• MindSpore Logo
• • Welcome to the Model Zoo for MindSpore
  • Table of Contents
  • • Official
    • Research
  • Announcements
  • • 2021.9.15 Set up repository models
  • Related Website
  • Disclaimers
  • License
  • FAQ

Welcome to the Model Zoo for MindSpore

In order to facilitate developers to enjoy the benefits of MindSpore framework, we will continue to add typical networks and some of the related pre-trained 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

• Officially maintained and supported

Table of Contents

Official

Domain	Sub Domain	Network	Ascend	GPU	CPU
Computer Vision (CV)	Image Classification	AlexNet	✅	✅
Computer Vision (CV)	Image Classification	CNN	✅
Computer Vision (CV)	Image Classification	DenseNet100			✅
Computer Vision (CV)	Image Classification	DenseNet121	✅
Computer Vision (CV)	Image Classification	DPN	✅
Computer Vision (CV)	Image Classification	EfficientNet-B0		✅
Computer Vision (CV)	Image Classification	GoogLeNet	✅	✅
Computer Vision (CV)	Image Classification	InceptionV3	✅
Computer Vision (CV)	Image Classification	InceptionV4	✅
Computer Vision (CV)	Image Classification	LeNet	✅	✅	✅
Computer Vision (CV)	Image Classification	LeNet (Quantization)	✅	✅
Computer Vision (CV)	Image Classification	MobileNetV1	✅
Computer Vision (CV)	Image Classification	MobileNetV2	✅	✅	✅
Computer Vision (CV)	Image Classification	MobileNetV2 (Quantization)	✅	✅
Computer Vision (CV)	Image Classification	MobileNetV3		✅
Computer Vision (CV)	Image Classification	NASNet		✅
Computer Vision (CV)	Image Classification	ResNet-18	✅
Computer Vision (CV)	Image Classification	ResNet-50	✅	✅	✅
Computer Vision (CV)	Image Classification	ResNet-50 (Quantization)	✅
Computer Vision (CV)	Image Classification	ResNet-101	✅	✅
Computer Vision (CV)	Image Classification	ResNeXt50	✅	✅
Computer Vision (CV)	Image Classification	SE-ResNet50	✅
Computer Vision (CV)	Image Classification	ShuffleNetV1	✅
Computer Vision (CV)	Image Classification	ShuffleNetV2		✅
Computer Vision (CV)	Image Classification	SqueezeNet	✅
Computer Vision (CV)	Image Classification	Tiny-DarkNet	✅
Computer Vision (CV)	Image Classification	VGG16	✅	✅
Computer Vision (CV)	Image Classification	Xception	✅
Computer Vision (CV)	Object Detection	CenterFace	✅
Computer Vision (CV)	Object Detection	CTPN	✅
Computer Vision (CV)	Object Detection	Faster R-CNN	✅	✅
Computer Vision (CV)	Object Detection	Mask R-CNN	✅
Computer Vision (CV)	Object Detection	Mask R-CNN (MobileNetV1)	✅
Computer Vision (CV)	Object Detection	RetinaFace-ResNet50		✅
Computer Vision (CV)	Object Detection	SSD	✅	✅	✅
Computer Vision (CV)	Object Detection	SSD-MobileNetV1-FPN	✅
Computer Vision (CV)	Object Detection	SSD-Resnet50-FPN	✅
Computer Vision (CV)	Object Detection	SSD-VGG16	✅
Computer Vision (CV)	Object Detection	WarpCTC	✅	✅
Computer Vision (CV)	Object Detection	YOLOv3-ResNet18	✅
Computer Vision (CV)	Object Detection	YOLOv3-DarkNet53	✅	✅
Computer Vision (CV)	Object Detection	YOLOv3-DarkNet53 (Quantization)	✅
Computer Vision (CV)	Object Detection	YOLOv4	✅
Computer Vision (CV)	Text Detection	DeepText	✅
Computer Vision (CV)	Text Detection	PSENet	✅
Computer Vision (CV)	Text Recognition	CNN+CTC	✅
Computer Vision (CV)	Semantic Segmentation	DeepLabV3	✅		✅
Computer Vision (CV)	Semantic Segmentation	U-Net2D (Medical)	✅
Computer Vision (CV)	Semantic Segmentation	U-Net3D (Medical)	✅
Computer Vision (CV)	Semantic Segmentation	U-Net++	✅
Computer Vision (CV)	Keypoint Detection	OpenPose	✅
Computer Vision (CV)	Keypoint Detection	SimplePoseNet	✅
Computer Vision (CV)	Optical Character Recognition	CRNN	✅
Natural Language Processing (NLP)	Natural Language Understanding	BERT	✅	✅
Natural Language Processing (NLP)	Natural Language Understanding	FastText	✅
Natural Language Processing (NLP)	Natural Language Understanding	GNMT v2	✅
Natural Language Processing (NLP)	Natural Language Understanding	GRU	✅
Natural Language Processing (NLP)	Natural Language Understanding	MASS	✅	✅
Natural Language Processing (NLP)	Natural Language Understanding	SentimentNet	✅	✅	✅
Natural Language Processing (NLP)	Natural Language Understanding	Transformer	✅	✅
Natural Language Processing (NLP)	Natural Language Understanding	TinyBERT	✅	✅
Natural Language Processing (NLP)	Natural Language Understanding	TextCNN	✅
Recommender	Recommender System, CTR prediction	DeepFM	✅	✅	✅
Recommender	Recommender System, Search, Ranking	Wide&Deep	✅	✅
Recommender	Recommender System	NAML	✅
Recommender	Recommender System	NCF	✅
Graph Neural Networks (GNN)	Text Classification	GCN	✅
Graph Neural Networks (GNN)	Text Classification	GAT	✅
Graph Neural Networks (GNN)	Recommender System	BGCF	✅

