James Betker 10f7e49214 Add ConvBnSilu to replace ConvBnRelu ... Relu produced good performance gains over LeakyRelu, but GAN performance degraded significantly. Try SiLU as an alternative to see if it's the leaky-ness we are looking for or the smooth activation curvature.		2020-07-05 13:39:08 -06:00
..
archs	Add ConvBnSilu to replace ConvBnRelu	2020-07-05 13:39:08 -06:00
__init__.py	Implement downsample GAN	2020-04-24 00:00:46 -06:00
base_model.py	Fix inverse temperature curve logic and add upsample factor	2020-06-19 09:18:30 -06:00
loss.py	mmsr	2019-08-23 21:42:47 +08:00
lr_scheduler.py	Enable forced learning rates	2020-06-07 16:56:05 -06:00
networks.py	Break out SRG1 as separate network	2020-07-04 13:28:50 -06:00
SR_model.py	Allow validating in batches, remove val size limit	2020-06-02 08:41:22 -06:00
SRGAN_model.py	Add a feature-based validation test	2020-07-03 15:18:57 -06:00