[Solved] U-net with non-square input images

Hashriama Asks: U-net with non-square input images
I am trying to implement U-net in Python using Keras with my biomedical data. Therefore I am using the following code as an example:

python_for_microscopists/074-Defining U-net in Python using Keras.py at master · bnsreenu/python_for_microscopists

However, my problem is, that my data is non-square and it’s really big: 3736 x 2800.

Does anyone has an idea how to perform U-net on non-square input data. Everytime, when I try to run the code it always says:

ValueError: A Concatenate layer requires inputs with matching shapes except for the concat axis. Got inputs shapes: [(None, 466, 466, 128), (None, 467, 467, 128)]

Ten-tools.com may not be responsible for the answers or solutions given to any question asked by the users. All Answers or responses are user generated answers and we do not have proof of its validity or correctness. Please vote for the answer that helped you in order to help others find out which is the most helpful answer. Questions labeled as solved may be solved or may not be solved depending on the type of question and the date posted for some posts may be scheduled to be deleted periodically. Do not hesitate to share your response here to help other visitors like you. Thank you, Ten-tools.