Error Float in Int64

[pauline-viguier]

Hi, I tried to train Drenet Model with Pytorch version 1.9.0 but I've got this error : Traceback (most recent call last): File "C:\Users\pauli\Documents\Detection_boat\DRENet\DRENet\train.py", line 521, in train(hyp, opt, device, tb_writer, wandb) File "C:\Users\pauli\Documents\Detection_boat\DRENet\DRENet\train.py", line 300, in train loss, loss_items, adaptParams = compute_loss(pred, dgimgs.to(device), targets.to(device)) # loss scaled by batch_size File "C:\Users\pauli\Documents\Detection_boat\DRENet\DRENet\utils\loss.py", line 135, in call tcls, tbox, indices, anchors = self.build_targets(p[0], targets) # targets File "C:\Users\pauli\Documents\Detection_boat\DRENet\DRENet\utils\loss.py", line 256, in build_targets indices.append((b, a, gj.clamp_(0, gain[3] - 1), gi.clamp_(0, gain[2] - 1))) # image, anchor, grid indices RuntimeError: result type Float can't be cast to the desired output type __int64

If someone can help me, thanks !!!

[WindVChen]

Hi @pauline-viguier ,

There seems a discussion about this problem [here]. A direct solution seems to change the version of Pytorch.

Also, you can also have a look at [this blog], which presents how to modify the code to solve the issue.

Hope these help.