roycemao/dsfd

PyTorch_DSFD复现

dsfd's Issues

When i run the train.py

Could you tell me where the problem is?

Traceback (most recent call last):
File "train.py", line 271, in
train(argments)
File "train.py", line 135, in train
loss = criterion(out, targets)
File "/home/cqupt/.conda/envs/w_py36/lib/python3.6/site-packages/torch/nn/modules/module.py", line 489, in call
result = self.forward(*input, **kwargs)
File "/home/cqupt/.conda/envs/w_py36/DSFD/layers/my_loss.py", line 214, in forward
loss_loc, loss_cls = self.loss_compute(predictions, targets)
File "/home/cqupt/.conda/envs/w_py36/DSFD/layers/my_loss.py", line 190, in loss_compute
p_t_log = - F.cross_entropy(cls_preds_pure, cls_batch[pos_neg_cls], size_average=False)
File "/home/cqupt/.conda/envs/w_py36/lib/python3.6/site-packages/torch/nn/functional.py", line 1970, in cross_entropy
return nll_loss(log_softmax(input, 1), target, weight, None, ignore_index, None, reduction)
File "/home/cqupt/.conda/envs/w_py36/lib/python3.6/site-packages/torch/nn/functional.py", line 1790, in nll_loss
ret = torch._C._nn.nll_loss(input, target, weight, _Reduction.get_enum(reduction), ignore_index)
RuntimeError: Expected object of scalar type Long but got scalar type Float for argument #2 'target'