Now I'm using tensorflow.keras to implement the FCN-16s,enter image description here

this picture may be different with others, you should focus this it add pool4 to 2x conv7 not 2x pool5 in FCN-16s. Actually the conv7's output_shape is (w/32,h/32,classes_number) in my implementation. I know conv7 should multiply 2 to achieve the same shape (1st,2nd) with pool4. But my question is the pool4's shape is (w/16,h/16,512), ps 512 is the output_channel of the last conv-layer. pool4 and 2x conv7 have not same shape(3rd), how to add?

And another question is what are the train-labels for the FCN, I think a train-label is just a image which has the same width and same height with input_image and has classes_number channel to show each pixel's possibility belong to each class. This idea is derived from the conv7's output_shape, is it right? I hope you can give me more and clear explanations. Thanks!!!

  • 2
    $\begingroup$ You should post implementation questions on either DataScience or StackOverflow. $\endgroup$ – Philip Raeisghasem Apr 3 '19 at 1:04
  • $\begingroup$ emm, I don't think it is a implementation question entirely. The main point is that I hope someone could give me a clear explanation about how to add pool4 to 2x conv7 which have the different 3rd-shape. If I fix up this, the implementation become easy.Thanks! Actually, I have asked some questions about DL on stackoverflow, but someone let me to ask here due to he thinks these questions are related with mathematics. $\endgroup$ – kakaw95 Apr 3 '19 at 1:22

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.