f55c22bebf
Merge pull request #1034 from zeakey/master
...
Fix hard-coded strides in VisFormer.
2021-12-14 14:12:47 -08:00
683fba7686
Add drop args to benchmark.py
2021-12-14 13:51:00 -08:00
ab49d275de
Significant norm update
...
* ConvBnAct layer renamed -> ConvNormAct and ConvNormActAa for anti-aliased
* Significant update to EfficientNet and MobileNetV3 arch to support NormAct layers and grouped conv (as alternative to depthwise)
* Update RegNet to add Z variant
* Add Pre variant of XceptionAligned that works with NormAct layers
* EvoNorm matches bits_and_tpu branch for merge
2021-12-14 13:48:30 -08:00
31bcd36e46
add tinynet models
2021-12-14 19:34:04 +05:30
b4b8d1ec18
fix hard-coded strides
2021-12-14 17:22:54 +08:00
d04f2f1377
Update drop_path and drop_block (fast impl) to be symbolically traceable, slightly faster
2021-12-05 15:36:56 -08:00
cd059cbe9c
Add FX backward tests back
2021-12-01 14:58:56 -08:00
834a9ec721
Disable use of timm nn.Linear wrapper since AMP autocast + torchscript use appears fixed
2021-12-01 14:58:09 -08:00
58ffa2bfb7
Update pytest for GitHub runner to use --forked with xdist, hopefully eliminate memory buildup
2021-12-01 12:09:23 -08:00
78912b6375
Updated EvoNorm implementations with some experimentation. Add FilterResponseNorm. Updated RegnetZ and ResNetV2 model defs for trials.
2021-12-01 12:09:01 -08:00
55adfbeb8d
Add commented code to increase open file limit via Python (for TFDS dataset building)
2021-11-30 17:02:27 -08:00
c11f4c3218
support CNNs
2021-11-30 08:48:08 +02:00
d6701d8a81
Merge branch 'rwightman:master' into master
2021-11-30 08:07:44 +02:00
ccb3815360
update arxiv link
2021-11-29 21:41:00 +03:00
b6c180ef19
use_ml_decoder_head
2021-11-28 13:56:55 +02:00
f7d210d759
Remove evonorm models from FX tests
2021-11-24 13:21:24 -08:00
3dc71695bf
Merge pull request #989 from martinsbruveris/feat/resmlp-dino
...
Added DINO pretrained ResMLP models.
2021-11-24 09:26:07 -08:00
480c676ffa
Fix FX breaking assert in evonorm
2021-11-24 09:24:47 -08:00
85c5ff26d7
Added DINO pretrained ResMLP models.
2021-11-24 15:02:46 +02:00
f83b0b01e3
Would like to pass GitHub tests again disabling both FX feature extract backward and torchscript tests
2021-11-23 22:24:58 -08:00
a22b85c1b9
Merge branch 'nateraw-hf-save-and-push'
2021-11-23 16:55:13 -08:00
d633a014e6
Post merge cleanup. Fix potential security issue passing kwargs directly through to serialized web data.
2021-11-23 16:54:01 -08:00
ab5ae32f75
fix: typo of argment parser desc in train.py
...
- Remove duplicated `of`
2021-11-24 09:32:05 +09:00
8a83c41d7b
Merge branch 'hf-save-and-push' of https://github.com/nateraw/pytorch-image-models into nateraw-hf-save-and-push
2021-11-23 14:33:07 -08:00
147e1059a8
Remove FX backward test from GitHub actions runs for now.
2021-11-23 14:32:32 -08:00
b18c9e323b
Update helpers.py
2021-11-22 23:43:44 -05:00
308d0b9554
Merge branch 'master' into hf-save-and-push
2021-11-22 23:39:27 -05:00
878bee1d5e
Add patch8 vit model to FX exclusion filter
2021-11-22 14:00:27 -08:00
9bb4c80d2a
Update README.md, missed recent regnetz results
2021-11-22 12:08:46 -08:00
79bf4f163f
Add mention of ResNet50 weights w/ RSB recipe ingredients and lower train res for better @ 224 results (but worse res scaling beyond). Not changing default.
2021-11-22 11:49:05 -08:00
ce76a810c2
New FX test strategy, filter based on param count
2021-11-22 11:48:40 -08:00
1e51c2d02e
More FX test tweaks
2021-11-22 09:46:43 -08:00
f0507f6da6
Fix k_decay default arg != 1.0 in poly scheduler
2021-11-22 09:37:36 -08:00
41559247e9
use_ml_decoder_head
2021-11-22 17:50:39 +02:00
947e1df3ef
Update README.md
2021-11-21 21:27:08 -08:00
90448031ea
Filter more large models from FX tests
2021-11-21 21:26:44 -08:00
1f53db2ece
Updated lamhalobotnet weights, 81.5 top-1
2021-11-21 19:49:51 -08:00
8dc269c303
Filter more models for FX tests
2021-11-21 19:49:33 -08:00
15ef108eb4
Add better halo2botnet50ts weights, 82 top-1 @ 256
2021-11-21 14:09:12 -08:00
2482652027
Add nfnet_f2 to FX test exclusion
2021-11-21 14:08:53 -08:00
734b2244fe
Add RegNetZ-D8 (83.5 @ 256, 84 @ 320) and RegNetZ-E8 (84.5 @ 256, 85 @ 320) weights. Update names of existing RegZ models to include group size.
2021-11-20 15:52:04 -08:00
05092e2fbe
Add more models to FX filter
2021-11-20 15:51:48 -08:00
93cc08fdc5
Make evonorm variables 1d to match other PyTorch norm layers, will break weight compat for any existing use (likely minimal, easy to fix).
2021-11-20 15:50:51 -08:00
af607b75cc
Prep a set of ResNetV2 models with GroupNorm, EvoNormB0, EvoNormS0 for BN free model experiments on TPU and IPU
2021-11-19 17:37:00 -08:00
3819bef93e
Add FX test exclusion since it uses more ram and barfs on GitHub actions. Will take a few iterations to include needed models :(
2021-11-19 17:35:41 -08:00
c976a410d9
Add ResNet-50 w/ GN (resnet50_gn) and SEBotNet-33-TS (sebotnet33ts_256) model defs and weights. Update halonet50ts weights w/ slightly better variant in1k val, more robust to test sets.
2021-11-19 14:24:43 -08:00
9b3519545d
Attempt to reduce memory footprint of FX tests for GitHub actions runs
2021-11-19 14:24:12 -08:00
bdd3dff0ca
beit_large models killing GitHub actions test, filter out
2021-11-19 08:39:48 -08:00
9d6aad44f8
Update tests to run Python 3.9, PyTorch 1.10, torchvision 0.11.1
2021-11-18 21:38:04 -08:00
ee40b582bb
Merge branch 'alexander-soare-fx-feature-extract-new'
2021-11-18 21:26:56 -08:00
Ross Wightman
Ross Wightman
Rahul Somani
KAI ZHAO
talrid
mrT23
qwertyforce
Martins Bruveris
han
Nathan Raw