Image Colorizer
Section 1
The goal is to colorize black and white pictures of flowers in a realistic way.
The latest version of the code is available on the github page.
The most interesting runs are represented below:
-
baseline made of 5 layers
-
baseline to which the up-sampling layers are replaced with up-convolutions
-
6 layers architecture
-
6 layers architecture with weight decay
Section 2
Surprisingly, replacing the simple up-sampling layers with up-convolutions did not affect the accuracy while increasing model size by about 35%!
It means that the filters do not learn anything more interesting than rudimentary interpolations.
Section 3
I tried to go as deep as possible (hoping it would lead to better final accuracy).
The 7-layer architecture quickly shows some over-fitting. I decided to settle with 6 layers.
Note: the 7-layer architecture starts at a lower loss because the training actually started a few epochs before this log.
Section 4
Using weight decay made the training much slower.
After running tests at different weight decay contribution factors, I decided I didn't have enough time/resources for using it.