DL-Art-School/codes
James Betker bc20b4739e vqvae3
Changes VQVAE as so:
- Reverts back to smaller codebook
- Adds an additional conv layer at the highest resolution for both the encoder & decoder
- Uses LeakyReLU on trunk
2021-01-29 15:24:26 -07:00
..
.idea IDEA update 2020-05-19 09:35:26 -06:00
data Support training imagenet classifier 2021-01-11 20:09:16 -07:00
models vqvae3 2021-01-29 15:24:26 -07:00
scripts test uresnet playground mods 2021-01-23 13:46:43 -07:00
trainer Add SrPixLoss, which focuses pixel-based losses on high-frequency regions 2021-01-25 08:26:14 -07:00
utils update vqvae to double codebook size for bottom quantizer 2021-01-23 13:47:07 -07:00
multi_modal_train.py More adjustments to support distributed training with teco & on multi_modal_train 2020-10-27 20:58:03 -06:00
process_video.py misc 2021-01-23 13:45:17 -07:00
requirements.txt Support training imagenet classifier 2021-01-11 20:09:16 -07:00
test_image_patch_classifier.py More refactoring 2020-12-18 09:18:34 -07:00
test.py misc 2021-01-23 13:45:17 -07:00
train.py Add switched_conv with hard routing and make vqvae use it. 2021-01-25 08:25:29 -07:00
train2.py resnet_unet_3 2021-01-15 14:51:03 -07:00