Research

Domain	Sub Domain	Network	Ascend	GPU	CPU
Computer Vision (CV)	Image Classification	FaceAttributes	✅
Computer Vision (CV)	Object Detection	FaceDetection	✅
Computer Vision (CV)	Image Classification	FaceQualityAssessment	✅
Computer Vision (CV)	Image Classification	FaceRecognition	✅
Computer Vision (CV)	Image Classification	FaceRecognitionForTracking	✅
Computer Vision (CV)	Object Detection	Spnas	✅
Computer Vision (CV)	Object Detection	SSD-GhostNet	✅
Computer Vision (CV)	Key Point Detection	CenterNet	✅		✅
Computer Vision (CV)	Image Style Transfer	CycleGAN			✅
Natural Language Processing (NLP)	Natural Language Understanding	DS-CNN	✅
Natural Language Processing (NLP)	Natural Language Understanding	TextRCNN	✅
Natural Language Processing (NLP)	Natural Language Understanding	TPRR	✅
Recommender	Recommender System, CTR prediction	AutoDis	✅
Audio	Audio Tagging	FCN-4	✅
High Performance Computing	Molecular Dynamics	DeepPotentialH2O	✅
High Performance Computing	Ocean Model	GOMO		✅

• Community

Announcements

2021.9.15 Set up repository models

models comes from the directory model_zoo of repository mindspore. This new repository doesn't contain any history of commits about the directory model_zoo in mindspore, you could refer to the repository mindspore for the past commits.

Related Website

Here is the ModelZoo for MindSpore which support different devices including Ascend, GPU, CPU and mobile.

If you are looking for exclusive models only for Ascend using different ML platform, you could refer to Ascend ModelZoo and corresponding gitee repository

If you are looking for some pretrained checkpoint of mindspore, you could refer to MindSpore Hub or Download Website.

Disclaimers

Mindspore only provides scripts that downloads and preprocesses public datasets. We do not own these datasets and are not responsible for their quality or maintenance. Please make sure you have permission to use the dataset under the dataset’s license. The models trained on these dataset are for non-commercial research and educational purpose only.

To dataset owners: we will remove or update all public content upon request if you don’t want your dataset included on Mindspore, or wish to update it in any way. Please contact us through a Github/Gitee issue. Your understanding and contribution to this community is greatly appreciated.

MindSpore is Apache 2.0 licensed. Please see the LICENSE file.

License

Apache License 2.0

FAQ

For more information about MindSpore framework, please refer to FAQ

• Q: How to resolve the lack of memory while using the model directly under "models" with errors such as Failed to alloc memory pool memory?

  A: The typical reason for insufficient memory when directly using models under "models" is due to differences in operating mode (PYNATIVE_MODE), operating environment configuration, and license control (AI-TOKEN). PYNATIVE_MODE usually uses more memory than GRAPH_MODE , especially in the training graph that needs back propagation calculation, you can try to use some smaller batch size; the operating environment will also cause similar problems due to the different configurations of NPU cores, memory, etc.; different gears of License control (AI-TOKEN ) will cause different memory overhead during execution. You can also try to use some smaller batch sizes.

• Q: How to resolve the error about the interface are not supported in some network operations, such as cann not import?

  A: Please check the version of MindSpore and the branch you fetch the modelzoo scripts. Some model scripits in latest branch will use new interface in the latest version of MindSpore.

• Q: How to run the scripts on Windows system?

  A: Most the start-up scripts are written in bash, but we usually can't run bash directly on Windows. You can try start python directly without bash scripts. If you really need the start-up bash scripts, we suggest you the following method to get a bash environment on Windows:

  1. Use a virtual system or docker container with linux system. Then run the scripts in the virtual system or container.
  2. Use WSL, you could turn on the Windows Subsystem for Linux on Windows to obtain an linux system which could run the bash scripts.
  3. Use some bash tools on Windows, such as cygwin and git bash.