BigDong

> > I wonder whether this code has not provided the code of the visualization program, using the TFA trained model for test? I have reproduced TFA and trained the...

LGTM

> if i set pretrained = 'open-mmlab://detectron2/resnet50_caffe' in configs/detection/base/models/faster_rcnn_r50_caffe_c4.py, the log print "unexpected key in source state_dict: conv1.weight, ......" More details are needed, for example your logging file. > if...

What config did you use? `configs/detection/base/models/faster_rcnn_r50_caffe_c4.py` is not the whole config file. I haven't met this error in MMDet before

Thanks for your reply, this error will fix ASAP. Also, PR is welcome to fix this error

You can try to just discard your old files, create a new folder, and start everything from scratch.

This maybe because of the random in PyTorch or CUDA ops, maybe you can try to set deterministic=True

@Nioolek Thanks for your contribution, Please remember to sign the CLA first. 

Kindly ping @HAOCHENYE have a look, maybe we can add `ignore_key` in ConcatDataset to avoid this error

@christian-hiebl Thanks for your contribution. I think maybe we can set `keep` out of the conditions. Such as: ```python if self.by_box: assert 'gt_bboxes' in results gt_bboxes = results['gt_bboxes'] instance_num =...