Learning-to-See-in-the-Dark upsample_and_cancat(x1,x2,output_channels,input_channels) does not contant the Crop operation

upsample_and_cancat(x1,x2,output_channels,input_channels) does not contant the Crop operation

Open zhanglijian opened this issue 6 years ago • 2 comments

@cchen156 Do you have the "Croplayer" crop operation in this fuctions, It only have 'DECONVOLUTION' ans 'CONCAT'，

Jul 19 '18 07:07 zhanglijian

I do not understand your question.

Jul 20 '18 17:07 cchen156

The crop operation does not work during the model. The crop operation work before the training. Every training iteration, the origin point randomly selected and the crop image is generated with certain patch size(e.g. 512 in the paper) to feed into the model.

Aug 07 '18 09:08 oneTaken

Learning-to-See-in-the-Dark Learning-to-See-in-the-Dark copied to clipboard

upsample_and_cancat(x1,x2,output_channels,input_channels) does not contant the Crop operation

Learning-to-See-in-the-Dark
Learning-to-See-in-the-Dark copied to clipboard