Ross Wightman
|
9914f744dc
|
Add more maxxvit weights includ ConvNeXt conv block based experiments.
|
2 years ago |
|
Ross Wightman
|
285771972e
|
Change --amp flags, no more --apex-amp and --native-amp, add --amp-impl to select apex, and --amp-dtype to allow bfloat16 AMP dtype
|
2 years ago |
|
Ross Wightman
|
b1b024dfed
|
Scheduler update, add v2 factory method, support scheduling on updates instead of just epochs. Add LR to summary csv. Add lr_base scaling calculations to train script. Fix #1168
|
2 years ago |
|
Ross Wightman
|
4f18d6dc5f
|
Fix logs in WDS parser
|
2 years ago |
|
nateraw
|
af0c644c5d
|
👷 remove --not_python_module flag
|
2 years ago |
|
nateraw
|
df29d46872
|
♻️ old doc links -> new doc links
|
2 years ago |
|
nateraw
|
8ef9c48cc5
|
👷 use main branch of doc-builder thats fixed now
|
2 years ago |
|
nateraw
|
9343f6e431
|
👷 update ci
|
2 years ago |
|
nateraw
|
5f9eef712c
|
👷 bump ci
|
2 years ago |
|
nateraw
|
09a77700f6
|
👷 bump back. it was actions outage not me
|
2 years ago |
|
nateraw
|
b8e3ffd498
|
👷 revert ci workflow to main
|
2 years ago |
|
nateraw
|
d56f9f7a23
|
🐛 fix link
|
2 years ago |
|
nateraw
|
6153816250
|
🚧 test doc-builder branch to fix build here
|
2 years ago |
|
Ross Wightman
|
145c4d8e46
|
Merge pull request #1483 from MohamedAliRashad/patch-3
Fix repo id bug
|
2 years ago |
|
Mohamed Rashad
|
8fda68aff6
|
Fix repo id bug
This to fix this issue #1482
|
2 years ago |
|
nateraw
|
2f1abc2cf9
|
👷 add build_documentation workflow
|
2 years ago |
|
nateraw
|
3a429d04ee
|
🚑 supply --not_python_module for now
|
2 years ago |
|
nateraw
|
d4d915caf3
|
🚧 update path_to_docs in pr doc builder workflow
|
2 years ago |
|
nateraw
|
96109a909b
|
🚧 update docs path
|
2 years ago |
|
nateraw
|
6c3d02a7e5
|
🚧 update inputs to build_pr_documentation workflow
|
2 years ago |
|
nateraw
|
25059001a9
|
🚧 add repo_owner
|
2 years ago |
|
Ross Wightman
|
b8c8550841
|
Data improvements. Improve train support for in_chans != 3. Add wds dataset support from bits_and_tpu branch w/ fixes and tweaks. TFDS tweaks.
|
2 years ago |
|
Ross Wightman
|
d4ea5c7d7d
|
Merge pull request #1476 from Afafard/class_dict
update to support pickle based dictionaries
|
2 years ago |
|
Alex Fafard
|
7327792f39
|
update to support pickle based dictionaries
|
2 years ago |
|
Ross Wightman
|
1199c5a1a4
|
clip_laion2b models need 1e-5 eps for LayerNorm
|
2 years ago |
|
nateraw
|
e4c99d2bd6
|
📝 add hfdocs documentation
|
2 years ago |
|
Ross Wightman
|
87939e6fab
|
Refactor device handling in scripts, distributed init to be less 'cuda' centric. More device args passed through where needed.
|
2 years ago |
|
Ross Wightman
|
c88947ad3d
|
Add initial Hugging Face Datasets parser impl.
|
2 years ago |
|
Ross Wightman
|
e858912e0c
|
Add brute-force checkpoint remapping option
|
2 years ago |
|
Ross Wightman
|
b293dfa595
|
Add CL SE module
|
2 years ago |
|
Ross Wightman
|
2a296412be
|
Add Adan optimizer
|
2 years ago |
|
Ross Wightman
|
5dc4343308
|
version 0.6.11
|
2 years ago |
|
Ross Wightman
|
a383ef99f5
|
Make huggingface_hub necessary if it's the only source for a pretrained weight
|
2 years ago |
|
Ross Wightman
|
d199f6651d
|
Merge pull request #1467 from rwightman/clip_laion2b
Adding support for fine-tune CLIP LAION-2B image tower weights for B/32, L/14, H/14, and g/14.
|
2 years ago |
|
Ross Wightman
|
33e30f8c8b
|
Remove layer-decay print
|
2 years ago |
|
Ross Wightman
|
e069249a2d
|
Add hf hub entries for laion2b clip models, add huggingface_hub dependency, update some setup/reqs, torch >= 1.7
|
2 years ago |
|
Ross Wightman
|
9d65557be3
|
Fix errant import
|
2 years ago |
|
Ross Wightman
|
9709dbaaa9
|
Adding support for fine-tune CLIP LAION-2B image tower weights for B/32, L/14, H/14 and g/14. Still WIP
|
2 years ago |
|
Ross Wightman
|
a520da9b49
|
Update tresnet features_info for v2
|
2 years ago |
|
Ross Wightman
|
c8ab747bf4
|
BEiT-V2 checkpoints didn't remove 'module' from weights, adapt checkpoint filter
|
2 years ago |
|
Ross Wightman
|
73049dc2aa
|
Fix type in dla weight update
|
2 years ago |
|
Ross Wightman
|
3599c7e6a4
|
version 0.6.10
|
2 years ago |
|
Ross Wightman
|
e11efa872d
|
Update a bunch of weights with external links to timm release assets. Fixes issue with *aliyuncs.com returning forbidden. Did pickle scan / verify and re-hash. Add TresNet-V2-L weights.
|
2 years ago |
|
Ross Wightman
|
fa8c84eede
|
Update maxvit_tiny_256 weight to better iter, add coatnet / maxvit / maxxvit model defs for future runs
|
2 years ago |
|
Ross Wightman
|
de40f66536
|
Update README.md
|
2 years ago |
|
Ross Wightman
|
c1b3cea19d
|
Add maxvit_rmlp_tiny_rw_256 model def and weights w/ 84.2 top-1 @ 256, 84.8 @ 320
|
2 years ago |
|
Ross Wightman
|
da6f8f5a40
|
Fix beitv2 tests
|
2 years ago |
|
Ross Wightman
|
914544fc81
|
Add beitv2 224x224 checkpoints from https://github.com/microsoft/unilm/tree/master/beit2
|
2 years ago |
|
Ross Wightman
|
dc90816f26
|
Add `maxvit_tiny_rw_224` weights 83.5 @ 224 and `maxvit_rmlp_pico_rw_256` relpos weights, 80.5 @ 256, 81.3 @ 320
|
2 years ago |
|
Ross Wightman
|
f489f02ad1
|
Make gcvit window size ratio based to improve resolution changing support #1449. Change default init to original.
|
2 years ago |
