Open shkarupa-alex opened 3 years ago
As far as i understand, here https://github.com/MarcoForte/FBA_Matting/blob/master/networks/models.py#L230 resnet backbone will return such feature maps: [original_image, conv_bn_relu out, layer1 out, layer2 out, layer3 out, layer4 out]
In the decoder https://github.com/MarcoForte/FBA_Matting/blob/master/networks/models.py#L350 you concatenate: (x, conv_out[-6][:, :3], img, two_chan_trimap).
But conv_out[-6][:, :3] is the same as img. Are you sure that image should be concatenated twice?
Possibly the same issue https://github.com/MarcoForte/FBA_Matting/issues/49#issuecomment-1027875080
As far as i understand, here https://github.com/MarcoForte/FBA_Matting/blob/master/networks/models.py#L230 resnet backbone will return such feature maps: [original_image, conv_bn_relu out, layer1 out, layer2 out, layer3 out, layer4 out]
In the decoder https://github.com/MarcoForte/FBA_Matting/blob/master/networks/models.py#L350 you concatenate: (x, conv_out[-6][:, :3], img, two_chan_trimap).
But conv_out[-6][:, :3] is the same as img. Are you sure that image should be concatenated twice?