Vision: Are new models planned to be added?

[talcs]

🚀 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

Adding the EfficientNets, MobileNet-v3, SE-ResNet and SE-ResNeXt.

Alternatives

Additional context

[oke-aditya]

This request has come often. Just linking all those for reference.

• [ ] RegNet #2655.
• [x] RetinaNet #1697 (this model is coming)
• [ ] DeepLabv3+ With Resnet #2689 (hopefully comes in). Also, this had a discussion about Xception.
• [ ] Efficient Net request #980
• [x] Mobile Net v3 #3252
• [ ] SE-ResNet and SE-ResNeXt #2179
• [ ] Mobile Net Backbones #2700.
• [x] Mobile Net Backbones for Detection #1999
• [ ] Pretrained weights for ShuffleNetv2 1.5x and 2.0x depth. #3257

A generalized guideline for adding models is being added in contributing.md file in this pr #2663.

[fmassa]

Hi,

To complement @oke-aditya great answer, we will be adding more models to torchvision, including Efficient Nets and MobileNetV3.

The current limitation is that we would like to ensure that we can reproduce the pretrained model using the training scripts from references/classification, but those models require a different training recipe than then one present in [references/classification`](https://github.com/pytorch/vision/tree/master/references/classification), so we will need to update those recipes before uploading those new models.

[songyuc]

I hope to add Mish activation function.

[digantamisra98]

@songyuc There is a closed feature request on PyTorch for adding Mish. You can comment over there for increased visibility so that Mish can be considered to be added in the future. Link to the issue - https://github.com/pytorch/pytorch/issues/25584