Young-Sun (Andy) Yun

@mrkieumy you should check the tcls value (tcls is target). I am guessing that tcls is empty. It means that there is not assigned target value.

@mrkieumy tcls means class information from ground truth value. if you adopt yolov2, then tcls at region_layer.py is used, else tcls of yolo_layer.py is used. tcls at region_layer.py is compared...

@mrkieumy @PurpleMStone Both you should check config and data files. The codes are well worked on coco and voc dataset.

You should upgrade pytorch > 0.4.1. Or you can change reduction='sum' to size_average=False

It depends your data. After saturation of training steps, it will be small.

@mrkieumy You can refer the same issue at https://github.com/marvis/pytorch-yolo2/issues/89 Here's the reason. https://medium.com/@yvanscher/pytorch-tip-yielding-image-sizes-6a776eb4115b The solution is set the batch_size=1 or in the get_different_scale() you should change the 64 to self.batch_size....

@mickolka yup. set batch_size=1 is recommended for test environment. How many GPUs do you use? I wonder the different image sets are used together.

Hi @mrkieumy Would you change the following 64 to self.batch_size ? 57th line of dataset.py: if index % 64 == 0: --> if index % (self.batch_size * 10) == 0:...

@mrkieumy I don't know what the exact problem is. But, in my opinion, the codes are well working with other people thus I am doubting your dataset and environment. Cheers.

Thanks @mrkieumy I updated codes.