value cannot be converted to type int without overflow

[gosling123456]

Traceback (most recent call last): File "train.py", line 216, in main(args) File "train.py", line 154, in main confmat = evaluate(model, val_loader, device=device, num_classes=num_classes) File "/home/ma-user/work/SEG/deep-learning-for-image-processing/pytorch_segmentation/deeplab_v3/train_utils/train_and_eval.py", line 29, in evaluate confmat.update(target.flatten(), output.argmax(1).flatten()) File "/home/ma-user/work/SEG/deep-learning-for-image-processing/pytorch_segmentation/deeplab_v3/train_utils/distributed_utils.py", line 88, in update self.mat += torch.bincount(inds, minlength=n**2).reshape(n, n) RuntimeError: value cannot be converted to type int without overflow