Closed wenouyang closed 7 years ago
You need an encoder-decoder architecture. See: https://blog.keras.io/building-autoencoders-in-keras.html You could use a ResNet for encoder and decoder part.
Closing due to inactivity. Reopen if you have further queries.
Hi, Thanks for sharing the code. I am just curious can this architecture be applied to solve semantic segmentation problem. If possible, which part of your code need to be modified? Thanks.