training error

[the-cat-crying]

Traceback (most recent call last):
File "train.py", line 395, in
main()
File "train.py", line 322, in main
train(cfg, train_loader, model, criterion, optimizer, scaler,
File "/home/zhoup/work/download_source_code/yolop/lib/core/function.py", line 77, in train
total_loss, head_losses = criterion(outputs, target, shapes,model)
File "/home/zhoup/anaconda3/envs/yolop/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1130, in call_impl
return forward_call(input, **kwargs)
File "/home/zhoup/work/download_source_code/yolop/lib/core/loss.py", line 50, in forward
total_loss, head_losses = self._forward_impl(head_fields, head_targets, shapes, model)
File "/home/zhoup/work/download_source_code/yolop/lib/core/loss.py", line 70, in _forward_impl
tcls, tbox, indices, anchors = build_targets(cfg, predictions[0], targets[0], model) # targets
File "/home/zhoup/work/download_source_code/yolop/lib/core/postprocess.py", line 79, in build_targets
print(""*10, gj.clamp(0, gain[3] - 1))
RuntimeError: result type Float can't be cast to the desired output type long int

[congwei45]

I meet the same problem！

[realTravisYou]

The version of pytorch should be 1.7.0