2f2b22d8c7
Disable nvfuser fma / opt level overrides per #1244
2022-05-13 09:27:13 -07:00
c0211b0bf7
Swin-V2 test fixes, typo
2022-05-12 22:31:55 -07:00
9a86b900fa
Official SwinV2 models
2022-05-12 15:05:10 -07:00
d07d015173
Merge pull request #1249 from okojoalg/sequencer
...
Add Sequencer
2022-05-09 20:42:43 -07:00
d30685c283
Merge pull request #1251 from hankyul2/fix-multistep-scheduler
...
fix: multistep lr decay epoch bugs
2022-05-09 16:07:46 -07:00
a16171335b
fix: change milestones to decay-milestones
...
- change argparser option `milestone` to `decay-milestone`
2022-05-10 07:57:19 +09:00
39b725e1c9
Fix tests for rank-4 output where feature channels dim is -1 (3) and not 1
2022-05-09 15:20:24 -07:00
78a32655fa
Fix poolformer group_matcher to merge proj downsample with previous block, support coarse
2022-05-09 12:20:04 -07:00
d79f3d9d1e
Fix torchscript use for sequencer, add group_matcher, forward_head support, minor formatting
2022-05-09 12:09:39 -07:00
37b6920df3
Fix group_matcher regex for regnet.py
2022-05-09 10:40:40 -07:00
93a79a3dd9
Fix num_features in Sequencer
2022-05-06 23:16:32 +09:00
2fec08e923
Add Sequencer to non std filters
2022-05-06 23:08:10 +09:00
57a988df30
fix: multistep lr decay epoch bugs
...
- add milestones arguments
- change decay_epochs to milestones variable
2022-05-06 13:14:43 +09:00
578d52e752
Add Sequencer
2022-05-06 00:36:01 +09:00
6d4665bb52
Merge pull request #1245 from rwightman/vit_relpos_refactor
...
Vision Transformer refactoring and Rel Pos impl
2022-05-03 09:27:02 -07:00
f5ca4141f7
Adjust arg order for recent vit model args, add a few comments
2022-05-02 22:41:38 -07:00
41dc49a337
Vision Transformer refactoring and Rel Pos impl
2022-05-02 15:37:39 -07:00
b7cb8d0337
Add Swin-V2 Small-NS weights (83.5 @ 224). Add layer scale like 'init_values' via post-norm LN weight scaling
2022-04-26 17:32:49 -07:00
001688dabf
Merge pull request #1233 from jjsjann123/nhwc_cond_conv2d
...
fixing channels_last on cond_conv2d; update nvfuser debug env variable
2022-04-25 20:42:03 -07:00
f88c606fcf
fixing channels_last on cond_conv2d; update nvfuser debug env variable
2022-04-25 12:41:46 -07:00
7d235c5a5f
Merge pull request #1230 from donglixp/patch-1
...
migrate azure blob for beit checkpoints
2022-04-24 14:06:26 -07:00
09e9f3defb
migrate azure blob for beit checkpoints
...
## Motivation
We are going to use a new blob account to store the checkpoints.
## Modification
Modify the azure blob storage URLs for BEiT checkpoints.
2022-04-23 13:02:29 +08:00
52ac881402
Missed first_conv in latest seresnext 'D' default_cfgs
2022-04-22 20:55:52 -07:00
7629d8264d
Add two new SE-ResNeXt101-D 32x8d weights, one anti-aliased and one not. Reshuffle default_cfgs vs model entrypoints for resnet.py so they are better aligned.
2022-04-22 16:54:53 -07:00
fbf597049c
Update README and change timmdocs link in documentation
2022-04-22 16:52:05 -07:00
01a0e25a67
Merge pull request #1208 from seefun/master
2022-04-05 14:12:31 -07:00
8f0bc0591e
fix convnext args
2022-04-05 20:00:57 +08:00
b0d2fcf647
Merge branch 'rwightman:master' into master
2022-04-05 19:23:18 +08:00
eac2df3d2c
Update PyTorch 1.10 benchmark numbers for latest code
2022-04-04 09:03:27 -07:00
c5a8e929fb
Add initial swinv2 tiny / small weights
2022-04-03 15:22:55 -07:00
83d7a11eec
Update .gitignore, remove out of date notebooks
2022-04-03 14:32:40 -07:00
02b806e00a
Add PyTorch 1.11 train benchmark numbers
2022-04-01 16:34:23 -07:00
c9f208f7f8
Update eval results and add latest PyTorch 1.11 inference benchmarks
2022-03-29 16:37:41 -07:00
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]
2022-03-24 21:43:56 -07:00
a9ecb880e5
Merge pull request #1190 from seefun/ConvNeXt-pretrain
...
Add ConvNeXt tiny and small pretrain in22k
2022-03-24 13:49:16 -07:00
5f4de2334b
Merge pull request #1 from seefun/ConvNeXt-pretrain
...
Add ConvNeXt tiny and small pretrain in22k
2022-03-24 15:19:49 +08:00
ec4e9aa5a0
Add ConvNeXt tiny and small pretrain in22k
...
Add ConvNeXt tiny and small pretrain in22k from ConvNeXt repo:
06f7b05f92
2022-03-24 15:18:08 +08:00
73ffade1f8
Update README.md
2022-03-23 22:00:31 -07:00
575924ed60
Update test crop for new RegNet-V weights to match Y
2022-03-23 21:40:53 -07:00
8f6d638887
Update README.md
2022-03-23 16:16:26 -07:00
1618527098
Add layer scale and parallel blocks to vision_transformer
2022-03-23 16:09:07 -07:00
c42be74621
Add attrib / comments about Swin-S3 (AutoFormerV2) weights
2022-03-23 16:07:09 -07:00
474ac906a2
Add 'head norm first' convnext_tiny_hnf weights
2022-03-23 16:06:00 -07:00
dc51334cdc
Fix pruned adapt for EfficientNet models that are now using BatchNormAct layers
2022-03-22 20:33:01 -07:00
024fc4d9ab
version 0.6.1 for master
2022-03-21 22:03:13 -07:00
e1e037ba52
Fix bad tuple typing fix that was on XLA branch bust missed on master merge
2022-03-21 22:00:33 -07:00
341b464a5a
Remove redundant noise attr from Plateau scheduler (use parent)
2022-03-21 22:00:03 -07:00
7514439573
Merge pull request #1014 from rwightman/norm_norm_norm
...
Normalization layer additions, model API updates, new models, new weights, and enhancements
2022-03-21 21:51:21 -07:00
ff21fdb41d
Update README.md ready for merge
2022-03-21 16:38:36 -07:00
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
2022-03-21 14:50:28 -07:00
Ross Wightman
Ross Wightman
han
okojoalg
jjsjann123
Li Dong
SeeFun