/models-autodis

huawei-recommend-autodis

Primary LanguagePythonApache License 2.0Apache-2.0

MindSpore Logo

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
Audio Speech Synthesis LPCNet ✅
Audio Speech Synthesis MelGAN ✅
Audio Speech Synthesis Tacotron2 ✅
Computer Vision (CV) Point Cloud Model OctSqueeze ✅
Computer Vision (CV) Optical Flow Estimation PWCNet ✅
Computer Vision (CV) Object Tracking Deepsort ✅
Computer Vision (CV) Object Tracking ADNet ✅
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 MobileNetV1 ✅
Computer Vision (CV) Image Classification MobileNetV2 ✅ ✅ ✅
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-34 ✅
Computer Vision (CV) Image Classification ResNet-50 ✅ ✅ ✅
Computer Vision (CV) Image Classification ResNet-101 ✅ ✅
Computer Vision (CV) Image Classification ResNet-152 ✅
Computer Vision (CV) Image Classification ResNeXt50 ✅ ✅
Computer Vision (CV) Image Classification ResNeXt101 ✅
Computer Vision (CV) Image Classification SE-ResNet50 ✅
Computer Vision（CV） Image Classification SE-ResNext50 ✅
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) Image Classification CspDarkNet53 ✅
Computer Vision (CV) Image Classification ErfNet ✅
Computer Vision (CV) Image Classification SimCLR ✅
Computer Vision (CV) Image Classification Vit ✅
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 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 YOLOv4 ✅
Computer Vision (CV) Object Detection YOLOv5 ✅
Computer Vision (CV) Object Detection RetinaNet ✅
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 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) Semantic Segmentation Fast-SCNN ✅
Computer Vision (CV) Semantic Segmentation FCN8s ✅
Computer Vision (CV) 6DoF Pose Estimation PVNet ✅
Computer Vision (CV) Keypoint Detection OpenPose ✅
Computer Vision (CV) Keypoint Detection SimplePoseNet ✅
Computer Vision (CV) Scene Text Detection East ✅
Computer Vision (CV) Scene Text Detection PSENet ✅
Computer Vision (CV) Scene Text Recognition CRNN ✅
Computer Vision (CV) Scene Text Recognition CNN+CTC ✅
Computer Vision (CV) Scene Text Recognition CRNN-Seq2Seq-OCR ✅
Computer Vision (CV) Scene Text Recognition WarpCTC ✅
Computer Vision (CV) Defect Detection ssim-ae ✅
Computer Vision (CV) Defect Detection PatchCore ✅
Computer Vision (CV) Face Detection RetinaFace-ResNet50 ✅ ✅
Computer Vision (CV) Face Detection CenterFace ✅
Computer Vision (CV) Face Detection SphereFace ✅
Computer Vision (CV) Crowd Counting MCNN ✅
Computer Vision (CV) Depth Estimation DepthNet ✅
Computer Vision (CV) Camera Relocalization PoseNet ✅
Computer Vision (CV) Image Matting Semantic Human Matting ✅
Computer Vision (CV) Video Classification C3D ✅
Computer Vision (CV) Image Super-Resolution SRCNN ✅
Computer Vision (CV) Image Super-Resolution RDN ✅ ✅
Computer Vision (CV) Image Denoising BRDNet ✅
Computer Vision (CV) Image Denoising DnCNN ✅
Computer Vision (CV) Image Denoising Learning-to-See-in-the-Dark ✅
Computer Vision (CV) Image Quality Assessment NIMA ✅
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 ✅
Natural Language Processing (NLP) Natural Language Understanding CPM ✅
Natural Language Processing (NLP) Natural Language Understanding ERNIE ✅
Natural Language Processing (NLP) Natural Language Understanding GPT-3 ✅
Natural Language Processing (NLP) Emotion Classification EmoTect ✅
Natural Language Processing (NLP) Emotion Classification LSTM ✅
Natural Language Processing (NLP) Dialogue Generation DGU ✅
Natural Language Processing (NLP) Dialogue Generation DuConv ✅
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 3D Densenet ✅
Computer Vision (CV) Image Classification Auto Augment ✅
Computer Vision (CV) Image Classification AVA ✅
