ab3ac3f25b
Add FX based FeatureGraphNet capability
2021-11-12 20:45:05 +00:00
65419f60cc
Merge pull request #964 from rwightman/more_datasets
...
Dataset additions
2021-11-11 13:34:05 -08:00
9ec3210c2d
More TFDS parser cleanup, support improved TFDS even_split impl (on tfds-nightly only currently).
2021-11-10 15:52:09 -08:00
ba65dfe2c6
Dataset work
...
* support some torchvision datasets
* improvements to TFDS wrapper for subsplit handling (fix #942 ), shuffle seed
* add class-map support to train (fix #957 )
2021-11-09 22:34:15 -08:00
ddc29da974
Add ResNet101 and ResNet152 weights from higher aug RSB recipes. 81.93 and 82.82 top-1 at 224x224.
2021-11-02 17:59:16 -07:00
b328e56f49
Update eca_halonext26ts weights to a better set
2021-11-02 16:52:53 -07:00
2ddef942b9
Better fix for #954 that doesn't break torchscript, pull torch._assert into timm namespace when it exists
2021-11-02 11:22:33 -07:00
4f0f9cb348
Fix #954 by bringing traceable _assert into timm to allow compat w/ PyTorch < 1.8
2021-11-02 09:21:40 -07:00
a41de1f666
Add interpolation mode handling to transforms. Removes InterpolationMode warning. Works for torchvision versions w/ and w/o InterpolationMode enum. Fix #738 .
2021-10-28 17:35:01 -07:00
ed41d32637
Add repr to auto_augment and random_erasing impl
2021-10-28 17:33:36 -07:00
135a48d024
Fix sam result again for imagenetv2
2021-10-28 14:46:45 -07:00
aaff2d82d0
Add new 50ts attn models to benchmark/meta csv files
2021-10-28 14:32:47 -07:00
1e17863b7b
Fixed botne*t26 model results, add some 50ts self-attn variants
2021-10-28 13:55:24 -07:00
ae72d009fa
Add weights for lambda_resnet50ts, halo2botnet50ts, lamhalobotnet50ts, updated halonet50ts
2021-10-27 22:08:54 -07:00
13178ba73a
Add benchmark and metadata csv files
2021-10-26 10:50:46 -07:00
b745d30a3e
Fix formatting of last commit
2021-10-25 15:15:14 -07:00
3478f1d7f1
Traceability fix for vit models for some experiments
2021-10-25 15:13:08 -07:00
f658a72e72
Cleanup re-use of Dropout modules in Mlp modules after some twitter feedback :p
2021-10-25 00:40:59 -07:00
71f00bfe9e
Don't run profile if model is torchscripted
2021-10-24 22:41:20 -07:00
7da1b0b61c
Merge pull request #933 from t-vi/unbind
...
use .unbind instead of explicitly listing the indices
2021-10-24 22:33:18 -07:00
5882e62ada
Add activation count to fvcore based profiling in benchmark.py
2021-10-24 15:30:38 -07:00
51f488b7f5
Update results.csv files with latest weights
2021-10-24 14:48:33 -07:00
f805ba86d9
use .unbind instead of explicitly listing the indices
2021-10-24 21:08:47 +02:00
57992509f9
Fix some formatting in utils/model.py
2021-10-23 20:35:36 -07:00
0fe4fd3f1f
add d8 and e8 regnetz models with group size 8
2021-10-23 20:34:21 -07:00
25e7c8c5e5
Update broken resnetv2_50 weight url, add resnetv1_101 a1h recipe weights for 224x224 train
2021-10-20 22:14:12 -07:00
f7325c7b71
Support either deepspeed or fvcore for flop profiling
2021-10-20 15:17:30 -07:00
66253790d4
Add `--bench profile` mode for benchmark.py to just run deepspeed detailed profile on model
2021-10-19 16:06:38 -07:00
13a8bf7972
Add train size override and deepspeed GMACs counter (if deepspeed installed) to benchmark.py
2021-10-19 15:15:01 -07:00
0ba73e6bcb
Update README.md
2021-10-19 14:38:56 -07:00
b6caa356d2
Fixed eca_botnext26ts_256 weights added, 79.27
2021-10-19 12:44:28 -07:00
c02334d9fa
Add weights for regnetz_d and haloregnetz_c, update regnetz_c weights. Add commented PyTorch XLA code for halo attention
2021-10-19 12:32:09 -07:00
02daf2ab94
Add option to include relative pos embedding in the attention scaling as per references. See discussion #912
2021-10-12 15:37:01 -07:00
2c33ca6d8c
Merge pull request #913 from ground0state/master
...
Fix bugs that Mixup does not work when device is cpu
2021-10-12 14:09:56 -07:00
047a5ec05f
Fix bugs that Mixup does not work device=cpu
2021-10-12 23:51:46 +09:00
cd34913278
Remove some outdated comments, botnet networks working great now.
2021-10-11 22:43:41 -07:00
6ed4cdccca
Update lambda_resnet26t weights with better set
2021-10-10 16:32:54 -07:00
288ece0e9f
Merge pull request #910 from tmp-iclr/master
...
Add ConvMixer
2021-10-10 16:00:58 -07:00
44d6d51668
Add ConvMixer
2021-10-09 21:09:51 -04:00
a85df34993
Update lambda_resnet26rpt weights to 78.9, add better halonet26t weights at 79.1 with tweak to attention dim
2021-10-08 17:44:13 -07:00
38804c721b
Checkpoint clean fn useable stand alone
2021-10-08 17:43:53 -07:00
b544ad4d3f
regnetz model default cfg tweaks
2021-10-06 21:14:59 -07:00
d80653cb99
Merge branch 'alexander-soare-freeze-functionality'
2021-10-06 17:01:41 -07:00
e5da481073
Small post-merge tweak for freeze/unfreeze, add to __init__ for utils
2021-10-06 17:00:27 -07:00
5ca72dcc75
Merge branch 'freeze-functionality' of https://github.com/alexander-soare/pytorch-image-models into alexander-soare-freeze-functionality
2021-10-06 16:51:03 -07:00
e2b8d44ff0
Halo, bottleneck attn, lambda layer additions and cleanup along w/ experimental model defs
...
* align interfaces of halo, bottleneck attn and lambda layer
* add qk_ratio to all of above, control q/k dim relative to output dim
* add experimental haloregnetz, and trionet (lambda + halo + bottle) models
2021-10-06 16:32:48 -07:00
e0b3a3fab3
Make test-pooling flag for validate.py opt in
2021-10-06 16:12:20 -07:00
431e60c83f
Add acknowledgements for freeze_batch_norm inspiration
2021-10-06 14:28:49 +01:00
fbf59c04ee
Change crop ratio on correct resnet50 variant.
2021-10-04 22:31:08 -07:00
ae1ff5792f
Clean a1/a2/3 rsb _0 checkpoints properly, fix v2 loading.
2021-10-04 16:46:00 -07:00
Alexander Soare
Ross Wightman
Ross Wightman
Thomas Viehmann
masafumi
ICLR Author