本 | Inception V1 |
| 资源 | Ascend 910 |
| 资源 | Ascend 910；系统 Euler2.8 |
| 上传日期 | 2020-09-20 |
| MindSpore版本 | 0.7.0-alpha |
| 数据集 | 12万张图像 |

4
model_zoo/official/cv/inceptionv3/README.md
View File

@ -247,7 +247,7 @@ metric: {'Loss': 1.778, 'Top1-Acc':0.788, 'Top5-Acc':0.942}
| Parameters | Ascend |
| -------------------------- | ---------------------------------------------- |
| Model Version | InceptionV3 |
| Resource | Ascend 910, cpu:2.60GHz 192cores, memory:755G |
| Resource | Ascend 910; cpu 2.60GHz, 192cores; memory 755G; OS Euler2.8 |
| uploaded Date | 08/21/2020 |
| MindSpore Version | 0.6.0-beta |
| Dataset | 1200k images |
@ -269,7 +269,7 @@ metric: {'Loss': 1.778, 'Top1-Acc':0.788, 'Top5-Acc':0.942}
| Parameters | Ascend |
| ------------------- | --------------------------- |
| Model Version | InceptionV3 |
| Resource | Ascend 910, cpu:2.60GHz 192cores, memory:755G |
| Resource | Ascend 910; cpu 2.60GHz, 192cores; memory 755G; OS Euler2.8 |
| Uploaded Date | 08/22/2020 |
| MindSpore Version | 0.6.0-beta |
| Dataset | 50k images |

4
model_zoo/official/cv/inceptionv3/README_CN.md
View File

@ -252,7 +252,7 @@ metric:{'Loss':1.778, 'Top1-Acc':0.788, 'Top5-Acc':0.942}
| 参数 | Ascend |
| -------------------------- | ---------------------------------------------- |
| 模型版本 | InceptionV3 |
| 资源 | Ascend 910, CPU:2.60GHz，192核，内存：755G |
| 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 |
| 数据集 | 120万张图像 |
@ -273,7 +273,7 @@ metric:{'Loss':1.778, 'Top1-Acc':0.788, 'Top5-Acc':0.942}
| 参数 | Ascend |
| ------------------- | --------------------------- |
| 模型版本 | InceptionV3 |
| 资源 | Ascend 910，CPU： 2.60GHz，192核；内存：755G |
| 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 |
| 数据集 | 5万张图像 |

4
model_zoo/official/cv/inceptionv4/README.md
View File

@ -232,7 +232,7 @@ metric: {'Loss': 0.8144, 'Top1-Acc': 0.8009, 'Top5-Acc': 0.9457}
| Parameters | Ascend | GPU |
| -------------------------- | --------------------------------------------- | -------------------------------- |
| Model Version | InceptionV4 | InceptionV4 |
| Resource | Ascend 910, cpu:2.60GHz 192cores, memory:755G | NV SMX2 V100-32G |
| Resource | Ascend 910; cpu 2.60GHz, 192cores; memory 755G; OS Euler2.8 | NV SMX2 V100-32G |
| uploaded Date | 11/04/2020 | 03/05/2021 |
| MindSpore Version | 1.0.0 | 1.0.0 |
| Dataset | 1200k images | 1200K images |
@ -253,7 +253,7 @@ metric: {'Loss': 0.8144, 'Top1-Acc': 0.8009, 'Top5-Acc': 0.9457}
| Parameters | Ascend | GPU |
| ------------------- | --------------------------------------------- | ---------------------------------- |
| Model Version | InceptionV4 | InceptionV4 |
| Resource | Ascend 910, cpu:2.60GHz 192cores, memory:755G | NV SMX2 V100-32G |
| Resource | Ascend 910; cpu 2.60GHz, 192cores; memory 755G; OS Euler2.8 | NV SMX2 V100-32G |
| Uploaded Date | 11/04/2020 | 03/05/2021 |
| MindSpore Version | 1.0.0 | 1.0.0 |
| Dataset | 50k images | 50K images |

2
model_zoo/official/cv/lenet/README.md
View File

@ -165,7 +165,7 @@ You can view the results through the file "log.txt". The accuracy of the test da
| Parameters | LeNet |
| -------------------------- | ----------------------------------------------------------- |
| Resource | Ascend 910 ；CPU 2.60GHz，192cores；Memory，755G |
| 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 |
| Dataset | MNIST |

2
model_zoo/official/cv/lenet/README_CN.md
View File

@ -167,7 +167,7 @@ sh run_standalone_eval_ascend.sh Data ckpt/checkpoint_lenet-1_1875.ckpt
| 参数 | LeNet |
| -------------------------- | ----------------------------------------------------------- |
| 资源 | Ascend 910; CPU：2.60GHz,192核；内存：755G |
| 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 |
| 数据集 | MNIST |

2
model_zoo/official/cv/lenet_quant/Readme.md
View File

@ -160,7 +160,7 @@ You can view the results through the file "log.txt". The accuracy of the test da
| Parameters | LeNet |
| -------------------------- | ----------------------------------------------------------- |
| Resource | Ascend 910 CPU 2.60GHz 192cores Memory 755G |
| 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 |
| Dataset | MNIST |

2
model_zoo/official/cv/lenet_quant/Readme_CN.md
View File

@ -164,7 +164,7 @@ python eval.py --data_path Data --ckpt_path ckpt/checkpoint_lenet-1_937.ckpt > l
| 参数 | LeNet |
| -------------------------- | ----------------------------------------------------------- |
| 资源 | Ascend 910 CPU：2.60GHz，192核，内存：755G |
| 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 |
| 数据集 | MNIST |

4
model_zoo/official/cv/maskrcnn/README.md
View File

@ -561,7 +561,7 @@ Accumulating evaluation results...
| Parameters | Ascend |
| -------------------------- | ----------------------------------------------------------- |
| Model Version | V1 |
| Resource | Ascend 910; CPU 2.60GHz, 192cores; Memory, 755G |
| 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 |
| Dataset | COCO2017 |
@ -582,7 +582,7 @@ Accumulating evaluation results...
| Parameters | Ascend |
| ------------------- | --------------------------- |
| Model Version | V1 |
| Resource | Ascend 910 |
| Resource | Ascend 910; OS Euler2.8 |
| Uploaded Date | 08/01/2020 (month/day/year) |
| MindSpore Version | 1.0.0 |
| Dataset | COCO2017 |

4
model_zoo/official/cv/maskrcnn/README_CN.md
View File

@ -558,7 +558,7 @@ Accumulating evaluation results...
| 参数 | MaskRCNN |
| ------------------- | --------------------------------------------------------- |
| 模型版本 | V1 |
| 资源 | Ascend 910；CPU： 2.60GHz，192核；内存：755G |
| 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 |
| 数据集 | COCO2017 |
@ -575,7 +575,7 @@ Accumulating evaluation results...
| 参数 | MaskRCNN |
| --------------------- | ----------------------------- |
| 模型版本 | V1 |
| 资源 | Ascend 910 |
| 资源 | Ascend 910；系统 Euler2.8 |
| 上传日期 | 2020-08-01 |
| MindSpore版本 | 0.6.0-alpha |
| 数据集 | COCO2017 |

4
model_zoo/official/cv/maskrcnn_mobilenetv1/README.md
View File

@ -412,7 +412,7 @@ Accumulating evaluation results...
| Parameters | Ascend |
| -------------------------- | ----------------------------------------------------------- |
| Model Version | V1 |
| Resource | Ascend 910; CPU 2.60GHz, 192cores; Memory, 755G |
| Resource | Ascend 910; CPU 2.60GHz, 192cores; Memory 755G; OS Euler2.8 |
| uploaded Date | 12/01/2020 (month/day/year) |
| MindSpore Version | 1.0.0 |
| Dataset | COCO2017 |
@ -430,7 +430,7 @@ Accumulating evaluation results...
| Parameters | Ascend |
| ------------------- | --------------------------- |
| Model Version | V1 |
| Resource | Ascend 910 |
| Resource | Ascend 910; OS Euler2.8 |
| Uploaded Date | 12/01/2020 (month/day/year) |
| MindSpore Version | 1.0.0 |
| Dataset | COCO2017 |

2
model_zoo/official/cv/mobilenetv1/README.md
View File

@ -164,7 +164,7 @@ result: {'top_5_accuracy': 0.9010016025641026, 'top_1_accuracy': 0.7128004807692
| Parameters | MobilenetV1 |
| -------------------------- | ------------------------------------------------------------------------------------------- |
| Model Version | V1 |
| Resource | Ascend 910 * 4, cpu:2.60GHz 192cores, memory:755G |
| Resource | Ascend 910 * 4; cpu 2.60GHz, 192cores; memory 755G; OS Euler2.8 |
| uploaded Date | 11/28/2020 |
| MindSpore Version | 1.0.0 |
| Dataset | ImageNet2012 |

2
model_zoo/official/cv/mobilenetv2/README.md
View File

@ -225,7 +225,7 @@ python export.py --platform [PLATFORM] --ckpt_file [CKPT_PATH] --file_format [EX
| Parameters | MobilenetV2 | |
| -------------------------- | ---------------------------------------------------------- | ------------------------- |
| Model Version | V1 | V1 |
| Resource | Ascend 910, cpu:2.60GHz 192cores, memory:755G | NV SMX2 V100-32G |
| 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 |
| Dataset | ImageNet | ImageNet |

2
model_zoo/official/cv/mobilenetv2/README_CN.md
View File

@ -231,7 +231,7 @@ python export.py --platform [PLATFORM] --ckpt_file [CKPT_PATH] --file_format [EX
| 参数 | MobilenetV2 | |
| -------------------------- | ---------------------------------------------------------- | ------------------------- |
| 模型版本 | V1 | V1 |
| 资源 | Ascend 910；CPU：2.60GHz，192核；内存：755G | NV SMX2 V100-32G |
| 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 |
| 数据集 | ImageNet | ImageNet |

4
model_zoo/official/cv/mobilenetv2_quant/README_CN.md
View File

@ -182,7 +182,7 @@ result:{'acc':0.71976314102564111}
| 参数 | MobilenetV2 |
| -------------------------- | ---------------------------------------------------------- |
| 模型版本 | V2 |
| 资源 | Ascend 910；CPU：2.60GHz，192核；内存：755G |
| 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 |
| 数据集 | ImageNet |
@ -202,7 +202,7 @@ result:{'acc':0.71976314102564111}
| 参数 | |
| -------------------------- | ----------------------------- |
| 模型版本 | V2 |
| 资源 | Ascend 910 |
| 资源 | Ascend 910；系统 Euler2.8 |
| 上传日期 | 2020-06-06 |
| MindSpore版本 | 0.3.0 |
| 数据集 | ImageNet, 1.2W |

