Training problem

[longjia1996]

Traceback (most recent call last): File "train.py", line 141, in Train() File "train.py", line 27, in init self._train() File "train.py", line 40, in _train self._train_epoch(i_epoch) File "train.py", line 69, in _train_epoch self._model.optimize_parameters(keep_data_for_visuals=do_visuals, train_generator=train_generator) File "/home/longjia/GANimation-master/models/ganimation.py", line 207, in optimize_parameters loss_D, fake_imgs_masked = self._forward_D() File "/home/longjia/GANimation-master/models/ganimation.py", line 273, in _forward_D fake_imgs, fake_img_mask = self._G.forward(self._real_img, self._desired_cond) File "/home/longjia/GANimation-master/networks/generator_wasserstein_gan.py", line 51, in forward c = c.expand(c.size(0), c.size(1), x.size(2), x.size(3)) RuntimeError: expand(torch.cuda.FloatTensor{[1, 0, 1, 1, 37]}, size=[1, 0, 128, 128]): the number of sizes provided (4) must be greater or equal to the number of dimensions in the tensor (5)

[xrtbuaa]

@longjia1996 I have meet this before , maybe you can check the format of AU that you provide

[shartoo]

batch size should be 25?

[tjzjp]

I met the same problem, have you solved it?

[czwbbbbb]

我以前遇到过这个，也许你可以检查一下你提供的AU格式

hello！I also encountered this problem, I want to ask how this is solved, thank you for your help, that is, this c is 0 channel, can not do concat