History

gong chen a6dfa281ea Init GraphKernel. - It provides a unified style to express graph and kernel for user. - It provides a unified IR to represent graph and kernel for developer. - It breaks the boundary between graph and kernel. - It provides more opportunities to do compile optimization.		2020-06-20 22:31:54 +08:00
..
Transformer	fix decoder loop for Transformer model	2020-06-18 14:18:21 +08:00
alexnet	!2370 modify alexnet shell def get_lr args	2020-06-20 10:54:57 +08:00
bert	Init GraphKernel.	2020-06-20 22:31:54 +08:00
deepfm	add DeepFM	2020-05-28 23:31:11 +08:00
deeplabv3	1:modify shell for deeplabv3	2020-06-10 18:55:29 +08:00
faster_rcnn	fix fastrcnn eval failed	2020-06-18 10:23:45 +08:00
gat	Add gat to model zoo	2020-06-16 08:32:45 +00:00
gcn	Add gat to model zoo	2020-06-16 08:32:45 +00:00
googlenet	Move googlenet into ModelZoo and add superlink in README	2020-06-19 20:50:10 +08:00
lenet	dataset sink is false when run in CPU	2020-06-20 11:28:57 +08:00
lenet_quant	quantization aware training for lenet readme.md update	2020-06-20 10:16:39 +08:00
lstm	aware quantization training auto create graph	2020-06-19 22:01:16 +08:00
mass	Implements of masked seq2seq pre-training for language generation.	2020-06-20 15:48:49 +08:00
mobilenetv2	change tensor dtype and shape from function to attr	2020-06-12 19:03:23 +08:00
mobilenetv3	change tensor dtype and shape from function to attr	2020-06-12 19:03:23 +08:00
resnet101	change tensor dtype and shape from function to attr	2020-06-12 19:03:23 +08:00
ssd	change tensor dtype and shape from function to attr	2020-06-12 19:03:23 +08:00
vgg16	refactoring code directory for vgg16 and lstm	2020-06-16 16:38:00 +08:00
wide_and_deep	!2279 add model zoo script of wide and deep for gpu	2020-06-18 20:08:47 +08:00
yolov3	clear pylint for yolov3	2020-06-19 10:28:07 +08:00
README.md	Move googlenet into ModelZoo and add superlink in README	2020-06-19 20:50:10 +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

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

License

Apache License 2.0