zbf1991

Also waiting for the code. Thanks

@hardBird123 I have one question, when you get the same IOU of cams and AffinityNet, you just use the provided weights by author or you train your own weights? when...

@hardBird123 Not yet. But I would not try cause it is enough for my research

@jbeomlee93 The result of the first part is the mIoU under the different thresholds (Line 116-117 in run_sample_coco.py), which is not the result of each class. Thanks a lot!

Please prepare the *.npy file to encode your class as a one-hot encoding (you can find a *.npy file in this project). Then prepare your train.txt like the "train_aug.txt" in...

I think it is correct.

@j-min I have the same bugs with you, have you solved?