4
model_zoo/official/cv/mobilenetv2_quant/Readme.md
View File

@ -169,7 +169,7 @@ result: {'acc': 0.71976314102564111}
| Parameters | MobilenetV2 |
| -------------------------- | ---------------------------------------------------------- |
| Model Version | V2 |
| Resource | Ascend 910, cpu:2.60GHz 192cores, memory:755G |
| Resource | Ascend 910; cpu 2.60GHz, 192cores; memory 755G; OS Euler2.8 |
| uploaded Date | 06/06/2020 |
| MindSpore Version | 0.3.0 |
| Dataset | ImageNet |
@ -189,7 +189,7 @@ result: {'acc': 0.71976314102564111}
| Parameters | |
| -------------------------- | ----------------------------- |
| Model Version | V2 |
| Resource | Ascend 910 |
| Resource | Ascend 910; OS Euler2.8 |
| uploaded Date | 06/06/2020 |
| MindSpore Version | 0.3.0 |
| Dataset | ImageNet, 1.2W |

2
model_zoo/official/cv/openpose/README.md
View File

@ -208,7 +208,7 @@ For more configuration details, please refer the script `config.py`.
| Parameters | Ascend
| -------------------------- | -----------------------------------------------------------
| Model Version | openpose
| Resource | Ascend 910 ；CPU 2.60GHz，192cores；Memory，755G
| 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
| Training Parameters | epoch=60(1pcs)/80(8pcs), steps=30k(1pcs)/5k(8pcs), batch_size=10, init_lr=0.0001

2
model_zoo/official/cv/psenet/README.md
View File

@ -184,7 +184,7 @@ Calculated!{"precision": 0.814796668299853, "recall": 0.8006740491092923, "hmean
| Parameters | PSENet |
| -------------------------- | ----------------------------------------------------------- |
| Model Version | V1 |
| Resource | Ascend 910 ；CPU 2.60GHz，192cores；Memory，755G |
| Resource | Ascend 910; CPU 2.60GHz, 192cores; Memory 755G; OS Euler2.8 |
| uploaded Date | 09/30/2020 (month/day/year) |
| MindSpore Version | 1.0.0 |
| Dataset | ICDAR2015 |

4
model_zoo/official/cv/psenet/README_CN.md
View File

@ -182,7 +182,7 @@ Calculated!{"precision": 0.8147966668299853，"recall"：0.8006740491092923，"h
| 参数 | PSENet |
| -------------------------- | ----------------------------------------------------------- |
| 模型版本 | Inception V1 |
| 资源 | Ascend 910； CPU： 2.60GHz，192内核；内存，755G |
| 资源 | Ascend 910； CPU 2.60GHz，192内核；内存 755G；系统 Euler2.8 |
| 上传日期 | 2020-09-15 |
| MindSpore版本 | 1.0-alpha |
| 数据集 | ICDAR2015 |
@ -202,7 +202,7 @@ Calculated!{"precision": 0.8147966668299853，"recall"：0.8006740491092923，"h
| 参数 | PSENet |
| ------------------- | --------------------------- |
| 模型版本 | Inception V1 |
| 资源 | Ascend 910 |
| 资源 | Ascend 910；系统 Euler2.8 |
| 上传日期 | 2020/09/15 |
| MindSpore版本 | 1.0-alpha |
| 数据集| ICDAR2015 |

24
model_zoo/official/cv/resnet/README.md
View File

@ -525,7 +525,7 @@ top1_accuracy:70.42, top5_accuracy:89.7
| Parameters | Ascend 910 |
| -------------------------- | -------------------------------------- |
| Model Version | ResNet18 |
| Resource | Ascend 910，CPU 2.60GHz 192cores，Memory 755G |
| 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 |
| Dataset | CIFAR-10 |
@ -545,7 +545,7 @@ top1_accuracy:70.42, top5_accuracy:89.7
| Parameters | Ascend 910 |
| -------------------------- | -------------------------------------- |
| Model Version | ResNet18 |
| Resource | Ascend 910，CPU 2.60GHz 192cores，Memory 755G |
| 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 |
| Dataset | ImageNet2012 |
@ -565,7 +565,7 @@ top1_accuracy:70.42, top5_accuracy:89.7
| Parameters | Ascend 910 | GPU |
| -------------------------- | -------------------------------------- |---------------------------------- |
| Model Version | ResNet50-v1.5 |ResNet50-v1.5|
| Resource | Ascend 910，CPU 2.60GHz 192cores，Memory 755G | GPU(Tesla V100 SXM2)，CPU 2.1GHz 24cores，Memory 128G
| 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 |
| Dataset | CIFAR-10 | CIFAR-10
@ -585,7 +585,7 @@ top1_accuracy:70.42, top5_accuracy:89.7
| Parameters | Ascend 910 | GPU |
| -------------------------- | -------------------------------------- |---------------------------------- |
| Model Version | ResNet50-v1.5 |ResNet50-v1.5|
| Resource | Ascend 910，CPU 2.60GHz 192cores，Memory 755G | GPU(Tesla V100 SXM2)，CPU 2.1GHz 24cores，Memory 128G
| 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 |
| Dataset | ImageNet2012 | ImageNet2012|
@ -605,7 +605,7 @@ top1_accuracy:70.42, top5_accuracy:89.7
| Parameters | Ascend 910 | GPU |
| -------------------------- | -------------------------------------- |---------------------------------- |
| Model Version | ResNet101 |ResNet101|
| Resource | Ascend 910，CPU 2.60GHz 192cores，Memory 755G | GPU(Tesla V100 SXM2)，CPU 2.1GHz 24cores，Memory 128G
| 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 |
| Dataset | ImageNet2012 | ImageNet2012|
@ -625,7 +625,7 @@ top1_accuracy:70.42, top5_accuracy:89.7
| Parameters | Ascend 910
| -------------------------- | ------------------------------------------------------------------------ |
| Model Version | SE-ResNet50 |
| Resource | Ascend 910，CPU 2.60GHz 192cores，Memory 755G |
| 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 |
| Dataset | ImageNet2012 |
@ -647,7 +647,7 @@ top1_accuracy:70.42, top5_accuracy:89.7
| Parameters | Ascend |
| ------------------- | --------------------------- |
| Model Version | ResNet18 |
| Resource | Ascend 910 |
| Resource | Ascend 910; OS Euler2.8 |
| Uploaded Date | 02/25/2021 (month/day/year) |
| MindSpore Version | 1.1.1-alpha |
| Dataset | CIFAR-10 |
@ -661,7 +661,7 @@ top1_accuracy:70.42, top5_accuracy:89.7
| Parameters | Ascend |
| ------------------- | --------------------------- |
| Model Version | ResNet18 |
| Resource | Ascend 910 |
| Resource | Ascend 910; OS Euler2.8 |
| Uploaded Date | 02/25/2021 (month/day/year) |
| MindSpore Version | 1.1.1-alpha |
| Dataset | ImageNet2012 |
@ -675,7 +675,7 @@ top1_accuracy:70.42, top5_accuracy:89.7
| Parameters | Ascend | GPU |
| ------------------- | --------------------------- | --------------------------- |
| Model Version | ResNet50-v1.5 | ResNet50-v1.5 |
| Resource | Ascend 910 | GPU |
| 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 |
| Dataset | CIFAR-10 | CIFAR-10 |
@ -689,7 +689,7 @@ top1_accuracy:70.42, top5_accuracy:89.7
| Parameters | Ascend | GPU |
| ------------------- | --------------------------- | --------------------------- |
| Model Version | ResNet50-v1.5 | ResNet50-v1.5 |
| Resource | Ascend 910 | GPU |
| 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 |
| Dataset | ImageNet2012 | ImageNet2012 |
@ -703,7 +703,7 @@ top1_accuracy:70.42, top5_accuracy:89.7
| Parameters | Ascend | GPU |
| ------------------- | --------------------------- | --------------------------- |
| Model Version | ResNet101 | ResNet101 |
| Resource | Ascend 910 | GPU |
| 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 |
| Dataset | ImageNet2012 | ImageNet2012 |
@ -717,7 +717,7 @@ top1_accuracy:70.42, top5_accuracy:89.7
| Parameters | Ascend |
| ------------------- | --------------------------- |
| Model Version | SE-ResNet50 |
| Resource | Ascend 910 |
| Resource | Ascend 910; OS Euler2.8 |
| Uploaded Date | 08/16/2020 (month/day/year) |
| MindSpore Version | 0.7.0-alpha |
| Dataset | ImageNet2012 |

12
model_zoo/official/cv/resnet/README_CN.md
View File

@ -492,7 +492,7 @@ top1_accuracy:70.42, top5_accuracy:89.7
| 参数 | Ascend 910 |
| -------------------------- | -------------------------------------- |
| 模型版本 | ResNet18 |
| 资源 | Ascend 910；CPU：2.60GHz，192核；内存：755G |
| 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 |
| 数据集 | CIFAR-10 |
@ -512,7 +512,7 @@ top1_accuracy:70.42, top5_accuracy:89.7
| 参数 | Ascend 910 |
| -------------------------- | -------------------------------------- |
| 模型版本 | ResNet18 |
| 资源 | Ascend 910；CPU：2.60GHz，192核；内存：755G |
| 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 |
| 数据集 | ImageNet2012 |
@ -532,7 +532,7 @@ top1_accuracy:70.42, top5_accuracy:89.7
| 参数 | Ascend 910 | GPU |
| -------------------------- | -------------------------------------- |---------------------------------- |
| 模型版本 | ResNet50-v1.5 |ResNet50-v1.5|
| 资源 | Ascend 910；CPU：2.60GHz，192核；内存：755G | GPU(Tesla V100 SXM2)；CPU：2.1GHz，24核；内存：128G
| 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 |
| 数据集 | CIFAR-10 | CIFAR-10
@ -552,7 +552,7 @@ top1_accuracy:70.42, top5_accuracy:89.7
| 参数 | Ascend 910 | GPU |
| -------------------------- | -------------------------------------- |---------------------------------- |
| 模型版本 | ResNet50-v1.5 |ResNet50-v1.5|
| 资源 | Ascend 910；CPU：2.60GHz，192核；内存：755G | GPU(Tesla V100 SXM2)；CPU：2.1GHz，24核；内存：128G
| 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 |
| 数据集 | ImageNet2012 | ImageNet2012|
@ -572,7 +572,7 @@ top1_accuracy:70.42, top5_accuracy:89.7
| 参数 | Ascend 910 | GPU |
| -------------------------- | -------------------------------------- |---------------------------------- |
| 模型版本 | ResNet101 |ResNet101|
| 资源 | Ascend 910；CPU：2.60GHz，192核；内存：755G GPU(Tesla V100 SXM2)；CPU：2.1GHz，24核；内存：128G
| 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 |
| 数据集 | ImageNet2012 | ImageNet2012|
@ -592,7 +592,7 @@ top1_accuracy:70.42, top5_accuracy:89.7
| 参数 | Ascend 910
| -------------------------- | ------------------------------------------------------------------------ |
| 模型版本 | SE-ResNet50 |
| 资源 | Ascend 910；CPU：2.60GHz，192核；内存：755G |
| 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 |
| 数据集 | ImageNet2012 |

