Nevermore

Hi, it seems that there is no top-down path for NAS-FPN (https://github.com/tensorflow/tpu/blob/master/models/official/detection/modeling/architecture/nasfpn.py) in the official implement? I am not sure about this. 这里的实现是把NAS-FPN接在top-down之后的feature map上么？官方代码好像是没有top-down那步？我自己在pytorch上的实现发现没有top-down的话NAS-FPN会掉点，不知道是不是我哪理解错了？

Hi, thanks for your code. I try to implement NAS-FPN in pytorch, but there seems to be some errors with my BN layer (Both 1-stage(RetinaNeet) / 2-stage). I freeze the...

It seems that the channels in branch_main and branch_proj should be out_channel // 2, but you use the inp here. https://github.com/ouyanghuiyu/Thundernet_Pytorch/blob/master/lib/model/faster_rcnn/modules.py#L289

The code [here](https://github.com/Atten4Vis/DemystifyLocalViT/blob/master/models/dwnet.py#L73) should be elif?

Question about the uploaded pretrained checkpoint

2

Thanks for your good work! I try to use your pretrained model in train_cls.py, however, when I load the checkpoint and get a low Acc during validation, is there something...