Ross Wightman
02b806e00a
Add PyTorch 1.11 train benchmark numbers
3 years ago
Ross Wightman
c9f208f7f8
Update eval results and add latest PyTorch 1.11 inference benchmarks
3 years ago
Ross Wightman
1ba0ec4c18
Merge remote-tracking branch 'origin/master' into bits_and_tpu
3 years ago
Ross Wightman
f670d98cb8
Make a few more layers symbolically traceable (remove from FX leaf modules)
...
* remove dtype kwarg from .to() calls in EvoNorm as it messed up script + trace combo
* BatchNormAct2d always uses custom forward (cut & paste from original) instead of super().forward. Fixes #1176
* BlurPool groups==channels, no need to use input.dim[1]
3 years ago
Ross Wightman
a9ecb880e5
Merge pull request #1190 from seefun/ConvNeXt-pretrain
...
Add ConvNeXt tiny and small pretrain in22k
3 years ago
SeeFun
5f4de2334b
Merge pull request #1 from seefun/ConvNeXt-pretrain
...
Add ConvNeXt tiny and small pretrain in22k
3 years ago
SeeFun
ec4e9aa5a0
Add ConvNeXt tiny and small pretrain in22k
...
Add ConvNeXt tiny and small pretrain in22k from ConvNeXt repo:
06f7b05f92
3 years ago
Ross Wightman
73ffade1f8
Update README.md
3 years ago
Ross Wightman
575924ed60
Update test crop for new RegNet-V weights to match Y
3 years ago
Ross Wightman
8f6d638887
Update README.md
3 years ago
Ross Wightman
1618527098
Add layer scale and parallel blocks to vision_transformer
3 years ago
Ross Wightman
c42be74621
Add attrib / comments about Swin-S3 (AutoFormerV2) weights
3 years ago
Ross Wightman
474ac906a2
Add 'head norm first' convnext_tiny_hnf weights
3 years ago
Ross Wightman
dc51334cdc
Fix pruned adapt for EfficientNet models that are now using BatchNormAct layers
3 years ago
Ross Wightman
024fc4d9ab
version 0.6.1 for master
3 years ago
Ross Wightman
e1e037ba52
Fix bad tuple typing fix that was on XLA branch bust missed on master merge
3 years ago
Ross Wightman
341b464a5a
Remove redundant noise attr from Plateau scheduler (use parent)
3 years ago
Ross Wightman
7514439573
Merge pull request #1014 from rwightman/norm_norm_norm
...
Normalization layer additions, model API updates, new models, new weights, and enhancements
3 years ago
Ross Wightman
749856cf25
Merge remote-tracking branch 'origin/norm_norm_norm' into bits_and_tpu
3 years ago
Ross Wightman
ff21fdb41d
Update README.md ready for merge
3 years ago
Ross Wightman
fe457c1996
Update SwinTransformerV2Cr post-merge, update with grad checkpointing / grad matcher
...
* weight compat break, activate norm3 for final block of final stage (equivalent to pre-head norm, but while still in BLC shape)
* remove fold/unfold for TPU compat, add commented out roll code for TPU
* add option for end of stage norm in all stages
* allow weight_init to be selected between pytorch default inits and xavier / moco style vit variant
3 years ago
Ross Wightman
b049a5c5c6
Merge remote-tracking branch 'origin/master' into norm_norm_norm
3 years ago
Ross Wightman
7cdd164d77
Fix #1184 , scheduler noise bug during merge madness
3 years ago
Ross Wightman
9440a50c95
Merge branch 'mrT23-master'
3 years ago
Ross Wightman
d98aa47d12
Revert ml-decoder changes to model factory and train script
3 years ago
Ross Wightman
04db5833eb
Merge pull request #986 from hankyul2/master
...
fix: typo of argment parser desc in train.py
3 years ago
Ross Wightman
b20665d379
Merge pull request #1007 from qwertyforce/patch-1
...
update arxiv link
3 years ago
Ross Wightman
d66b4c2355
Merge pull request #801 from developer0hye/patch-1
...
fix a typo in ### Select specific feature levels or limit the stride
3 years ago
Ross Wightman
7a0994f581
Merge pull request #1150 from ChristophReich1996/master
...
Swin Transformer V2
3 years ago
Ross Wightman
d757fecaac
Merge pull request #1112 from ayasyrev/sched_noise_dup_code
...
sched noise dup code remove
3 years ago
Ross Wightman
61d3493f87
Fix hf-hub handling when hf-hub is config source
3 years ago
Ross Wightman
5f47518f27
Fix pit implementation to be clsoer to deit/levit re distillation head handling
3 years ago
Ross Wightman
0862e6ebae
Fix correctness of some group matching regex (no impact on result), some formatting, missed forward_head for resnet
3 years ago
Ross Wightman
94bcdebd73
Add latest weights trained on TPU-v3 VM instances
3 years ago
Ross Wightman
95739b45d7
Fix partially removed alt_lable impl from TFDS variant of ImageNet22/12k
3 years ago
Ross Wightman
5e1be34a60
Add ImageNet-22k/12k TFDS dataset defs
3 years ago
Ross Wightman
59ffab537c
Fix mistake in wds sample slicing
3 years ago
Ross Wightman
ef57561d51
Fix some TPU (XLA) issues with swin transformer v2
3 years ago
Ross Wightman
ab16a358bb
Add log and continue handler for WDS errors, fix args.num_gpu for validation script fallback
3 years ago
Ross Wightman
7eeaf521a0
use gopen in wds to open info file in case it's at a url/gs location
3 years ago
Ross Wightman
229ac6b8d8
Fix alternate label handling in WDS parser to skip invalid alt labels
3 years ago
Ross Wightman
a444d4b891
Add alternative label support to WDS for imagenet22k/12k split, add 21k/22k/12k indices filters to results/
3 years ago
Ross Wightman
da2796ae82
Add webdataset (WDS) support, update TFDS to make some naming in parsers more similar. Fix workers=0 compatibility. Add ImageNet22k/12k synset defs.
3 years ago
Ross Wightman
3fce010ca8
Merge remote-tracking branch 'origin/norm_norm_norm' into bits_and_tpu
3 years ago
Ross Wightman
0557c8257d
Fix bug introduced in non layer_decay weight_decay application. Remove debug print, fix arg desc.
3 years ago
Ross Wightman
15cc9eae3e
Fix Swin v2 tuple type hint
3 years ago
Ross Wightman
bb85b09d2a
swin v2 fixup for latest changes on norm_norm_norm / bits_and_tpu branch
3 years ago
Ross Wightman
10fa42b143
Merge branch 'ChristophReich1996-master' into bits_and_tpu
3 years ago
Ross Wightman
c639a86c67
Change TFDS default to full re-shuffle (init) each epoch (for now)
3 years ago
Ross Wightman
a16ea1e355
Merge remote-tracking branch 'origin/norm_norm_norm' into bits_and_tpu
3 years ago