2
model_zoo/official/cv/resnet152/README-CN.md
View File

@ -179,7 +179,7 @@ result: {'top_5_accuracy': 0.9438420294494239, 'top_1_accuracy': 0.78817221518}
| 参数 | Ascend 910 |
|---|---|
| 模型版本 | ResNet152 |
| 资源 | Ascend 910；CPU：2.60GHz，192核；内存：755G |
| 资源 | Ascend 910；CPU 2.60GHz，192核；内存 755G；系统 Euler2.8 |
| 上传日期 |2021-02-10 ; |
| MindSpore版本 | 1.0.1 |
| 数据集 | ImageNet2012 |

4
model_zoo/official/cv/resnet50_quant/README.md
View File

@ -178,7 +178,7 @@ result: {'acc': 0.76576314102564111}
| Parameters | Ascend |
| -------------------------- | ----------------------------------------------------------- |
| Model Version | ResNet50 V1.5 |
| Resource | Ascend 910, CPU 2.60GHz, 56cores, Memory 314G |
| 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 |
| Dataset | ImageNet |
@ -198,7 +198,7 @@ result: {'acc': 0.76576314102564111}
| Parameters | Ascend |
| ------------------- | --------------------------- |
| Model Version | ResNet50 V1.5 |
| Resource | Ascend 910, CPU 2.60GHz, 56cores, Memory 314G |
| 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 |
| Dataset | ImageNet |

4
model_zoo/official/cv/resnet50_quant/README_CN.md
View File

@ -186,7 +186,7 @@ result:{'acc'：0.76576314102564111}
| 参数 | Resnet50 |
| -------------------------- | ---------------------------------------------------------- |
| 模型版本 | V1 |
| 资源 | Ascend 910； CPU：2.60GHz，192核；内存：755G |
| 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 |
| 数据集 | ImageNet |
@ -206,7 +206,7 @@ result:{'acc'：0.76576314102564111}
| 参数列表 | Resnet50 |
| -------------------------- | ----------------------------- |
| 模型版本 | V1 |
| 资源 | Ascend 910 |
| 资源 | Ascend 910；系统 Euler2.8 |
| 上传日期 | 2020-06-06 |
| MindSpore版本 | 0.3.0 |
| 数据集 | ImageNet, 1.2W |

4
model_zoo/official/cv/resnet_thor/README.md
View File

@ -258,7 +258,7 @@ Inference result will be stored in the example path, whose folder name is "eval"
| Parameters | Ascend 910 | GPU |
| -------------------------- | -------------------------------------- |---------------------------------- |
| Model Version | ResNet50-v1.5 |ResNet50-v1.5|
| Resource | Ascend 910，CPU 2.60GHz 192cores，Memory 755G | GPU(Tesla V100 SXM2)，CPU 2.1GHz 24cores，Memory 128G
| 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 |
| Dataset | ImageNet2012 | ImageNet2012|
@ -278,7 +278,7 @@ Inference result will be stored in the example path, whose folder name is "eval"
| Parameters | Ascend 910 | GPU |
| ------------------- | --------------------------- | --------------------------- |
| Model Version | ResNet50-v1.5 | ResNet50-v1.5 |
| Resource | Ascend 910 | GPU |
| 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 |
| Dataset | ImageNet2012 | ImageNet2012 |

4
model_zoo/official/cv/resnet_thor/README_CN.md
View File

@ -264,7 +264,7 @@ epoch： 36 step: 5004，loss is 1.645802
| 参数 | Ascend 910 | GPU |
| -------------------------- | -------------------------------------- | ---------------------------------- |
| 模型版本 | ResNet50-v1.5 | ResNet50-v1.5 |
| 资源 | Ascend 910-CPU 2.60GHz 192核-内存755G | GPU(Tesla V100 SXM2)-CPU 2.1GHz 24核-内存128G |
| 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|
| 数据集 | ImageNet2012 | ImageNet2012 |
@ -284,7 +284,7 @@ epoch： 36 step: 5004，loss is 1.645802
| 参数 | Ascend 910 | GPU |
| ------------------- | --------------------------- | --------------------------- |
| 模型版本 | ResNet50-v1.5 | ResNet50-v1.5 |
| 资源 | Ascend 910 | GPU |
| 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 |
| 数据集 | ImageNet2012 | ImageNet2012 |

4
model_zoo/official/cv/resnext50/README.md
View File

@ -222,7 +222,7 @@ python export.py --device_target [PLATFORM] --ckpt_file [CKPT_PATH] --file_forma
| Parameters | ResNeXt50 | |
| -------------------------- | ---------------------------------------------------------- | ------------------------- |
| Resource | Ascend 910, cpu:2.60GHz 192cores, memory:755G | NV SMX2 V100-32G |
| 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 |
| Dataset | ImageNet | ImageNet |
@ -238,7 +238,7 @@ python export.py --device_target [PLATFORM] --ckpt_file [CKPT_PATH] --file_forma
| Parameters | | | |
| -------------------------- | ----------------------------- | ------------------------- | -------------------- |
| Resource | Ascend 910 | NV SMX2 V100-32G | Ascend 310 |
| 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 |
| Dataset | ImageNet, 1.2W | ImageNet, 1.2W | ImageNet, 1.2W |

4
model_zoo/official/cv/resnext50/README_CN.md
View File

@ -226,7 +226,7 @@ python export.py --device_target [PLATFORM] --ckpt_file [CKPT_PATH] --file_forma
| 参数 | ResNeXt50 | |
| -------------------------- | ---------------------------------------------------------- | ------------------------- |
| 资源 | Ascend 910；CPU：2.60GHz，192核；内存：755GB | NV SMX2 V100-32G |
| 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 |
| 数据集 | ImageNet | ImageNet |
@ -242,7 +242,7 @@ python export.py --device_target [PLATFORM] --ckpt_file [CKPT_PATH] --file_forma
| 参数 | | | |
| -------------------------- | ----------------------------- | ------------------------- | -------------------- |
| 资源 | Ascend 910 | NV SMX2 V100-32G | Ascend 310 |
| 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 |
| 数据集 | ImageNet， 1.2万 | ImageNet， 1.2万 | ImageNet， 1.2万 |

4
model_zoo/official/cv/retinanet/README_CN.md
View File

@ -260,7 +260,7 @@ mAP: 0.34747137754625645
| 参数 | Ascend |
| -------------------------- | ------------------------------------- |
| 模型名称 | Retinanet |
| 运行环境 | Ascend 910; CPU 2.6GHz,192cores;Memory 755G |
| 运行环境 | Ascend 910；CPU 2.6GHz，192cores；Memory 755G；系统 Euler2.8 |
| 上传时间 | 10/01/2021 |
| MindSpore 版本 | 1.2.0 |
| 数据集 | 123287 张图片 |
@ -278,7 +278,7 @@ mAP: 0.34747137754625645
| 参数 | Ascend |
| ------------------- | --------------------------- |
| 模型名称 | Retinanet |
| 运行环境 | Ascend 910; CPU 2.6GHz,192cores;Memory 755G|
| 运行环境 | Ascend 910；CPU 2.6GHz，192cores；Memory 755G；系统 Euler2.8|
| 上传时间 | 10/01/2021 |
| MindSpore 版本 | 1.2.0 |
| 数据集 | 5k 张图片 |

2
model_zoo/official/cv/shufflenetv1/README_CN.md
View File

@ -155,7 +155,7 @@ result:{'Loss': 2.0479587888106323, 'Top_1_Acc': 0.7385817307692307, 'Top_5_Acc'
| 参数 | Ascend |
| -------------------------- | ------------------------------------- |
| 模型名称 | ShuffleNetV1 |
| 运行环境 | Ascend 910 |
| 运行环境 | Ascend 910；系统 Euler2.8 |
| 上传时间 | 2020-12-3 |
| MindSpore 版本 | 1.0.0 |
| 数据集 | imagenet |

2
model_zoo/official/cv/simple_pose/README.md
View File

@ -314,7 +314,7 @@ Total boxes: 104125
| Parameters | Standalone | Distributed |
| ------------------- | --------------------------- | --------------------------- |
| Model Version | SimplePoseNet | SimplePoseNet |
| Resource | Ascend 910 | 4 Ascend 910 cards |
| Resource | Ascend 910; OS Euler2.8 | 4 Ascend 910 cards; OS Euler2.8 |
| Uploaded Date | 12/18/2020 (month/day/year) | 12/18/2020 (month/day/year) |
| MindSpore Version | 1.1.0 | 1.1.0 |
| Dataset | COCO2017 | COCO2017 |

