[Master Issue] Add more models to torchvision

This is a master issue to track requests for adding new pre-trained models to torchvision.

Here is the (potentially incomplete) list I compiled:

• ResNext https://github.com/pytorch/vision/issues/154 https://github.com/pytorch/vision/issues/543 https://github.com/pytorch/vision/issues/154
• ResNet / ResNext with Group Norm https://github.com/pytorch/vision/issues/631
• mobilenet https://github.com/pytorch/vision/issues/625
• Inception family https://github.com/pytorch/vision/issues/490 https://github.com/pytorch/vision/issues/537
• NasNet https://github.com/pytorch/vision/issues/321 Implemented as MNasNet
• SENet https://github.com/pytorch/vision/issues/260
• ShuffleNet

@Cadene has already implemented a number of those models in his fantastic https://github.com/Cadene/pretrained-models.pytorch . I'll start from there and try to get models trained using pytorch/examples/imagenet, so that the models are reproducible.

Requirements

• python implementation to live in vision/models
• pre-trained weights using the same mean / std normalization as in the imagenet example
• the script used to train the models, or the command-line arguments used if the script was exactly the one from examples/imagenet.