History

mindspore-ci-bot e32ea53db5 !2864 add mobilenetV2 export Merge pull request !2864 from chenzhongming/master		2020-07-07 14:06:56 +08:00
..
Transformer	modify tokenization for transformer model	2020-06-30 21:31:59 +08:00
alexnet	modify dataset.py	2020-06-22 20:06:53 +08:00
bert	!2514 add bert support for glue task	2020-07-01 10:13:21 +08:00
deepfm	add Yolov3-darknet53 model	2020-06-30 09:46:58 +08:00
deeplabv3	add flags on function	2020-06-23 20:22:07 +08:00
faster_rcnn	fix fastrcnn accuracy	2020-07-01 15:43:01 +08:00
gat	adjust model zoo utils	2020-06-28 23:19:20 +08:00
gcn	!2802 fix gcn import path error	2020-07-02 14:18:58 +08:00
googlenet	support multi server muli process	2020-07-06 02:14:55 +08:00
lenet	checkpoint add model_type	2020-06-24 12:31:08 +08:00
lenet_quant	bug fix in auto create quant graph in master	2020-07-03 16:56:02 +08:00
lstm	GPU Lstm network	2020-07-01 09:33:42 +08:00
mass	Solve MASS codex warning.	2020-06-29 16:32:31 +08:00
mobilenetv2	!2801 add mobilenet v2 quant and resnet50 quant to model_zoo	2020-07-02 10:13:41 +08:00
mobilenetv2_quant	add mobilenetV2 quant export	2020-07-07 11:13:42 +08:00
mobilenetv3	!2801 add mobilenet v2 quant and resnet50 quant to model_zoo	2020-07-02 10:13:41 +08:00
resnet	move resnet series from example to model_zoo	2020-06-28 23:01:16 +08:00
resnet50_quant	add mobilenet v2 quant and resnet50 quant to model_zoo	2020-07-02 09:04:02 +08:00
resnet_thor	move resnet_thor series from example to model_zoo	2020-06-29 14:41:37 +08:00
resnext50	add resnext50	2020-06-29 20:21:58 +08:00
ssd	change tensor dtype and shape from function to attr	2020-06-12 19:03:23 +08:00
utils	add hccl_tools	2020-07-06 16:25:49 +08:00
vgg16	fix accurancy lower then 92	2020-06-24 14:08:16 +08:00
warpctc	add warpctc to modelzoo	2020-06-29 22:37:30 +08:00
wide_and_deep	clean codedex warning	2020-07-01 16:01:49 +08:00
yolov3_darknet53	fix data preprocess bug	2020-07-03 18:48:07 +08:00
yolov3_resnet18	add Yolov3-darknet53 model	2020-06-30 09:46:58 +08:00
README.md	add transformer in model_zoo/README	2020-07-03 11:07:16 +08:00
__init__.py	Implements of masked seq2seq pre-training for language generation.	2020-06-20 15:48:49 +08:00

README.md

Welcome to the Model Zoo for MindSpore

In order to facilitate developers to enjoy the benefits of MindSpore framework and Huawei chips, we will continue to add typical networks and models . If you have needs for the model zoo, you can file an issue on gitee or MindSpore, We will consider it in time.

SOTA models using the latest MindSpore APIs
The best benefits from MindSpore and Huawei chips
Officially maintained and supported

Models and Implementations
- Computer Vision
  - Image Classification
    - GoogleNet
    - ResNet50[benchmark]
    - ResNet101
    - VGG16
    - AlexNet
    - LeNet
  - Object Detection and Segmentation
    - YoloV3
    - MobileNetV2
    - MobileNetV3
    - SSD
- Natural Language Processing
  - BERT
  - MASS
  - Transformer

Announcements

Date	News
May 31, 2020	Support MindSpore v0.3.0-alpha

Models and Implementations

Computer Vision

Image Classification

GoogleNet

Parameters	GoogleNet
Published Year	2014
Paper	Going Deeper with Convolutions
Resource	Ascend 910
Features	• Mixed Precision • Multi-GPU training support with Ascend
MindSpore Version	0.3.0-alpha
Dataset	CIFAR-10
Training Parameters	epoch=125, batch_size = 128, lr=0.1
Optimizer	Momentum
Loss Function	Softmax Cross Entropy
Accuracy	1pc: 93.4%; 8pcs: 92.17%
Speed	79 ms/Step
Loss	0.0016
Params (M)	6.8
Checkpoint for Fine tuning	43.07M (.ckpt file)
Model for inference	21.50M (.onnx file), 21.60M(.geir file)
Scripts	https://gitee.com/mindspore/mindspore/tree/master/model_zoo/googlenet