16
model_zoo/official/cv/squeezenet/README.md
View File

@ -341,7 +341,7 @@ result: {'top_1_accuracy': 0.6094950384122919, 'top_5_accuracy': 0.8263244238156
| Parameters | Ascend |
| -------------------------- | ----------------------------------------------------------- |
| Model Version | SqueezeNet |
| Resource | Ascend 910 ；CPU 2.60GHz，192cores；Memory，755G |
| Resource | Ascend 910; CPU 2.60GHz, 192cores; Memory 755G; OS Euler2.8 |
| uploaded Date | 11/06/2020 (month/day/year) |
| MindSpore Version | 1.0.0 |
| Dataset | CIFAR-10 |
@ -361,7 +361,7 @@ result: {'top_1_accuracy': 0.6094950384122919, 'top_5_accuracy': 0.8263244238156
| Parameters | Ascend |
| -------------------------- | ----------------------------------------------------------- |
| Model Version | SqueezeNet |
| Resource | Ascend 910 ；CPU 2.60GHz，192cores；Memory，755G |
| Resource | Ascend 910; CPU 2.60GHz, 192cores; Memory 755G; OS Euler2.8 |
| uploaded Date | 11/06/2020 (month/day/year) |
| MindSpore Version | 1.0.0 |
| Dataset | ImageNet |
@ -381,7 +381,7 @@ result: {'top_1_accuracy': 0.6094950384122919, 'top_5_accuracy': 0.8263244238156
| Parameters | Ascend |
| -------------------------- | ----------------------------------------------------------- |
| Model Version | SqueezeNet_Residual |
| Resource | Ascend 910 ；CPU 2.60GHz，192cores；Memory，755G |
| Resource | Ascend 910; CPU 2.60GHz, 192cores; Memory 755G; OS Euler2.8 |
| uploaded Date | 11/06/2020 (month/day/year) |
| MindSpore Version | 1.0.0 |
| Dataset | CIFAR-10 |
@ -401,7 +401,7 @@ result: {'top_1_accuracy': 0.6094950384122919, 'top_5_accuracy': 0.8263244238156
| Parameters | Ascend |
| -------------------------- | ----------------------------------------------------------- |
| Model Version | SqueezeNet_Residual |
| Resource | Ascend 910 ；CPU 2.60GHz，192cores；Memory，755G |
| Resource | Ascend 910; CPU 2.60GHz, 192cores; Memory 755G; OS Euler2.8 |
| uploaded Date | 11/06/2020 (month/day/year) |
| MindSpore Version | 1.0.0 |
| Dataset | ImageNet |
@ -423,7 +423,7 @@ result: {'top_1_accuracy': 0.6094950384122919, 'top_5_accuracy': 0.8263244238156
| Parameters | Ascend |
| ------------------- | --------------------------- |
| Model Version | SqueezeNet |
| Resource | Ascend 910 |
| Resource | Ascend 910; OS Euler2.8 |
| Uploaded Date | 11/06/2020 (month/day/year) |
| MindSpore Version | 1.0.0 |
| Dataset | CIFAR-10 |
@ -436,7 +436,7 @@ result: {'top_1_accuracy': 0.6094950384122919, 'top_5_accuracy': 0.8263244238156
| Parameters | Ascend |
| ------------------- | --------------------------- |
| Model Version | SqueezeNet |
| Resource | Ascend 910 |
| Resource | Ascend 910; OS Euler2.8 |
| Uploaded Date | 11/06/2020 (month/day/year) |
| MindSpore Version | 1.0.0 |
| Dataset | ImageNet |
@ -449,7 +449,7 @@ result: {'top_1_accuracy': 0.6094950384122919, 'top_5_accuracy': 0.8263244238156
| Parameters | Ascend |
| ------------------- | --------------------------- |
| Model Version | SqueezeNet_Residual |
| Resource | Ascend 910 |
| Resource | Ascend 910; OS Euler2.8 |
| Uploaded Date | 11/06/2020 (month/day/year) |
| MindSpore Version | 1.0.0 |
| Dataset | CIFAR-10 |
@ -462,7 +462,7 @@ result: {'top_1_accuracy': 0.6094950384122919, 'top_5_accuracy': 0.8263244238156
| Parameters | Ascend |
| ------------------- | --------------------------- |
| Model Version | SqueezeNet_Residual |
| Resource | Ascend 910 |
| Resource | Ascend 910; OS Euler2.8 |
| Uploaded Date | 11/06/2020 (month/day/year) |
| MindSpore Version | 1.0.0 |
| Dataset | ImageNet |

4
model_zoo/official/cv/ssd/README.md
View File

@ -454,7 +454,7 @@ mAP: 0.33880018942412393
| Parameters | Ascend | GPU | Ascend |
| ------------------- | ----------------------------------------------------------------------------- | ----------------------------------------------------------------------------- | ----------------------------------------------------------------------------- |
| Model Version | SSD V1 | SSD V1 | SSD-Mobilenet-V1-Fpn |
| Resource | Ascend 910 ；CPU 2.60GHz，192cores；Memory，755G | NV SMX2 V100-16G | Ascend 910 ；CPU 2.60GHz，192cores；Memory，755G |
| 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 |
| Dataset | COCO2017 | COCO2017 | COCO2017 |
@ -471,7 +471,7 @@ mAP: 0.33880018942412393
| Parameters | Ascend | GPU | Ascend |
| ------------------- | --------------------------- | --------------------------- | --------------------------- |
| Model Version | SSD V1 | SSD V1 | SSD-Mobilenet-V1-Fpn |
| Resource | Ascend 910 | GPU | Ascend 910 |
| 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 |
| Dataset | COCO2017 | COCO2017 | COCO2017 |

4
model_zoo/official/cv/ssd/README_CN.md
View File

@ -368,7 +368,7 @@ mAP: 0.33880018942412393
| 参数 | Ascend | GPU |
| -------------------------- | -------------------------------------------------------------| -------------------------------------------------------------|
| 模型版本 | SSD V1 | SSD V1 |
| 资源 | Ascend 910；CPU： 2.60GHz，192核；内存：755 GB | NV SMX2 V100-16G |
| 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 |
| 数据集 | COCO2017 | COCO2017 |
@ -385,7 +385,7 @@ mAP: 0.33880018942412393
| 参数 | Ascend | GPU |
| ------------------- | ----------------------------| ----------------------------|
| 模型版本 | SSD V1 | SSD V1 |
| 资源 | Ascend 910 | GPU |
| 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 |
| 数据集 | COCO2017 | COCO2017 |

4
model_zoo/official/cv/tinydarknet/README.md
View File

@ -244,7 +244,7 @@ For more configuration details, please refer the script config.py.
| Parameters | Ascend |
| -------------------------- | ----------------------------------------------------------- |
| Model Version | V1 |
| Resource | Ascend 910, CPU 2.60GHz, 56cores, Memory 314G |
| Resource | Ascend 910; CPU 2.60GHz, 56cores; Memory 314G; OS Euler2.8 |
| Uploaded Date | 2020/12/22 |
| MindSpore Version | 1.1.0 |
| Dataset | 1200k images |
@ -261,7 +261,7 @@ For more configuration details, please refer the script config.py.
| Parameters | Ascend |
| ------------------- | --------------------------- |
| Model Version | V1 |
| Resource | Ascend 910 |
| Resource | Ascend 910; OS Euler2.8 |
| Uploaded Date | 2020/12/22 |
| MindSpore Version | 1.1.0 |
| Dataset | 200k images |

4
model_zoo/official/cv/tinydarknet/README_CN.md
View File

@ -252,7 +252,7 @@ Tiny-DarkNet是Joseph Chet Redmon等人提出的一个16层的针对于经典的
| 参数 | Ascend |
| -------------------------- | ----------------------------------------------------------- |
| 模型版本 | V1 |
| 资源 | Ascend 910, CPU 2.60GHz, 56cores, Memory 314G |
| 资源 | Ascend 910；CPU 2.60GHz，56cores；内存 314G；系统 Euler2.8 |
| 上传日期 | 2020/12/22 |
| MindSpore版本 | 1.1.0 |
| 数据集 | 1200k张图片 |
@ -269,7 +269,7 @@ Tiny-DarkNet是Joseph Chet Redmon等人提出的一个16层的针对于经典的
| 参数 | Ascend |
| ------------------- | --------------------------- |
| 模型版本 | V1 |
| 资源 | Ascend 910 |
| 资源 | Ascend 910；系统 Euler2.8 |
| 上传日期 | 2020/12/22 |
| MindSpore版本 | 1.1.0 |
| 数据集 | 200k张图片 |

2
model_zoo/official/cv/unet/README.md
View File

@ -290,7 +290,7 @@ The above python command will run in the background. You can view the results th
| Parameters | Ascend |
| -------------------------- | ------------------------------------------------------------ |
| Model Version | Unet |
| Resource | Ascend 910 ;CPU 2.60GHz,192cores; Memory,755G |
| 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 |
| Dataset | ISBI |

2
model_zoo/official/cv/unet/README_CN.md
View File

@ -283,7 +283,7 @@ step: 300, loss is 0.18949677, fps is 57.63118508760329
| 参数 | Ascend |
| -------------------------- | ------------------------------------------------------------ |
| 模型版本 | U-Net |
| 资源 | Ascend 910；CPU：2.60GHz，192核；内存：755 GB |
| 资源 | Ascend 910；CPU 2.60GHz，192核；内存 755GB；系统 Euler2.8 |
| 上传日期 | 2020-9-15 |
| MindSpore版本 | 1.0.0 |
| 数据集 | ISBI |

4
model_zoo/official/cv/unet3d/README.md
View File

@ -228,7 +228,7 @@ eval average dice is 0.9502010010453671
| Parameters | Ascend |
| ------------------- | --------------------------------------------------------- |
| Model Version | Unet3D |
| Resource | Ascend 910; CPU 2.60GHz，192cores；Memory，755G |
| Resource | Ascend 910; CPU 2.60GHz, 192cores; Memory 755G; OS Euler2.8 |
| uploaded Date | 03/18/2021 (month/day/year) |
| MindSpore Version | 1.2.0 |
| Dataset | LUNA16 |
@ -245,7 +245,7 @@ eval average dice is 0.9502010010453671
| Parameters | Ascend |
| ------------------- | --------------------------- |
| Model Version | Unet3D |
| Resource | Ascend 910 |
| Resource | Ascend 910; OS Euler2.8 |
| Uploaded Date | 03/18/2021 (month/day/year) |
| MindSpore Version | 1.2.0 |
| Dataset | LUNA16 |

4
model_zoo/official/cv/vgg16/README.md
View File

@ -353,7 +353,7 @@ after allreduce eval: top5_correct=45582, tot=50000, acc=91.16%
| Parameters | VGG16(Ascend) | VGG16(GPU) |
| -------------------------- | ---------------------------------------------- |------------------------------------|
| Model Version | VGG16 | VGG16 |
| Resource | Ascend 910 ；CPU 2.60GHz，192cores；Memory，755G |NV SMX2 V100-32G |
| 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 |
| Dataset | CIFAR-10 |ImageNet2012 |
@ -372,7 +372,7 @@ after allreduce eval: top5_correct=45582, tot=50000, acc=91.16%
| Parameters | VGG16(Ascend) | VGG16(GPU)
| ------------------- | --------------------------- |---------------------
| Model Version | VGG16 | VGG16 |
| Resource | Ascend 910 | GPU |
| Resource | Ascend 910; OS Euler2.8 | GPU |
| Uploaded Date | 10/28/2020 | 10/28/2020 |
| MindSpore Version | 1.0.0 | 1.0.0 |
| Dataset | CIFAR-10, 10,000 images |ImageNet2012, 5000 images |

