Aditya Oke

Hello @SamihaSara ! Thank you for brining this question! The FasterRCNN used here is from [torchvision](https://github.com/pytorch/vision/). You can find FasterRCNN code [here](https://github.com/pytorch/vision/blob/master/torchvision/models/detection/faster_rcnn.py) ! Bounding Box regression: - It is step...

True, but that reduces codebase significantly to maintain. I would love a custom implementation though, it would need some testing and weights etc.

Just saw your implementation. That's great. Really nice and so complete.

That's absoltely fine!. Just one small doubt. Will using `GeneralizedRCNNTransform` detoriate the results ? P.S> I'm not super expert in these models or scratch implementing them.

I will try once locally by using `torch.hub` without opencv dependency and try to produce a training script, which we can use. There are few problems which I forsee while...

Though `GeneralizedRCNNTransform` worked actually fine while torchvision adopted RetinaNet, there seemed to be no issue that time. I'm not sure how super flexible it is.

Sure, I will share a Colab so that we can dig into their implementation. This will enable us to compare ours as well later !

Just a doubt. FRCNN and RetinaNet are not differentiable in `eval` model. E.g. ``` model = FRCNN() model.eval() opt = Adam(lr=1e-3, model.parameters()) opt.step() ``` Will not work. But it will...

No Thumb rule here. For Detr, I seperated out the `PostProcess` as I think it is something optional and leave it to best of users. That's what Detr too did...

Both `loss_dict` and `detections` is fine too, but currently torchvision models don't do that. This is acutally good idea, as users can slowly track how the detection is improving with...