Computer Vision (CV) Image Classification CCT ✅
Computer Vision (CV) Image Classification dnet-nas ✅
Computer Vision (CV) Image Classification Efficientnet-b0 ✅
Computer Vision (CV) Image Classification Efficientnet-b1 ✅
Computer Vision (CV) Image Classification Efficientnet-b2 ✅
Computer Vision (CV) Image Classification Efficientnet-b3 ✅
Computer Vision (CV) Image Classification FDA-BNN ✅
Computer Vision (CV) Image Classification fishnet99 ✅
Computer Vision (CV) Image Classification GENET ✅
Computer Vision (CV) Image Classification GhostNet ✅
Computer Vision (CV) Image Classification Glore_res200 ✅
Computer Vision (CV) Image Classification Glore_res50 ✅
Computer Vision (CV) Image Classification HarDNet ✅
Computer Vision (CV) Image Classification HourNAS ✅
Computer Vision (CV) Image Classification HRNetW48-cls ✅
Computer Vision (CV) Image Classification ibn-net ✅
Computer Vision (CV) Image Classification Inception ResNet V2 ✅
Computer Vision (CV) Image Classification Resnetv2_50_frn ✅
Computer Vision (CV) Image Classification META-Baseline ✅
Computer Vision (CV) Image Classification MNasNet ✅
Computer Vision (CV) Image Classification MobilenetV3-Large ✅
Computer Vision (CV) Image Classification MobilenetV3-Small ✅
Computer Vision (CV) Image Classification NFNet-F0 ✅
Computer Vision (CV) Image Classification ntsnet ✅
Computer Vision (CV) Image Classification Pdarts ✅
Computer Vision (CV) Image Classification PNASNet-5 ✅
Computer Vision (CV) Image Classification ProtoNet ✅
Computer Vision (CV) Image Classification Proxylessnas ✅
Computer Vision (CV) Image Classification RelationNet ✅
Computer Vision (CV) Image Classification renas ✅
Computer Vision (CV) Image Classification Res2net ✅
Computer Vision (CV) Image Classification ResNeSt-50 ✅
Computer Vision (CV) Image Classification ResNet50-BAM ✅
Computer Vision (CV) Image Classification ResNet50-quadruplet ✅
Computer Vision (CV) Image Classification ResNet50-triplet ✅
Computer Vision (CV) Image Classification ResNetV2 ✅
Computer Vision (CV) Image Classification ResNeXt152_vd_64x4d ✅
Computer Vision (CV) Image Classification SE-Net ✅
Computer Vision (CV) Image Classification SERes2Net50 ✅
Computer Vision (CV) Image Classification SinglePathNas ✅
Computer Vision (CV) Image Classification SKNet-50 ✅
Computer Vision (CV) Image Classification SPPNet ✅
Computer Vision (CV) Image Classification SqueezeNet ✅
Computer Vision (CV) Image Classification SqueezeNet1_1 ✅
Computer Vision (CV) Image Classification Swin Transformer ✅
Computer Vision (CV) Image Classification TNT ✅
Computer Vision (CV) Image Classification VGG19 ✅
Computer Vision (CV) Image Classification Vit-Base ✅
Computer Vision (CV) Image Classification Wide ResNet ✅
Computer Vision (CV) Image Classification FaceAttributes ✅
Computer Vision (CV) Image Classification FaceQualityAssessment ✅
Computer Vision (CV) Re-Identification Aligned-ReID ✅
Computer Vision (CV) Re-Identification DDAG ✅
Computer Vision (CV) Re-Identification MVD ✅
Computer Vision (CV) Re-Identification OSNet ✅
Computer Vision (CV) Re-Identification PAMTRI ✅
Computer Vision (CV) Re-Identification VehicleNet ✅
Computer Vision (CV) Face Detection FaceDetection ✅
Computer Vision (CV) Face Detection FaceBoxes ✅
Computer Vision (CV) Face Detection RetinaFace ✅
Computer Vision (CV) Face Recognition Arcface ✅
Computer Vision (CV) Face Recognition DeepID ✅
Computer Vision (CV) Face Recognition FaceRecognition ✅
Computer Vision (CV) Face Recognition FaceRecognitionForTracking ✅
Computer Vision (CV) Face Recognition LightCNN ✅
Computer Vision (CV) Object Detection Spnas ✅
Computer Vision (CV) Object Detection SSD-GhostNet ✅
Computer Vision (CV） Object Detection EGNet ✅
Computer Vision (CV) Object Detection FasterRCNN-FPN-DCN ✅
