search

isl-org / PhotorealismEnhancement

Code & Data for Enhancing Photorealism Enhancement
1.3k stars 106 forks source link

Training config for hr_new (ienet2.py) #42

Closed marcelpuyat closed 2 years ago

marcelpuyat commented 2 years ago

The README says the following:

For the ienet2.py (hr_new in config) we take inspiration from superresolution works: we remove all batch/group normalization and initialize the residual paths such they have a lower initial contribution. Further, we add 2 stages to the HRNet. This further improves final quality as well as training stability.

The training config provided in train.yaml seems to only work for hr (ienet.py) – simply changing hr to hr_new didn't seem to work for me (generated images were really bad). Would you mind submitting the config used that gave the improved final quality and training stability? Thanks!

marcelpuyat commented 2 years ago

Nevermind – these were uploaded as separate yaml files already. Namely: train_pfd2cs_ie2.yaml