search

quinngroup / CiliaRepresentation

A modular generative pipeline for understanding cilia appearance and dynamics
MIT License
0 stars 1 forks source link

Exp12: Overfit Test #28

Closed Micky774 closed 4 years ago

Micky774 commented 4 years ago

Try to overfit as best we can with beta = 0 to sanity check whether we have a sufficiently complex network.

Micky774 commented 4 years ago

Currently running a 90 epoch overfit test. Results pending

Micky774 commented 4 years ago

Initial conclusions: brightness had a large effect on quality, as brighter regions tended to be better reconstructed. I believe skip connections may solve this. Normalization of input or layers may also help. Furthermore, a noticed deficiency in the length of the FC layer has been fixed as a result of this overfit test. A new overfit test will be run to confirm the significance of the changes