Computer Vision (CV) Object Detection NAS-FPN ✅
Computer Vision (CV) Object Detection RAS ✅
Computer Vision (CV) Object Detection r-cnn ✅
Computer Vision (CV) Object Detection RefineDet ✅
Computer Vision (CV) Object Detection Res2net_fasterrcnn ✅
Computer Vision (CV) Object Detection Res2net_yolov3 ✅
Computer Vision (CV) Object Detection Retinanet_resnet101 ✅
Computer Vision (CV) Object Detection SSD_MobilenetV2_fpnlite ✅
Computer Vision (CV) Object Detection ssd_mobilenet_v2 ✅
Computer Vision (CV) Object Detection ssd_resnet50 ✅
Computer Vision (CV) Object Detection ssd_inceptionv2 ✅
Computer Vision (CV) Object Detection ssd_resnet34 ✅
Computer Vision (CV) Object Detection U-2-Net ✅
Computer Vision (CV) Object Detection YOLOV3-tiny ✅
Computer Vision (CV) Object Tracking SiamFC ✅
Computer Vision (CV) Object Tracking SiamRPN ✅
Computer Vision (CV) Object Tracking FairMOT ✅
Computer Vision (CV) Key Point Detection CenterNet ✅ ✅
Computer Vision (CV) Key Point Detection CenterNet-hourglass ✅
Computer Vision (CV) Key Point Detection CenterNet-resnet101 ✅
Computer Vision (CV) Key Point Detection CenterNet-resnet50 ✅
Computer Vision (CV) Point Cloud Model PointNet ✅
Computer Vision (CV) Point Cloud Model PointNet++ ✅
Computer Vision (CV) Depth Estimation midas ✅
Computer Vision (CV) Sequential Image Classification TCN ✅
Computer Vision (CV) Temporal Localization TALL ✅
Computer Vision (CV) Image Matting FCA-net ✅
Computer Vision (CV) Video Classification Attention Cluster ✅
Computer Vision (CV) Video Classification ECO-lite ✅
Computer Vision (CV) Video Classification R(2+1)D ✅
Computer Vision (CV) Video Classification Resnet-3D ✅
Computer Vision (CV) Video Classification StNet ✅
Computer Vision (CV) Video Classification TSM ✅
Computer Vision (CV) Video Classification TSN ✅
Computer Vision (CV) Zero-Shot Learnning DEM ✅
Computer Vision (CV) Style Transfer AECRNET ✅
Computer Vision (CV) Style Transfer APDrawingGAN ✅
Computer Vision (CV) Style Transfer Arbitrary-image-stylization ✅
Computer Vision (CV) Style Transfer AttGAN ✅
Computer Vision (CV) Style Transfer CycleGAN ✅
Computer Vision (CV) Image Super-Resolution CSD ✅
Computer Vision (CV) Image Super-Resolution DBPN ✅
Computer Vision (CV) Image Super-Resolution EDSR ✅
Computer Vision (CV) Image Super-Resolution esr-ea ✅
Computer Vision (CV) Image Super-Resolution ESRGAN ✅
Computer Vision (CV) Image Super-Resolution IRN ✅
Computer Vision (CV) Image Super-Resolution RCAN ✅
Computer Vision (CV) Image Super-Resolution sr-ea ✅
Computer Vision (CV) Image Super-Resolution SRGAN ✅
Computer Vision (CV) Image Super-Resolution wdsr ✅
Computer Vision (CV) Image Denoising Neighbor2Neighbor ✅
Computer Vision (CV) Image Generation CGAN ✅
Computer Vision (CV) Image Generation DCGAN ✅
Computer Vision (CV) Image Generation GAN ✅
Computer Vision (CV) Image Generation IPT ✅
Computer Vision (CV) Image Generation pgan ✅
Computer Vision (CV) Image Generation Photo2Cartoon ✅
Computer Vision (CV) Image Generation Pix2Pix ✅
Computer Vision (CV) Image Generation SinGAN ✅
Computer Vision (CV) Image Generation StarGAN ✅
Computer Vision (CV) Image Generation STGAN ✅
Computer Vision (CV) Image Generation WGAN ✅
Computer Vision (CV) Scene Text Detection AdvancedEast ✅
Computer Vision (CV) Scene Text Detection TextFuseNet ✅
Computer Vision (CV) Scene Text Recognition ManiDP ✅
Computer Vision (CV) Semantic Segmentation 3d-cnn ✅
Computer Vision (CV) Semantic Segmentation adelaide_ea ✅
Computer Vision (CV) Semantic Segmentation DDRNet ✅
Computer Vision (CV) Semantic Segmentation E-Net ✅
Computer Vision (CV) Semantic Segmentation Hrnet ✅
Computer Vision (CV) Semantic Segmentation ICNet ✅
Computer Vision (CV) Semantic Segmentation PSPnet ✅
