使用默认的进行训练，有个报错
File "train.py", line 527, in main
train(opt.hyp, opt, device, callbacks)
File "train.py", line 324, in train
loss, loss_items = compute_loss(pred, targets.to(device)) # loss scaled by batch_size
tph-yolov5/utils/loss.py", line 243, in buildtargets
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 long int
zhongranHerz
commented
2 years ago
使用默认的进行训练，有个报错 File "train.py", line 527, in main train(opt.hyp, opt, device, callbacks) File "train.py", line 324, in train loss, loss_items = compute_loss(pred, targets.to(device)) # loss scaled by batch_size tph-yolov5/utils/loss.py", line 243, in buildtargets 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 long int