RuntimeError:shape does not match when I train Refinedet in both 0.4 branch and master branch

[lc17721825]

Traceback (most recent call last):
File "refinedet_train_test.py", line 448, in
train()
File "refinedet_train_test.py", line 310, in train
arm_loss_l,arm_loss_c = arm_criterion((arm_loc,arm_conf),priors,targets)
File "/home/lc/.local/lib/python2.7/site-packages/torch/nn/modules/module.py", line 491, in call
result = self.forward(*input, **kwargs)
File "/home/lc/git/pytorch_project/PytorchSSD/layers/modules/refine_multibox_loss.py", line 112, in forward
loss_c[pos] = 0 # filter out pos boxes for now
RuntimeError: The shape of the mask [32, 6375] at index 0 does not match the shape of the indexed tensor [204000, 1] at index 0
Exception NameError: "global name 'FileNotFoundError' is not defined" in <bound method _DataLoaderIter.del of <torch.utils.data.dataloader._DataLoaderIter object at 0x7faf15a9bfd0>> ignored

Thanks in advance. @lzx1413

[lc17721825]

I have solved this problem, you can see the solution in ssd.pytorch in github

[foralliance]

@lc17721825
能否给出一个链接

[lc17721825]

amdegroot/ssd.pytorch#173

[lc17721825]

@foralliance

[foralliance]

@lc17721825
thks