【Demo】RuntimeError: Sizes of tensors must match except in dimension 2. Got 1024 and 8192 (The offending index is 0)

[fudanvi]

【Demo】RuntimeError: Sizes of tensors must match except in dimension 2. Got 1024 and 8192 (The offending index is 0)

[JingyeChen]

I have tested this command in my environment but did not encounter this problem.

Firstly you need to create a folder named 'demo', then put some pictures in it.
The format should be 'name.png'

I wish this answer could address your confusion :)

[JingyeChen]

运行速度很快的， 你可以检查一下程序卡在什么地方了

[JingyeChen]

读取方式详见
scene-text-telescope/dataset/dataset.py 里的若干lmdb Class

[Lz-2019317]

好啦，这个问题解决了。可是我没有找到输出的图片，运行demo时也有event,out文件。可是这个tensorboard显示No image data was found.。合成的图片会在哪里显示呀？

[JingyeChen]

你可以查看训练时的event文件

[Lz-2019317]

deom可以单独显示吗

[JingyeChen]

event文件用于记录训练过程中各种参数的变化，因此train过程生成的event才有内容的

[kanika02]

好啦，这个问题解决了。可是我没有找到输出的图片，运行demo时也有event,out文件。可是这个tensorboard显示No image data was found.。合成的图片会在哪里显示呀？

How the problem Sizes of tensors must match except in dimension 2. Got 1024 and 8192 (The offending index is 0) is solved? Can you help me with that? I am having the same issue

[523997931]

I also have the same issue, how to deal with it

[JingyeChen]

The bug has been fixed in the latest commit. You can have a try.

[523997931]

The bug has been fixed in the latest commit. You can have a try.

thanks for fixing it, but another issue occur,

File "/workspace/scene-text-telescope/model/tbsrn.py", line 119, in forward
for l, x in zip(self.linears, (query, key, value))]
File "/workspace/scene-text-telescope/model/tbsrn.py", line 119, in
for l, x in zip(self.linears, (query, key, value))]
File "/opt/conda/lib/python3.7/site-packages/torch/nn/modules/module.py", line 722, in _call_impl
result = self.forward(*input, **kwargs)
File "/opt/conda/lib/python3.7/site-packages/torch/nn/modules/linear.py", line 91, in forward
return F.linear(input, self.weight, self.bias)
File "/opt/conda/lib/python3.7/site-packages/torch/nn/functional.py", line 1676, in linear
output = input.matmul(weight.t())
RuntimeError: mat1 dim 1 must match mat2 dim 0

[JingyeChen]

what is the command? I did not encounter this problem