Open
Description
🚀 Feature
Adding new models to the models section.
Motivation
Many new models have been proposed in the recent years and do not exist in the models module.
For example, the EfficientNets appear to provide with 8 models of different complexities that outperform everything else that exists at each complexity level.
Pitch
See Contributing to Torchvision - Models for guidance on adding new models.
- RetinaNet RetinaNet object detection. #1697
- Mobile Net v3 Add MobileNetV3 architecture for Classification #3252
- Mobile Net Backbones Pretrained MobileNet-V2 Backbones for Segmentation Tasks #2700.
- Mobile Net Backbones for Detection Request Mobilenet fpn #1999
- Mobile Net Backbones for Segmenetation Add MobileNetV3 architecture for Segmentation #3276
- Single Shot Multi-Box (SSD) Detector Add SSD512 with ResNet50 backbone #3760 Add SSD architecture with VGG16 backbone #3403
- SSD Lite Add SSDlite architecture with MobileNetV3 backbones #3757
- Efficient Net (b0 to b7) [Feature Request] Add EfficientNet #980
- RegNet RegNet in torchvision ? #2655.
- ViT Adding ViT to torchvision/models #4594
- FCOS add FCOS #4961
- ConvNeXt Adding ConvNeXt architecture in prototype #5197 Adding more ConvNeXt variants + Speed optimizations #5253
- EfficientNetV2 Adding EfficientNetV2 architecture #5450
- Swin Transformer Adding Swin Transformer architecture #5491
- Improved MViT Add MViT architecture in TorchVision #6198
- Swin Transformer V2 - Add SwinV2 in TorchVision #6242 Add SwinV2 #6246
- DeTR Add DETR model #5922
- DINO
- Deformable DeTR
- EfficientDet
- YOLO Hope Yolo model can be added in pretrained models #2074
- Cascade RCNN
- HTC
- CondInst
- SOLO
- DeepLabv3+ With Resnet Add DeepLabV3+ Support #2689
- SE-ResNet and SE-ResNeXt Implementing and training SE-ResNet and SE-ResNeXt and including them in "torchvision.models" #2179
- Inception-ResNet Inception-ResNet #3899 and V2 Can you add the inception-resnetv2？ #5036
- NFNets
- ResNeSt
- ReXNet
- FBNet
- CoAtNet
Add pre-trained weights for the following variants:
- Pretrained weights for ShuffleNetv2 1.5x and 2.0x + the Quantized versions. Add shufflenetv2 1.5 and 2.0 weights #5906 Pre-trained shufflenetv2_x1.5 and shufflenetv2_x2.0 raise "...not supported as of now". #3257
- Pretrained weights for MNasnet 0_75 and 1_3. torchvision.models.mnasnet1_3(pretrained=True) #3722 Add weight for mnasnet0_75 and mnasnet1_3 #6019
- Variant + Pretrained weights for Resnext101_64x4d depth. Adding resnext101 64x4d model #5935 add the pretrained resnext101_64x4d model #3485
- Variant + Pretrained weights for Resnext152_32x4d depth. add the pretrained resnext101_64x4d model #3485