Computer Vision (CV) Semantic Segmentation RefineNet ✅
Computer Vision (CV) Semantic Segmentation Res2net_deeplabv3 ✅
Computer Vision (CV) Semantic Segmentation UNet 3+ ✅
Computer Vision (CV) Semantic Segmentation V-net ✅
Computer Vision (CV) Semantic Segmentation Autodeeplab ✅
Computer Vision (CV) Pose Estimation AlphaPose ✅
Computer Vision (CV) Pose Estimation Hourglass ✅
Computer Vision (CV) Pose Estimation Simple Baseline ✅
Computer Vision (CV) Image Retrieval Delf ✅
Natural Language Processing (NLP) Word Embedding Word2Vec Skip-Gram ✅
Natural Language Processing (NLP) Dialogue Generation DAM ✅
Natural Language Processing (NLP) Machine Translation Seq2Seq ✅
Natural Language Processing (NLP) Emotion Classification Senta ✅
Natural Language Processing (NLP) Emotion Classification Attention LSTM ✅
Natural Language Processing (NLP) Named Entity Recognition LSTM_CRF ✅
Natural Language Processing (NLP) Text Classification HyperText ✅
Natural Language Processing (NLP) Text Classification TextRCNN ✅
Natural Language Processing (NLP) Natural Language Understanding ALBert ✅
Natural Language Processing (NLP) Natural Language Understanding KT-Net ✅
Natural Language Processing (NLP) Natural Language Understanding LUKE ✅
Natural Language Processing (NLP) Natural Language Understanding TPRR ✅
Natural Language Processing (NLP) Knowledge Graph Embedding RotatE ✅
Recommender Recommender System, CTR prediction AutoDis ✅
Recommender Recommender System, CTR prediction DeepFFM ✅
Recommender Recommender System, CTR prediction DIEN ✅
Recommender Recommender System, CTR prediction DLRM ✅
Recommender Recommender System, CTR prediction EDCN ✅
Recommender Recommender System, CTR prediction MMOE ✅
Audio Audio Tagging FCN-4 ✅
Audio Keyword Spotting DS-CNN ✅
Audio Speech Recognition CTCModel ✅
Audio Speech Synthesis Wavenet ✅
GNN Traffic Prediction STGCN ✅
GNN Traffic Prediction TGCN ✅
GNN Social and Information Networks SGCN ✅
GNN Graph Classification DGCN ✅
GNN Graph Classification SDNE ✅
High Performance Computing Molecular Dynamics DeepPotentialH2O ✅
High Performance Computing Ocean Model GOMO ✅
Reinforcement Learning Recommender System, CTR prediction MMOE ✅

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, there are two ways to try to solve this problem. Method 1: You can try to use some smaller batch size; Method 2: Add context.set_context(mempool_block_size="XXGB"), where the current maximum effective value of "XX" can be set to "31". If method 1 and method 2 are used in combination, the effect will be better.
    • 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: What is Some RANK_TBAL_FILE which mentioned in many models?

    A: RANK_TABLE_FILE is the config file of cluster on Ascend while running distributed training. For more information, you could refer to the generator hccl_tools and Parallel Distributed Training Example

  • 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.

  • Q: How to resolve the compile error point to gflags when infer on ascend310 with errors such as undefined reference to 'google::FlagRegisterer::FlagRegisterer'?

    A: Please check the version of GCC and gflags. You can refer to GCC and gflags to install GCC and gflags. You need to ensure that the components used are ABI compatible, for more information, please refer to _GLIBCXX_USE_CXX11_ABI.

  • Q: How to solve the error when loading dataset in mindrecord format on Mac system, such as Invalid file, failed to open files for reading mindrecord files.?

    A: Please check the system limit with ulimit -a, if the number of file descriptors is 256 (default), you need to use ulimit -n 1024 to set it to 1024 (or larger). Then check whether the file is damaged or modified.