4
model_zoo/official/cv/vgg16/README_CN.md
View File

@ -361,7 +361,7 @@ after allreduce eval: top5_correct=45582, tot=50000, acc=91.16%
| 参数 | VGG16(Ascend) | VGG16(GPU) |
| -------------------------- | ---------------------------------------------- |------------------------------------|
| 模型版本 | VGG16 | VGG16 |
| 资源 | Ascend 910；CPU：2.60GHz，192核；内存：755 GB |NV SMX2 V100-32G |
| 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 |
| 数据集 | CIFAR-10 |ImageNet2012 |
@ -380,7 +380,7 @@ after allreduce eval: top5_correct=45582, tot=50000, acc=91.16%
| 参数 | VGG16(Ascend) | VGG16(GPU)
| ------------------- | --------------------------- |---------------------
| 模型版本 | VGG16 | VGG16 |
| 资源 | Ascend 910 | GPU |
| 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 |
| 数据集 | CIFAR-10，10000张图像 | ImageNet2012，5000张图像 |

4
model_zoo/official/cv/warpctc/README.md
View File

@ -209,7 +209,7 @@ bash run_eval.sh [DATASET_PATH] [CHECKPOINT_PATH] [PLATFORM]
| Parameters | Ascend 910 | GPU |
| -------------------------- | --------------------------------------------- |---------------------------------- |
| Model Version | v1.0 | v1.0 |
| Resource | Ascend 910，CPU 2.60GHz 192cores，Memory 755G | GPU(Tesla V100 SXM2)，CPU 2.1GHz 24cores，Memory 128G /
| 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 |
| Dataset | Captcha | Captcha |
@ -229,7 +229,7 @@ bash run_eval.sh [DATASET_PATH] [CHECKPOINT_PATH] [PLATFORM]
| Parameters | WarpCTC |
| ------------------- | --------------------------- |
| Model Version | V1.0 |
| Resource | Ascend 910 |
| Resource | Ascend 910; OS Euler2.8 |
| Uploaded Date | 08/01/2020 (month/day/year) |
| MindSpore Version | 0.6.0-alpha |
| Dataset | Captcha |

4
model_zoo/official/cv/warpctc/README_CN.md
View File

@ -213,7 +213,7 @@ bash run_eval.sh [DATASET_PATH] [CHECKPOINT_PATH] [PLATFORM]
| 参数 | Ascend 910 | GPU |
| -------------------------- | --------------------------------------------- |---------------------------------- |
| 模型版本 | v1.0 | v1.0 |
| 资源 | Ascend 910，CPU 2.60GHz 192核，内存：755G | GPU(Tesla V100 SXM2)，CPU 2.1GHz 24核，内存： 128G
| 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 |
| 数据集 | Captcha | Captcha |
@ -233,7 +233,7 @@ bash run_eval.sh [DATASET_PATH] [CHECKPOINT_PATH] [PLATFORM]
| 参数 | WarpCTC |
| ------------------- | --------------------------- |
| 模型版本 | V1.0 |
| 资源 | Ascend 910 |
| 资源 |Ascend 910；系统 Euler2.8 |
| 上传日期 | 2020-08-01 |
| MindSpore版本 | 0.6.0-alpha |
| 数据集 | Captcha |

4
model_zoo/official/cv/yolov3_darknet53/README.md
View File

@ -340,7 +340,7 @@ This the standard format from `pycocotools`, you can refer to [cocodataset](http
| Parameters | YOLO |YOLO |
| -------------------------- | ----------------------------------------------------------- |------------------------------------------------------------ |
| Model Version | YOLOv3 |YOLOv3 |
| Resource | Ascend 910; CPU 2.60GHz, 192cores; Memory, 755G | NV SMX2 V100-16G; CPU 2.10GHz, 96cores; Memory, 251G |
| Resource | Ascend 910; CPU 2.60GHz, 192cores; Memory 755G; OS Euler2.8 | NV SMX2 V100-16G; CPU 2.10GHz, 96cores; Memory, 251G |
| uploaded Date | 09/15/2020 (month/day/year) | 09/02/2020 (month/day/year) |
| MindSpore Version | 1.1.1 | 1.1.1 |
| Dataset | COCO2014 | COCO2014 |
@ -360,7 +360,7 @@ This the standard format from `pycocotools`, you can refer to [cocodataset](http
| Parameters | YOLO |YOLO |
| ------------------- | --------------------------- |------------------------------|
| Model Version | YOLOv3 | YOLOv3 |
| Resource | Ascend 910 | NV SMX2 V100-16G |
| Resource | Ascend 910; OS Euler2.8 | NV SMX2 V100-16G |
| Uploaded Date | 09/15/2020 (month/day/year) | 08/20/2020 (month/day/year) |
| MindSpore Version | 1.1.1 | 1.1.1 |
| Dataset | COCO2014, 40,504 images | COCO2014, 40,504 images |

4
model_zoo/official/cv/yolov3_darknet53/README_CN.md
View File

@ -343,7 +343,7 @@ sh run_eval.sh dataset/coco2014/ checkpoint/0-319_102400.ckpt
| 参数 | YOLO |YOLO |
| -------------------------- | ----------------------------------------------------------- |------------------------------------------------------------ |
| 模型版本 | YOLOv3 |YOLOv3 |
| 资源 | Ascend 910；CPU 2.60GHz，192核；内存：755G | NV SMX2 V100-16G；CPU 2.10GHz，96核；内存：251G |
| 资源 | Ascend 910；CPU 2.60GHz，192核；内存 755G；系统 Euler2.8 | NV SMX2 V100-16G；CPU 2.10GHz，96核；内存：251G |
| 上传日期 | 2020-06-31 | 2020-09-02 |
| MindSpore版本 | 1.1.1 | 1.1.1 |
| 数据集 | COCO2014 | COCO2014 |
@ -363,7 +363,7 @@ sh run_eval.sh dataset/coco2014/ checkpoint/0-319_102400.ckpt
| 参数 | YOLO |YOLO |
| ------------------- | --------------------------- |------------------------------|
| 模型版本 | YOLOv3 | YOLOv3 |
| 资源 | Ascend 910 | NV SMX2 V100-16G |
| 资源 | Ascend 910；系统 Euler2.8 | NV SMX2 V100-16G |
| 上传日期 | 2020-06-31 | 2020-08-20 |
| MindSpore版本 | 1.1.1 | 1.1.1 |
| 数据集 | COCO2014，40504张图像 | COCO2014，40504张图像 |

4
model_zoo/official/cv/yolov3_darknet53_quant/README.md
View File

@ -266,7 +266,7 @@ Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.558
| Parameters | Ascend |
| -------------------------- | ---------------------------------------------------------------------------------------------- |
| Model Version | YOLOv3_Darknet53_Quant V1 |
| Resource | Ascend 910; CPU 2.60GHz, 192cores; Memory, 755G |
| 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 |
| Dataset | COCO2014 |
@ -286,7 +286,7 @@ Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.558
| Parameters | Ascend |
| ------------------- | --------------------------- |
| Model Version | YOLOv3_Darknet53_Quant V1 |
| Resource | Ascend 910 |
| Resource | Ascend 910; OS Euler2.8 |
| Uploaded Date | 09/15/2020 (month/day/year) |
| MindSpore Version | 1.0.0 |
| Dataset | COCO2014, 40,504 images |

4
model_zoo/official/cv/yolov3_darknet53_quant/README_CN.md
View File

@ -275,7 +275,7 @@ Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.558
| 参数 | Ascend |
| -------------------------- | ---------------------------------------------------------------------------------------------- |
| 模型版本 | YOLOv3_Darknet53_Quant V1 |
| 资源 | Ascend 910; CPU 2.60GHz，192核; 内存：755G |
| 资源 | Ascend 910；CPU 2.60GHz，192核；内存 755G；系统 Euler2.8 |
| 上传日期 | 2020-06-31 |
| MindSpore版本 | 0.6.0-alpha |
| 数据集 | COCO2014 |
@ -295,7 +295,7 @@ Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.558
| 参数 | Ascend |
| ------------------- | --------------------------- |
| 模型版本 | YOLOv3_Darknet53_Quant V1 |
| 资源 | Ascend 910 |
| 资源 |Ascend 910；系统 Euler2.8 |
| 上传日期 | 2020-06-31 |
| MindSpore版本 | 0.6.0-alpha |
| 数据集 | COCO2014，40,504张图片 |

4
model_zoo/official/cv/yolov3_resnet18/README.md
View File

@ -202,7 +202,7 @@ Note the precision and recall values are results of two-classification(person an
| Parameters | Ascend |
| -------------------------- | ----------------------------------------------------------- |
| Model Version | YOLOv3_Resnet18 V1 |
| Resource | Ascend 910 ；CPU 2.60GHz，192cores；Memory，755G |
| 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 |
| Dataset | COCO2017 |
@ -220,7 +220,7 @@ Note the precision and recall values are results of two-classification(person an
| Parameters | Ascend |
| ------------------- | ----------------------------------------------- |
| Model Version | YOLOv3_Resnet18 V1 |
| Resource | Ascend 910 |
| Resource | Ascend 910; OS Euler2.8 |
| Uploaded Date | 09/15/2020 (month/day/year) |
| MindSpore Version | 1.0.0 |
| Dataset | COCO2017 |

4
model_zoo/official/cv/yolov3_resnet18/README_CN.md
View File

@ -203,7 +203,7 @@ YOLOv3整体网络架构如下：
| 参数 | Ascend |
| -------------------------- | ----------------------------------------------------------- |
| 模型版本 | YOLOv3_Resnet18 V1 |
| 资源 | Ascend 910 ；CPU 2.60GHz，192核；内存：755G |
| 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 |
| 数据集 | COCO2017 |
@ -221,7 +221,7 @@ YOLOv3整体网络架构如下：
| 参数 | Ascend |
| ------------------- | ----------------------------------------------- |
| 模型版本 | YOLOv3_Resnet18 V1 |
| 资源 | Ascend 910 |
| 资源 | Ascend 910；系统 Euler2.8 |
| 上传日期 | 2020-06-01 |
| MindSpore版本 | 0.2.0-alpha |
| 数据集 | COCO2017 |

4
model_zoo/official/cv/yolov4/README.md
View File

@ -448,7 +448,7 @@ YOLOv4 on 118K images(The annotation and data format must be the same as coco201
| Parameters | YOLOv4 |
| -------------------------- | ----------------------------------------------------------- |
| Resource | Ascend 910; CPU 2.60GHz, 192cores; Memory, 755G; System, Euleros 2.8;|
| Resource | Ascend 910; CPU 2.60GHz, 192cores; Memory 755G; OS Euler2.8; System, Euleros 2.8;|
| uploaded Date | 10/16/2020 (month/day/year) |
| MindSpore Version | 1.0.0-alpha |
| Dataset | 118K images |
@ -468,7 +468,7 @@ YOLOv4 on 20K images(The annotation and data format must be the same as coco tes
| Parameters | YOLOv4 |
| -------------------------- | ----------------------------------------------------------- |
| Resource | Ascend 910; CPU 2.60GHz, 192cores; Memory, 755G |
| Resource | Ascend 910; CPU 2.60GHz, 192cores; Memory 755G; OS Euler2.8 |
| uploaded Date | 10/16/2020 (month/day/year) |
| MindSpore Version | 1.0.0-alpha |
| Dataset | 20K images |