ResNet50

Parameters	ResNet50
Published Year
Paper
Resource
Features
MindSpore Version
Dataset
Training Parameters
Optimizer
Loss Function
Accuracy
Speed
Loss
Params (M)
Checkpoint for Fine tuning
Model for inference
Scripts

ResNet101

Parameters	ResNet101
Published Year
Paper
Resource
Features
MindSpore Version
Dataset
Training Parameters
Optimizer
Loss Function
Accuracy
Speed
Loss
Params (M)
Checkpoint for Fine tuning
Model for inference
Scripts

VGG16

Parameters	VGG16
Published Year
Paper
Resource
Features
MindSpore Version
Dataset
Training Parameters
Optimizer
Loss Function
Accuracy
Speed
Loss
Params (M)
Checkpoint for Fine tuning
Model for inference
Scripts

AlexNet

Parameters	AlexNet
Published Year
Paper
Resource
Features
MindSpore Version
Dataset
Training Parameters
Optimizer
Loss Function
Accuracy
Speed
Loss
Params (M)
Checkpoint for Fine tuning
Model for inference
Scripts

LeNet

Parameters	LeNet
Published Year
Paper
Resource
Features
MindSpore Version
Dataset
Training Parameters
Optimizer
Loss Function
Accuracy
Speed
Loss
Params (M)
Checkpoint for Fine tuning
Model for inference
Scripts

Object Detection and Segmentation

YoloV3

Parameters	YoLoV3
Published Year
Paper
Resource
Features
MindSpore Version
Dataset
Training Parameters
Optimizer
Loss Function
Mean Average Precision (mAP@0.5)
Speed
Loss
Params (M)
Checkpoint for Fine tuning
Model for inference
Scripts

MobileNetV2

Parameters	MobileNetV2
Published Year
Paper
Resource
Features
MindSpore Version
Dataset
Training Parameters
Optimizer
Loss Function
Mean Average Precision (mAP@0.5)
Speed
Loss
Params (M)
Checkpoint for Fine tuning
Model for inference
Scripts

MobileNetV3

Parameters	MobileNetV3
Published Year
Paper
Resource
Features
MindSpore Version
Dataset
Training Parameters
Optimizer
Loss Function
Mean Average Precision (mAP@0.5)
Speed
Loss
Params (M)
Checkpoint for Fine tuning
Model for inference
Scripts

SSD

Parameters	SSD
Published Year
Paper
Resource
Features
MindSpore Version
Dataset
Training Parameters
Optimizer
Loss Function
Mean Average Precision (mAP@0.5)
Speed
Loss
Params (M)
Checkpoint for Fine tuning
Model for inference
Scripts

Natural Language Processing

BERT

Parameters	BERT
Published Year
Paper
Resource
Features
MindSpore Version
Dataset
Training Parameters
Optimizer
Loss Function
GLUE Score
Speed
Loss
Params (M)
Checkpoint for Fine tuning
Model for inference
Scripts

MASS

Parameters	MASS
Published Year
Paper
Resource
Features
MindSpore Version
Dataset
Training Parameters
Optimizer
Loss Function
ROUGE Score
Speed
Loss
Params (M)
Checkpoint for Fine tuning
Model for inference
Scripts

Transformer

Parameters	Transformer
Published Year	2017
Paper	Attention Is All You Need
Resource	Ascend 910
Features	• Multi-GPU training support with Ascend
MindSpore Version	0.5.0-beta
Dataset	WMT Englis-German
Training Parameters	epoch=52, batch_size=96
Optimizer	Adam
Loss Function	Softmax Cross Entropy
BLEU Score	28.7
Speed	410ms/step (8pcs)
Loss	2.8
Params (M)	213.7
Checkpoint for inference	2.4G (.ckpt file)
Scripts	https://gitee.com/mindspore/mindspore/tree/master/model_zoo/Transformer

License

Apache License 2.0