runtime error when running toy example

[luo-yuanfu]

Traceback (most recent call last):
File "train.py", line 614, in
test(128, write_to_file=wr_dir, just_one=True)
File "train.py", line 533, in test
pred_hat_4d = predict(obsv, noise, n_next)
File "train.py", line 374, in predict
new_v = decoder(encoder.lstm_h[0].view(bs, -1), weighted_features, noise).view(bs, 2)
File "/home/yuanfu/workspace/socialways/env/lib/python3.5/site-packages/torch/nn/modules/module.py", line 491, in call
result = self.forward(*input, **kwargs)
File "train.py", line 290, in forward
inp = torch.cat([h, s, z], dim=1)
RuntimeError: invalid argument 0: Tensors must have same number of dimensions: got 2 and 1 at /pytorch/aten/src/THC/generic/THCTensorMath.cu:102

[amiryanj]

I dont encounter such problem.
Can you put a breakpoint at line 290 and tell me the size of tensors: h , s & z ?
They should be 128x64, 128x64 and 128x32 respectively.

[Dear-zhangliyuan]

Traceback (most recent call last):
File "train.py", line 614, in
test(128, write_to_file=wr_dir, just_one=True)
File "train.py", line 533, in test
pred_hat_4d = predict(obsv, noise, n_next)
File "train.py", line 374, in predict
new_v = decoder(encoder.lstm_h[0].view(bs, -1), weighted_features, noise).view(bs, 2)
File "/home/yuanfu/workspace/socialways/env/lib/python3.5/site-packages/torch/nn/modules/module.py", line 491, in call
result = self.forward(*input, **kwargs)
File "train.py", line 290, in forward
inp = torch.cat([h, s, z], dim=1)
RuntimeError: invalid argument 0: Tensors must have same number of dimensions: got 2 and 1 at /pytorch/aten/src/THC/generic/THCTensorMath.cu:102

Excuse me，I encounter the same problem when I use the seq_hotel dataset. Have you solved this problem, please?

[amiryanj]

@Dear-zhangliyuan
Hi Liyuan,
thanks for reporting this issue,
I found out this bug was due to some special case in the dataset,
anyway I fixed it, and now you should be able to train on hotel dataset.
80c0209

[Dear-zhangliyuan]

@Dear-zhangliyuan
Hi Liyuan,
thanks for reporting this issue,
I found out this bug was due to some special case in the dataset,
anyway I fixed it, and now you should be able to train on hotel dataset.
80c0209

Yes, it is really work now. You are so great! ! Thanks very much!!

[Dear-zhangliyuan]

hello javad,
I used the hotel dataset to train yesterday, it can work. But I run the visualize.py today, I found it can't work normally. And the zara01 dataset can't also visualize. Besides，When I train use the zara02, it has a huge loss. I hope that you can help me debug it if you are convenient.
Thanks!