4
model_zoo/official/gnn/bgcf/README.md
View File

@ -253,7 +253,7 @@ Parameters for both training and evaluation can be set in config.py.
| Parameter | BGCF Ascend | BGCF GPU |
| ------------------------------ | ------------------------------------------ | ------------------------------------------ |
| Model Version | Inception V1 | Inception V1 |
| Resource | Ascend 910 | Tesla V100-PCIE |
| Resource | Ascend 910; OS Euler2.8 | Tesla V100-PCIE |
| uploaded Date | 09/23/2020(month/day/year) | 01/27/2021(month/day/year) |
| MindSpore Version | 1.0.0 | 1.1.0 |
| Dataset | Amazon-Beauty | Amazon-Beauty |
@ -268,7 +268,7 @@ Parameters for both training and evaluation can be set in config.py.
| Parameter | BGCF Ascend | BGCF GPU |
| ------------------------------ | ---------------------------- | ---------------------------- |
| Model Version | Inception V1 | Inception V1 |
| Resource | Ascend 910 | Tesla V100-PCIE |
| Resource | Ascend 910; OS Euler2.8 | Tesla V100-PCIE |
| uploaded Date | 09/23/2020(month/day/year) | 01/28/2021(month/day/year) |
| MindSpore Version | 1.0.0 | Master(4b3e53b4) |
| Dataset | Amazon-Beauty | Amazon-Beauty |

18
model_zoo/official/gnn/bgcf/README_CN.md
View File

@ -273,11 +273,11 @@ BGCF包含两个主要模块。首先是抽样，它生成基于节点复制的
## 模型描述
### 性能
### 训练性能
| 参数 | BGCF Ascend | BGCF GPU |
| -------------------------- | ------------------------------------------ | ------------------------------------------ |
| 资源 | Ascend 910 | Tesla V100-PCIE |
| 资源 | Ascend 910；系统 Euler2.8 | Tesla V100-PCIE |
| 上传日期 | 09/23/2020(月/日/年) | 01/28/2021(月/日/年) |
| MindSpore版本 | 1.0.0 | Master(4b3e53b4) |
| 数据集 | Amazon-Beauty | Amazon-Beauty |
@ -289,6 +289,20 @@ BGCF包含两个主要模块。首先是抽样，它生成基于节点复制的
| 训练成本 | 25min | 60min |
| 脚本 | [bgcf脚本](https://gitee.com/mindspore/mindspore/tree/master/model_zoo/official/gnn/bgcf) | [bgcf脚本](https://gitee.com/mindspore/mindspore/tree/master/model_zoo/official/gnn/bgcf) |
### 推理性能
| Parameter | BGCF Ascend | BGCF GPU |
| ------------------------------ | ---------------------------- | ---------------------------- |
| 模型版本 | Inception V1 | Inception V1 |
| 资源 | Ascend 910；系统 Euler2.8 | Tesla V100-PCIE |
| 上传日期 | 09/23/2020(月/日/年) | 01/28/2021(月/日/年) |
| MindSpore版本 | 1.0.0 | Master(4b3e53b4) |
| 数据集 | Amazon-Beauty | Amazon-Beauty |
| Batch_size | 5000 | 5000 |
| 输出 | 概率 | 概率 |
| Recall@20 | 0.1534 | 0.15524 |
| NDCG@20 | 0.0912 | 0.09249 |
## 随机情况说明
BGCF模型中有很多的dropout操作，如果想关闭dropout，可以在src/config.py中将neighbor_dropout设置为[0.0, 0.0, 0.0] 。

2
model_zoo/official/gnn/gat/README.md
View File

@ -183,7 +183,7 @@ Parameters for both training and evaluation can be set in config.py.
| Parameter | GAT |
| ------------------------------------ | ----------------------------------------- |
| Resource | Ascend 910 |
| Resource | Ascend 910; OS Euler2.8 |
| uploaded Date | 06/16/2020(month/day/year) |
| MindSpore Version | 1.0.0 |
| Dataset | Cora/Citeseer |

2
model_zoo/official/gnn/gat/README_CN.md
View File

@ -181,7 +181,7 @@
| 参数 | GAT |
| ------------------------------------ | ----------------------------------------- |
| 资源 | Ascend 910 |
| 资源 | Ascend 910；系统 Euler2.8 |
| 上传日期 | 2020-06-16 |
| MindSpore版本 | 0.5.0-beta |
| 数据集 | Cora/Citeseer |

2
model_zoo/official/gnn/gcn/README.md
View File

@ -159,7 +159,7 @@ Test set results: cost= 1.00983 accuracy= 0.81300 time= 0.39083
| Parameters | GCN |
| -------------------------- | -------------------------------------------------------------- |
| Resource | Ascend 910 |
| Resource | Ascend 910; OS Euler2.8 |
| uploaded Date | 06/09/2020 (month/day/year) |
| MindSpore Version | 1.0.0 |
| Dataset | Cora/Citeseer |

2
model_zoo/official/gnn/gcn/README_CN.md
View File

@ -167,7 +167,7 @@ Test set results: cost= 1.00983 accuracy= 0.81300 time= 0.39083
| 参数 | GCN |
| -------------------------- | -------------------------------------------------------------- |
| 资源 | Ascend 910 |
| 资源 | Ascend 910；系统 Euler2.8 |
| 上传日期 | 2020-06-09 |
| MindSpore版本 | 0.5.0-beta |
| 数据集 | Cora/Citeseer |

6
model_zoo/official/nlp/bert/README.md
View File

@ -596,7 +596,7 @@ The result will be as follows:
| Parameters | Ascend | GPU |
| -------------------------- | ---------------------------------------------------------- | ------------------------- |
| Model Version | BERT_base | BERT_base |
| Resource | Ascend 910, cpu:2.60GHz 192cores, memory:755G | NV SMX2 V100-16G, cpu: Intel(R) Xeon(R) Platinum 8160 CPU @2.10GHz, memory: 256G |
| 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 |
| Dataset | cn-wiki-128(4000w) | cn-wiki-128(4000w) |
@ -616,7 +616,7 @@ The result will be as follows:
| Parameters | Ascend |
| -------------------------- | ---------------------------------------------------------- |
| Model Version | BERT_NEZHA |
| Resource | Ascend 910, cpu:2.60GHz 192cores, memory:755G |
| Resource | Ascend 910; cpu 2.60GHz, 192cores; memory 755G; OS Euler2.8 |
| uploaded Date | 08/20/2020 |
| MindSpore Version | 1.0.0 |
| Dataset | cn-wiki-128(4000w) |
@ -638,7 +638,7 @@ The result will be as follows:
| Parameters | Ascend |
| -------------------------- | ----------------------------- |
| Model Version | |
| Resource | Ascend 910 |
| Resource | Ascend 910; OS Euler2.8 |
| uploaded Date | 08/22/2020 |
| MindSpore Version | 1.0.0 |
| Dataset | cola, 1.2W |

6
model_zoo/official/nlp/bert/README_CN.md
View File

@ -559,7 +559,7 @@ bash scripts/squad.sh
| 参数 | Ascend | GPU |
| -------------------------- | ---------------------------------------------------------- | ------------------------- |
| 模型版本 | BERT_base | BERT_base |
| 资源 | Ascend 910；CPU：2.60GHz，192核；内存：755GB || NV SMX2 V100-32G |
| 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 |
@ -578,7 +578,7 @@ bash scripts/squad.sh
| 参数 | Ascend | GPU |
| -------------------------- | ---------------------------------------------------------- | ------------------------- |
| 模型版本 | BERT_NEZHA | BERT_NEZHA |
| 资源 | Ascend 910；CPU：2.60GHz，192核；内存：755GB || NV SMX2 V100-32G |
| 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 |
@ -599,7 +599,7 @@ bash scripts/squad.sh
| 参数 | Ascend | GPU |
| -------------------------- | ----------------------------- | ------------------------- |
| 模型版本 | | |
| 资源 | Ascend 910 | NV SMX2 V100-32G |
| 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 |

2
model_zoo/official/nlp/bert_thor/README.md
View File

@ -204,7 +204,7 @@ step: 3000 Accuracy: [0.71377236]
| Parameters | Ascend 910 |
| -------------------------- | -------------------------------------- |
| Model Version | BERT-LARGE |
| Resource | Ascend 910，CPU 2.60GHz 192cores，Memory 755G |
| 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 |
| Dataset | MLPerf v0.7 dataset |

2
model_zoo/official/nlp/bert_thor/README_CN.md
View File

@ -211,7 +211,7 @@ step: 3000 Accuracy: [0.71377236]
| 参数 | Ascend 910 |
| -------------------------- | -------------------------------------- |
| 模型版本 | BERT-LARGE |
| 资源 | Ascend 910 ;CPU 2.60GHz,192cores；内存，755G |
| 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 |
| 数据集 | MLPerf v0.7 |

12
model_zoo/official/nlp/fasttext/README.md
View File

@ -164,7 +164,7 @@ Parameters for both training and evaluation can be set in config.py. All the dat
| Parameters | Ascend |
| -------------------------- | -------------------------------------------------------------- |
| Resource | Ascend 910 |
| Resource | Ascend 910; OS Euler2.8 |
| uploaded Date | 12/21/2020 (month/day/year) |
| MindSpore Version | 1.1.0 |
| Dataset | AG's News Topic Classification Dataset |
@ -181,7 +181,7 @@ Parameters for both training and evaluation can be set in config.py. All the dat
| Parameters | Ascend |
| -------------------------- | -------------------------------------------------------------- |
| Resource | Ascend 910 |
| Resource |Ascend 910; OS Euler2.8 |
| uploaded Date | 11/21/2020 (month/day/year) |
| MindSpore Version | 1.1.0 |
| Dataset | DBPedia Ontology Classification Dataset |
@ -198,7 +198,7 @@ Parameters for both training and evaluation can be set in config.py. All the dat
| Parameters | Ascend |
| -------------------------- | -------------------------------------------------------------- |
| Resource | Ascend 910 |
| Resource | Ascend 910; OS Euler2.8 |
| uploaded Date | 11/21/2020 (month/day/year) |
| MindSpore Version | 1.1.0 |
| Dataset | Yelp Review Polarity Dataset |
@ -217,7 +217,7 @@ Parameters for both training and evaluation can be set in config.py. All the dat
| Parameters | Ascend |
| ------------------- | --------------------------- |
| Resource | Ascend 910 |
| Resource | Ascend 910; OS Euler2.8 |
| Uploaded Date | 12/21/2020 (month/day/year) |
| MindSpore Version | 1.1.0 |
| Dataset | AG's News Topic Classification Dataset |
@ -229,7 +229,7 @@ Parameters for both training and evaluation can be set in config.py. All the dat
| Parameters | Ascend |
| ------------------- | --------------------------- |
| Resource | Ascend 910 |
| Resource | Ascend 910; OS Euler2.8 |
| Uploaded Date | 12/21/2020 (month/day/year) |
| MindSpore Version | 1.1.0 |
| Dataset | DBPedia Ontology Classification Dataset |
@ -241,7 +241,7 @@ Parameters for both training and evaluation can be set in config.py. All the dat
| Parameters | Ascend |
| ------------------- | --------------------------- |
| Resource | Ascend 910 |
| Resource |Ascend 910; OS Euler2.8 |
| Uploaded Date | 12/21/2020 (month/day/year) |
| MindSpore Version | 1.1.0 |
| Dataset | Yelp Review Polarity Dataset |

