FCN in TensorFlow missing crop layer

Question

I am currently trying to implement FCN for semantic segmentation in TensorFlow as it was previously done in Caffe here.

Unfortunately I\'m struggling with following 3 th

Answer 1

I found the way for solving arbitrary size image in tensorflow, by implementing crop layer. Now it can be used any size of image you want, when just single image is passed. More about my solution is here: https://stackoverflow.com/a/45632285/3134418

Answer 2

Thanks to the advice from @24hours I have found answer to all the 3 questions. Unfortunately FCN of arbitrary size in tensorflow is a bit more complicated than in caffe, but hopefully I'll solve that soon as well.

1) tf.nn.conv2d_transpose can be used.

2) Crop layer is not needed, output_size of the tf.nn.conv2d_transpose layer can be used instead.

3) At the end I have used tf.nn.sparse_softmax_cross_entropy_with_logits