RuntimeError: output size is error

[gjy3035]

I try to train the model, but the output size is error:

RuntimeError: input and target batch or spatial sizes don't match: target [4 x 512 x 1024], input [4 x 20 x 1534 x 3070] at /pytorch/torch/lib/THCUNN/generic/SpatialClassNLLCriterion.cu:24

[4 x 512 x 1024] is the size of label.
[4 x 20 x 1534 x 3070] is the size of model output.

How to solve it?

[gjy3035]

Through comparing with original lua code, I maybe find the reason of inconsistent sizes.
In model.py, Line 34:

self.Convolution = nn.ConvTranspose2d

should be:

self.Convolution = nn.Conv2d