4
model_zoo/official/nlp/gnmt_v2/README.md
View File

@ -241,7 +241,7 @@ The `VOCAB_ADDR` is the vocabulary address, `BPE_CODE_ADDR` is the bpe code addr
| Parameters | Ascend |
| -------------------------- | -------------------------------------------------------------- |
| Resource | Ascend 910 |
| Resource | Ascend 910; OS Euler2.8 |
| uploaded Date | 11/06/2020 (month/day/year) |
| MindSpore Version | 1.0.0 |
| Dataset | WMT English-German for training |
@ -260,7 +260,7 @@ The `VOCAB_ADDR` is the vocabulary address, `BPE_CODE_ADDR` is the bpe code addr
| Parameters | Ascend |
| ------------------- | --------------------------- |
| Resource | Ascend 910 |
| Resource | Ascend 910; OS Euler2.8 |
| Uploaded Date | 11/06/2020 (month/day/year) |
| MindSpore Version | 1.0.0 |
| Dataset | WMT newstest2014 |

4
model_zoo/official/nlp/gru/README.md
View File

@ -227,7 +227,7 @@ Note: The `DATASET_PATH` is path to mindrecord. eg. train: /dataset_path/multi30
| Parameters | Ascend |
| -------------------------- | -------------------------------------------------------------- |
| Resource | Ascend 910 |
| Resource | Ascend 910; OS Euler2.8 |
| uploaded Date | 01/18/2021 (month/day/year) |
| MindSpore Version | 1.1.0 |
| Dataset | Multi30k Dataset |
@ -246,7 +246,7 @@ Note: The `DATASET_PATH` is path to mindrecord. eg. train: /dataset_path/multi30
| Parameters | Ascend |
| ------------------- | --------------------------- |
| Resource | Ascend 910 |
| Resource | Ascend 910; OS Euler2.8 |
| Uploaded Date | 01/18/2020 (month/day/year) |
| MindSpore Version | 1.1.0 |
| Dataset | Multi30K |

4
model_zoo/official/nlp/lstm/README.md
View File

@ -285,7 +285,7 @@ Ascend:
| Parameters | LSTM (Ascend) | LSTM (GPU) | LSTM (CPU) |
| -------------------------- | -------------------------- | -------------------------------------------------------------- | -------------------------- |
| Resource | Ascend 910 | Tesla V100-SMX2-16GB | Ubuntu X86-i7-8565U-16GB |
| 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 |
| Dataset | aclimdb_v1 | aclimdb_v1 | aclimdb_v1 |
@ -302,7 +302,7 @@ Ascend:
| Parameters | LSTM (Ascend) | LSTM (GPU) | LSTM (CPU) |
| ------------------- | ---------------------------- | --------------------------- | ---------------------------- |
| Resource | Ascend 910 | Tesla V100-SMX2-16GB | Ubuntu X86-i7-8565U-16GB |
| 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 |
| Dataset | aclimdb_v1 | aclimdb_v1 | aclimdb_v1 |

2
model_zoo/official/nlp/lstm/README_CN.md
View File

@ -307,7 +307,7 @@ Ascend:
| 参数 | LSTM (Ascend) | LSTM (GPU) | LSTM (CPU) |
| ------------------- | ---------------------------- | --------------------------- | ---------------------------- |
| 资源 | Ascend 910 | Tesla V100-SMX2-16GB | Ubuntu X86-i7-8565U-16GB |
| 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 |
| 数据集 | aclimdb_v1 | aclimdb_v1 | aclimdb_v1 |

4
model_zoo/official/nlp/mass/README.md
View File

@ -613,7 +613,7 @@ The comparisons between MASS and other baseline methods in terms of PPL on Corne
| Parameters | Masked Sequence to Sequence Pre-training for Language Generation |
|:---------------------------|:--------------------------------------------------------------------------|
| Model Version | v1 |
| Resource | Ascend 910, cpu 2.60GHz, 192cores；memory, 755G |
| Resource | Ascend 910; cpu 2.60GHz, 192cores; memory 755G; OS Euler2.8 |
| uploaded Date | 05/24/2020 |
| MindSpore Version | 1.0.0 |
| Dataset | News Crawl 2007-2017 English monolingual corpus, Gigaword corpus, Cornell Movie Dialog corpus |
@ -632,7 +632,7 @@ The comparisons between MASS and other baseline methods in terms of PPL on Corne
| Parameters | Masked Sequence to Sequence Pre-training for Language Generation |
|:---------------------------|:-----------------------------------------------------------|
| Model Version | V1 |
| Resource | Huawei 910 |
| Resource | Ascend 910; OS Euler2.8 |
| uploaded Date | 05/24/2020 |
| MindSpore Version | 1.0.0 |
| Dataset | Gigaword corpus, Cornell Movie Dialog corpus |

4
model_zoo/official/nlp/mass/README_CN.md
View File

@ -612,7 +612,7 @@ sh run_gpu.sh -t i -n 1 -i 1 -c config/config.json -o {outputfile}
| 参数 | 掩式序列到序列预训练语言生成 |
|:---------------------------|:--------------------------------------------------------------------------|
| 模型版本 | v1 |
| 资源 | Ascend 910；CPU：2.60GHz，192核；内存：755GB |
| 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 |
| 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 |
@ -631,7 +631,7 @@ sh run_gpu.sh -t i -n 1 -i 1 -c config/config.json -o {outputfile}
| 参数 | 掩式序列到序列预训练语言生成 |
|:---------------------------|:-----------------------------------------------------------|
|模型版本| V1 |
| 资源 | Ascend 910 |
| 资源 | Ascend 910；系统 Euler2.8 |
| 上传日期 | 2020-05-24 |
| MindSpore版本 | 0.2.0 |
| 数据集 | Gigaword语料库、Cornell电影对白语料库 |

2
model_zoo/official/nlp/prophetnet/README.md
View File

@ -508,7 +508,7 @@ The comparisons between MASS and other baseline methods in terms of PPL on Corne
| Parameters | Masked Sequence to Sequence Pre-training for Language Generation |
|:---------------------------|:--------------------------------------------------------------------------|
| Model Version | v1 |
| Resource | Ascend 910, cpu 2.60GHz, 56cores；memory, 314G |
| Resource | Ascend 910; cpu 2.60GHz, 56cores; memory 314G; OS Euler2.8 |
| uploaded Date | 05/24/2020 |
| MindSpore Version | 0.2.0 |
| Dataset | News Crawl 2007-2017 English monolingual corpus, Gigaword corpus, Cornell Movie Dialog corpus |

2
model_zoo/official/nlp/textcnn/README.md
View File

@ -161,7 +161,7 @@ For more configuration details, please refer the script `config.py`.
| Parameters | Ascend |
| ------------------- | ----------------------------------------------------- |
| Model Version | TextCNN |
| Resource | Ascend 910 ；CPU 2.60GHz，192cores；Memory，755G |
| Resource |Ascend 910; CPU 2.60GHz, 192cores; Memory 755G; OS Euler2.8 |
| uploaded Date | 11/10/2020 (month/day/year) |
| MindSpore Version | 1.0.1 |
| Dataset | Movie Review Data |

4
model_zoo/official/nlp/tinybert/README.md
View File

@ -418,7 +418,7 @@ The best acc is 0.891176
| Parameters | Ascend | GPU |
| -------------------------- | ---------------------------------------------------------- | ------------------------- |
| Model Version | TinyBERT | TinyBERT |
| Resource | Ascend 910, cpu:2.60GHz 192cores, memory:755G | NV SMX2 V100-32G, cpu:2.10GHz 64cores, memory:251G |
| 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 |
| Dataset | en-wiki-128 | en-wiki-128 |
@ -438,7 +438,7 @@ The best acc is 0.891176
| Parameters | Ascend | GPU |
| -------------------------- | ----------------------------- | ------------------------- |
| Model Version | | |
| Resource | Ascend 910 | NV SMX2 V100-32G |
| 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 |
| Dataset | SST-2, | SST-2 |

4
model_zoo/official/nlp/tinybert/README_CN.md
View File

@ -419,7 +419,7 @@ The best acc is 0.891176
| 参数 | Ascend | GPU |
| -------------------------- | ---------------------------------------------------------- | ------------------------- |
| 模型版本 | TinyBERT | TinyBERT |
| 资源 | Ascend 910, cpu:2.60GHz 192核, 内存:755G | NV SMX2 V100-32G, cpu:2.10GHz 64核, 内存:251G |
| 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 |
| 数据集 | en-wiki-128 | en-wiki-128 |
@ -438,7 +438,7 @@ The best acc is 0.891176
| 参数 | Ascend | GPU |
| -------------------------- | ----------------------------- | ------------------------- |
| 模型版本 | | |
| 资源 | Ascend 910 | NV SMX2 V100-32G |
| 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 |
| 数据集 | SST-2, | SST-2 |

4
model_zoo/official/nlp/transformer/README.md
View File

@ -240,7 +240,7 @@ Parameters for learning rate:
| Parameters | Ascend |
| -------------------------- | -------------------------------------------------------------- |
| Resource | Ascend 910 |
| Resource | Ascend 910; OS Euler2.8 |
| uploaded Date | 09/15/2020 (month/day/year) |
| MindSpore Version | 1.0.0 |
| Dataset | WMT Englis-German |
@ -258,7 +258,7 @@ Parameters for learning rate:
| Parameters | Ascend |
| ------------------- | --------------------------- |
| Resource | Ascend 910 |
| Resource | Ascend 910; OS Euler2.8 |
| Uploaded Date | 09/15/2020 (month/day/year) |
| MindSpore Version | 1.0.0 |
| Dataset | WMT newstest2014 |

