Hu Ye

@ain-soph Thanks for you good PR. I have two advice: - we should fix the problem in https://github.com/pytorch/vision/pull/6222 ( for input size=256 window size=8, it works well, but for input...

> @xiaohu2015 I'll take a look at the problem you mentioned here, and add the `pretrained_window_size` as the argument (it's zero for all variants though). And I think it should...

I am aming at adding FCOS to torchvision. https://github.com/xiaohu2015/vision/blob/main/torchvision/models/detection/fcos.py

@datumbox Yes, I am working to implement it and reproduce the peformance. But I think that some time is need.

@datumbox @fmassa Hi, we have pulled the FCOS code (https://github.com/pytorch/vision/pull/4961), Could you review it and give some advice?

Another CNN: https://github.com/facebookresearch/deit/blob/main/patchconvnet_models.py

> Hi there, > > I'm doing few-shot classification and similarity learning, and currently [dino deit backbone](https://github.com/facebookresearch/dino) is a top-performing one on my datasets. Can we add it to `torchvision.models`?...

I want to add another object detection model: ATSS.

maybe I can implement some features, eg DropBlock layer.

I think prototype API is wonderful design. Now that you add the data transform of `eval mode` in the weights, is it possble to include the data transform of `train...