1. 26 Aug, 2021 1 commit
    • Vasilis Vryniotis's avatar
      Add EfficientNet Architecture in TorchVision (#4293) · 37a9ee5b
      Vasilis Vryniotis authored
      * Adding code skeleton
      
      * Adding MBConvConfig.
      
      * Extend SqueezeExcitation to support custom min_value and activation.
      
      * Implement MBConv.
      
      * Replace stochastic_depth with operator.
      
      * Adding the rest of the EfficientNet implementation
      
      * Update torchvision/models/efficientnet.py
      
      * Replacing 1st activation of SE with SiLU.
      
      * Adding efficientnet_b3.
      
      * Replace mobilenetv3 assets with custom.
      
      * Switch to standard sigmoid and reconfiguring BN.
      
      * Reconfiguration of efficientnet.
      
      * Add repr
      
      * Add weights.
      
      * Update weights.
      
      * Adding B5-B7 weights.
      
      * Update docs and hubconf.
      
      * Fix doc link.
      
      * Fix typo on comment.
      37a9ee5b
  2. 27 Jan, 2021 1 commit
    • Vasilis Vryniotis's avatar
      Add MobileNetV3 architecture for Segmentation (#3276) · e2db2edd
      Vasilis Vryniotis authored
      * Making _segm_resnet() generic and reusable.
      
      * Adding fcn and deeplabv3 directly on mobilenetv3 backbone.
      
      * Adding tests for segmentation models.
      
      * Rename is_strided with _is_cn.
      
      * Add dilation support on MobileNetV3 for Segmentation.
      
      * Add Lite R-ASPP with MobileNetV3 backbone.
      
      * Add pretrained model weights.
      
      * Removing model fcn_mobilenet_v3_large.
      
      * Adding docs and imports.
      
      * Fixing typo and readme.
      e2db2edd
  3. 14 Jan, 2021 1 commit
    • Vasilis Vryniotis's avatar
      Add MobileNetV3 architecture for Classification (#3252) · 7bf6e7b1
      Vasilis Vryniotis authored
      * Add MobileNetV3 Architecture in TorchVision (#3182)
      
      * Adding implementation of network architecture
      
      * Adding rmsprop support on the train.py
      
      * Adding auto-augment and random-erase in the training scripts.
      
      * Adding support for reduced tail on MobileNetV3.
      
      * Tagging blocks with comments.
      
      * Adding documentation, pre-trained model URL and a minor refactoring.
      
      * Handling better untrained supported models.
      7bf6e7b1
  4. 11 May, 2020 1 commit
  5. 26 Jun, 2019 1 commit
    • Sergey Zagoruyko's avatar
      Add pretrained Wide ResNet (#912) · 2b6da28c
      Sergey Zagoruyko authored
      * add wide resnet
      
      * add docstring for wide resnet
      
      * update WRN-50-2 model
      
      * add docs
      
      * extend WRN docstring
      
      * use pytorch storage for WRN
      
      * fix rebase
      
      * fix typo in docs
      2b6da28c
  6. 31 May, 2019 1 commit
  7. 16 Apr, 2019 1 commit
  8. 26 Oct, 2018 1 commit
    • Ailing's avatar
      Hub (#639) · c7e9bd30
      Ailing authored
      * init hub.py
      
      * rename hub.py -> hub_info.py
      
      * torchvision_hub->torchvision; use alexnet as example since it's smaller
      
      * alexnet -> resnet18
      
      * update repo example structure
      
      * address comment
      
      * add readme as comment
      
      * address comment
      
      * fix lint
      c7e9bd30