4
model_zoo/official/nlp/transformer/README_CN.md
View File

@ -247,7 +247,7 @@ Parameters for learning rate:
| 参数 | Ascend |
| -------------------------- | -------------------------------------------------------------- |
| 资源 | Ascend 910 |
| 资源 | Ascend 910；系统 Euler2.8 |
| 上传日期 | 2020-06-09 |
| MindSpore版本 | 0.5.0-beta |
| 数据集 | WMT英-德翻译数据集 |
@ -265,7 +265,7 @@ Parameters for learning rate:
| 参数 | Ascend |
| ------------------- | --------------------------- |
|资源| Ascend 910 |
|资源| Ascend 910；系统 Euler2.8 |
| 上传日期 | 2020-06-09 |
| MindSpore版本 | 0.5.0-beta |
| 数据集 | WMT newstest2014 |

4
model_zoo/official/recommend/deepfm/README.md
View File

@ -265,7 +265,7 @@ Parameters for both training and evaluation can be set in config.py
| Parameters | Ascend | GPU |
| -------------------------- | ----------------------------------------------------------- | ---------------------- |
| Model Version | DeepFM | To do |
| Resource | Ascend 910; CPU 2.60GHz, 192cores; Memory 755G | 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 |
| MindSpore Version | 1.0.0 | To do |
| Dataset | [1] | To do |
@ -285,7 +285,7 @@ Parameters for both training and evaluation can be set in config.py
| Parameters | Ascend | GPU |
| ------------------- | --------------------------- | --------------------------- |
| Model Version | DeepFM | To do |
| Resource | Ascend 910 | 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 |
| Dataset | [1] | To do |

4
model_zoo/official/recommend/deepfm/README_CN.md
View File

@ -248,7 +248,7 @@ FM和深度学习部分拥有相同的输入原样特征向量，让DeepFM能从
| 参数 | Ascend | GPU |
| -------------------------- | ----------------------------------------------------------- | ---------------------- |
| 模型版本 | DeepFM | 待运行 |
| 资源 | Ascend 910;CPU 2.60GHz,192核；内存：755G | 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 |
| 数据集 | [1] | 待运行 |
@ -268,7 +268,7 @@ FM和深度学习部分拥有相同的输入原样特征向量，让DeepFM能从
| 参数 | Ascend | GPU |
| ------------------- | --------------------------- | --------------------------- |
| 模型版本 | DeepFM | 待运行 |
| 资源 | Ascend 910 | 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 |
| 数据集 | [1] | 待运行 |

4
model_zoo/official/recommend/naml/README.md
View File

@ -109,7 +109,7 @@ python export.py --platform [PLATFORM] --checkpoint_path [CHECKPOINT_PATH] --fil
| Parameters | Ascend |
| -------------------------- | ------------------------------------------------------------ |
| Model Version | NAML |
| Resource | Ascend 910 ；CPU 2.60GHz，56cores；Memory，314G |
| Resource |Ascend 910; CPU 2.60GHz, 56cores; Memory 314G; OS Euler2.8 |
| uploaded Date | 02/23/2021 (month/day/year) |
| MindSpore Version | 1.2.0 |
| Dataset | MINDlarge |
@ -125,7 +125,7 @@ python export.py --platform [PLATFORM] --checkpoint_path [CHECKPOINT_PATH] --fil
| Parameters | Ascend |
| ------------------- | --------------------------- |
| Model Version | NAML |
| Resource | Ascend 910 |
| Resource | Ascend 910; OS Euler2.8 |
| Uploaded Date | 02/23/2021 (month/day/year) |
| MindSpore Version | 1.2.0 |
| Dataset | MINDlarge |

4
model_zoo/official/recommend/ncf/README.md
View File

@ -196,7 +196,7 @@ Parameters for both training and evaluation can be set in config.py.
| Parameters | Ascend |
| -------------------------- | ------------------------------------------------------------ |
| Model Version | NCF |
| Resource | Ascend 910 ；CPU 2.60GHz，56cores；Memory，314G |
| Resource | Ascend 910; CPU 2.60GHz, 56cores; Memory 314G; OS Euler2.8 |
| uploaded Date | 10/23/2020 (month/day/year) |
| MindSpore Version | 1.0.0 |
| Dataset | ml-1m |
@ -212,7 +212,7 @@ Parameters for both training and evaluation can be set in config.py.
| Parameters | Ascend |
| ------------------- | --------------------------- |
| Model Version | NCF |
| Resource | Ascend 910 |
| Resource | Ascend 910; OS Euler2.8 |
| Uploaded Date | 10/23/2020 (month/day/year) |
| MindSpore Version | 1.0.0 |
| Dataset | ml-1m |

4
model_zoo/official/recommend/wide_and_deep/README.md
View File

@ -316,7 +316,7 @@ python eval.py
| Parameters | Single <br />Ascend | Single<br />GPU | Data-Parallel-8P | Host-Device-mode-8P |
| ------------------------ | ------------------------------- | ------------------------------- | ------------------------------- | ------------------------------- |
| Resource | Ascend 910 | Tesla V100-PCIE 32G | Ascend 910 | Ascend 910 |
| 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 |
| Dataset | [1] | [1] | [1] | [1] |
@ -337,7 +337,7 @@ Note: The result of GPU is tested under the master version. The parameter server
| Parameters | Wide&Deep |
| ----------------- | --------------------------- |
| Resource | Ascend 910 |
| Resource | Ascend 910; OS Euler2.8 |
| Uploaded Date | 10/27/2020 (month/day/year) |
| MindSpore Version | 1.0 |
| Dataset | [1] |

4
model_zoo/official/recommend/wide_and_deep/README_CN.md
View File

@ -318,7 +318,7 @@ python eval.py
| 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 | Tesla V100-PCIE 32G | Ascend 910 | Ascend 910 |
| 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 |
| 数据集 | [1] | [1] | [1] | [1] |
@ -339,7 +339,7 @@ python eval.py
| 参数 | Wide&Deep |
| ----------------- | --------------------------- |
| 资源 | Ascend 910 |
| 资源 | Ascend 910；系统 Euler2.8 |
| 上传日期 | 2020-08-21 |
| MindSpore版本 | 0.6.0-beta |
| 数据集 | [1] |

4
model_zoo/official/recommend/wide_and_deep_multitable/README.md
View File

@ -167,7 +167,7 @@ python eval.py
| Parameters | Single <br />Ascend | Data-Parallel-8P |
| ------------------------ | ------------------------------- | ------------------------------- |
| Resource | Ascend 910 | Ascend 910 |
| 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 |
| Dataset | [1] | [1] |
@ -187,7 +187,7 @@ All executable scripts can be found in [here](https://gitee.com/mindspore/mindsp
| Parameters | Wide&Deep |
| ----------------- | --------------------------- |
| Resource | Ascend 910 |
| Resource | Ascend 910; OS Euler2.8 |
| Uploaded Date | 10/27/2020 (month/day/year) |
| MindSpore Version | 1.0 |
| Dataset | [1] |

2
model_zoo/official/rl/dqn/README.md
View File

@ -109,7 +109,7 @@ pip install gym
| Parameters | DQN |
| -------------------------- | ----------------------------------------------------------- |
| Resource | Ascend 910 ；CPU 2.60GHz，192cores；Memory，755G |
| Resource | Ascend 910; CPU 2.60GHz, 192cores; Memory 755G; OS Euler2.8 |
| uploaded Date | 03/10/2021 (month/day/year) |
| MindSpore Version | 1.1.0 |
| Training Parameters | batch_size = 512, lr=0.001 |

2
model_zoo/research/audio/fcn-4/README.md
View File

@ -181,7 +181,7 @@ Parameters for both training and evaluation can be set in config.py
| Parameters | Ascend |
| -------------------------- | ----------------------------------------------------------- |
| Model Version | FCN-4 |
| Resource | Ascend 910 ；CPU 2.60GHz，56cores；Memory，314G |
| 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 |
| Training Parameters | epoch=10, steps=534, batch_size = 32, lr=0.005 |

4
model_zoo/research/cv/FaceAttribute/README.md
View File

@ -238,7 +238,7 @@ sh run_export.sh [BATCH_SIZE] [USE_DEVICE_ID] [PRETRAINED_BACKBONE]
| Parameters | Face Attribute |
| -------------------------- | ----------------------------------------------------------- |
| Model Version | V1 |
| Resource | Ascend 910; CPU 2.60GHz, 192cores; Memory, 755G |
| Resource | Ascend 910; CPU 2.60GHz, 192cores; Memory 755G; OS Euler2.8 |
| uploaded Date | 09/30/2020 (month/day/year) |
| MindSpore Version | 1.0.0 |
| Dataset | 91K images |
@ -255,7 +255,7 @@ sh run_export.sh [BATCH_SIZE] [USE_DEVICE_ID] [PRETRAINED_BACKBONE]
| Parameters | Face Attribute |
| ------------------- | --------------------------- |
| Model Version | V1 |
| Resource | Ascend 910 |
| Resource | Ascend 910; OS Euler2.8 |
| Uploaded Date | 09/30/2020 (month/day/year) |
| MindSpore Version | 1.0.0 |
| Dataset | 11K images |

4
model_zoo/research/cv/FaceDetection/README.md
View File

@ -214,7 +214,7 @@ sh run_export.sh [BATCH_SIZE] [USE_DEVICE_ID] [PRETRAINED_BACKBONE]
| Parameters | Face Detection |
| -------------------------- | ----------------------------------------------------------- |
| Model Version | V1 |
| Resource | Ascend 910; CPU 2.60GHz, 192cores; Memory, 755G |
| Resource | Ascend 910; CPU 2.60GHz, 192cores; Memory 755G; OS Euler2.8 |
| uploaded Date | 09/30/2020 (month/day/year) |
| MindSpore Version | 1.0.0 |
| Dataset | 13K images |
@ -231,7 +231,7 @@ sh run_export.sh [BATCH_SIZE] [USE_DEVICE_ID] [PRETRAINED_BACKBONE]
| Parameters | Face Detection |
| ------------------- | --------------------------- |
| Model Version | V1 |
| Resource | Ascend 910 |
| Resource | Ascend 910; OS Euler2.8 |
| Uploaded Date | 09/30/2020 (month/day/year) |
| MindSpore Version | 1.0.0 |
| Dataset | 3K images |

Some files were not shown because too many files have changed in this diff Show More