475ecdfa3d
cast env var args for dataset readers to int
2 years ago
39190f5f44
Remove inplace operators when calculating the loss
...
Remove inplace operators to overcome the following error when using `asymmetric_loss`
```
RuntimeError: one of the variables needed for gradient computation has been modified by an inplace operation
```
2 years ago
6635bc3f7d
Merge pull request #1479 from rwightman/script_cleanup
...
Train / val script enhancements, non-GPU (ie CPU) device support, HF datasets support, TFDS/WDS dataloading improvements
2 years ago
0e6023f032
Merge pull request #1381 from ChristophReich1996/master
...
Fix typo in PositionalEncodingFourier
2 years ago
66f4af7090
Merge remote-tracking branch 'origin/master' into script_cleanup
2 years ago
d3961536c9
comment some debug logs for WDS dataset
2 years ago
e9dccc918c
Rename dataset/parsers -> dataset/readers, create_parser to create_reader, etc
2 years ago
8c28363dc9
Version 0.7.dev0 for master
2 years ago
30bafd7347
🔖 add dev suffix to version tag
2 years ago
f67a7ee8bd
Set num_workers in Iterable WDS/TFDS datasets early so sample estimate is correct
2 years ago
cea8df3d0c
Version 0.6.12
2 years ago
9914f744dc
Add more maxxvit weights includ ConvNeXt conv block based experiments.
2 years ago
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
4f18d6dc5f
Fix logs in WDS parser
2 years ago
8fda68aff6
Fix repo id bug
...
This to fix this issue #1482
2 years ago
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
7327792f39
update to support pickle based dictionaries
2 years ago
1199c5a1a4
clip_laion2b models need 1e-5 eps for LayerNorm
2 years ago
87939e6fab
Refactor device handling in scripts, distributed init to be less 'cuda' centric. More device args passed through where needed.
2 years ago
c88947ad3d
Add initial Hugging Face Datasets parser impl.
2 years ago
e858912e0c
Add brute-force checkpoint remapping option
2 years ago
b293dfa595
Add CL SE module
2 years ago
2a296412be
Add Adan optimizer
2 years ago
5dc4343308
version 0.6.11
2 years ago
a383ef99f5
Make huggingface_hub necessary if it's the only source for a pretrained weight
2 years ago
33e30f8c8b
Remove layer-decay print
2 years ago
e069249a2d
Add hf hub entries for laion2b clip models, add huggingface_hub dependency, update some setup/reqs, torch >= 1.7
2 years ago
9d65557be3
Fix errant import
2 years ago
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
a520da9b49
Update tresnet features_info for v2
2 years ago
c8ab747bf4
BEiT-V2 checkpoints didn't remove 'module' from weights, adapt checkpoint filter
2 years ago
73049dc2aa
Fix type in dla weight update
2 years ago
3599c7e6a4
version 0.6.10
2 years ago
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
fa8c84eede
Update maxvit_tiny_256 weight to better iter, add coatnet / maxvit / maxxvit model defs for future runs
2 years ago
c1b3cea19d
Add maxvit_rmlp_tiny_rw_256 model def and weights w/ 84.2 top-1 @ 256, 84.8 @ 320
2 years ago
914544fc81
Add beitv2 224x224 checkpoints from https://github.com/microsoft/unilm/tree/master/beit2
2 years ago
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
f489f02ad1
Make gcvit window size ratio based to improve resolution changing support #1449 . Change default init to original.
2 years ago
7f1b223c02
Add maxvit_rmlp_nano_rw_256 model def & weights, make window/grid size dynamic wrt img_size by default
2 years ago
e6a4361306
pretrained_cfg entry for mvitv2_small_cls
2 years ago
f66e5f0e35
Fix class token support in MViT-V2, add small_class variant to ensure it's tested. Fix #1443
2 years ago
f1d2160d85
Update a few maxxvit comments, rename PartitionAttention -> PartitionAttenionCl for consistency with other blocks
2 years ago
eca6f0a25c
Fix syntax error (extra dataclass comma) in maxxvit.py
2 years ago
ff6a919cf5
Add --fast-norm arg to benchmark.py, train.py, validate.py
2 years ago
769ab4b98a
Clean up no_grad for trunc normal weight inits
2 years ago
48e1df8b37
Add norm/norm_act header comments
2 years ago
7c2660576d
Tweak init for convnext block using maxxvit/coatnext.
2 years ago
1d8d6f6072
Fix two default args in DenseNet blocks... fix #1427
2 years ago
527f9a4cb2
Updated to correct maxvit_nano weights...
2 years ago
Ross Wightman