Ross Wightman
7eb7e73216
File will not stay deleted
3 years ago
Ross Wightman
0012bf7fb5
Merge branch 'norm_norm_norm' into bits_and_tpu
3 years ago
Ross Wightman
8a93ce6ee3
Fix regnetv/w tests, refactor regnet generator code a bit
3 years ago
Ross Wightman
cbc4f33220
Merge branch 'norm_norm_norm' into bits_and_tpu
3 years ago
Ross Wightman
4dec8c8087
Fix skip path regression for updated EfficientNet and RegNet def. Add Pre-Act RegNet support (experimental). Remove BN-TF flag. Add efficientnet_b0_g8_gn model.
3 years ago
Ross Wightman
a52a614475
Remove layer experiment which should not have been added
3 years ago
Ross Wightman
d829858550
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
3 years ago
Ross Wightman
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
3 years ago
Ross Wightman
57fca2b5b2
Fix c16_evos stem / first conv setup
3 years ago
Ross Wightman
1f54a1fff7
Add C16 and E8 EvoNormS0 configs for RegNetZ BYOB nets
3 years ago
Ross Wightman
4d7a5544f7
Remove inplace sigmoid for consistency with other impl
3 years ago
Ross Wightman
88a5b54802
A few small evonorm tweaks for convergence comparisons
3 years ago
Ross Wightman
66daee4f31
Last change wasn't complete, missed adding full evo_norm changeset
3 years ago
Ross Wightman
7bbbd5ef1b
EvoNorm and GroupNormAct options for debugging TPU / XLA concerns
3 years ago
Ross Wightman
ff0f709c20
Testing TFDS shuffle across epochs
3 years ago
Ross Wightman
69e90dcd8c
Merge branch 'norm_norm_norm' into bits_and_tpu
3 years ago
Ross Wightman
d04f2f1377
Update drop_path and drop_block (fast impl) to be symbolically traceable, slightly faster
3 years ago
Ross Wightman
820ae9925e
Fix load_state_dict to handle None ema entries
3 years ago
Ross Wightman
0e212e8fe5
Merge remote-tracking branch 'origin/norm_norm_norm' into bits_and_tpu
3 years ago
Ross Wightman
834a9ec721
Disable use of timm nn.Linear wrapper since AMP autocast + torchscript use appears fixed
3 years ago
Ross Wightman
cad170e494
Merge remote-tracking branch 'origin/norm_norm_norm' into bits_and_tpu
3 years ago
Ross Wightman
78912b6375
Updated EvoNorm implementations with some experimentation. Add FilterResponseNorm. Updated RegnetZ and ResNetV2 model defs for trials.
3 years ago
Ross Wightman
55adfbeb8d
Add commented code to increase open file limit via Python (for TFDS dataset building)
3 years ago
Ross Wightman
3dc71695bf
Merge pull request #989 from martinsbruveris/feat/resmlp-dino
...
Added DINO pretrained ResMLP models.
3 years ago
Ross Wightman
480c676ffa
Fix FX breaking assert in evonorm
3 years ago
Martins Bruveris
85c5ff26d7
Added DINO pretrained ResMLP models.
3 years ago
Ross Wightman
d633a014e6
Post merge cleanup. Fix potential security issue passing kwargs directly through to serialized web data.
3 years ago
Nathan Raw
b18c9e323b
Update helpers.py
3 years ago
Nathan Raw
308d0b9554
Merge branch 'master' into hf-save-and-push
3 years ago
Ross Wightman
f0507f6da6
Fix k_decay default arg != 1.0 in poly scheduler
3 years ago
Ross Wightman
1f53db2ece
Updated lamhalobotnet weights, 81.5 top-1
3 years ago
Ross Wightman
15ef108eb4
Add better halo2botnet50ts weights, 82 top-1 @ 256
3 years ago
Ross Wightman
809c7bb1ec
Merge remote-tracking branch 'origin/master' into bits_and_tpu
3 years ago
Ross Wightman
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.
3 years ago
Ross Wightman
93cc08fdc5
Make evonorm variables 1d to match other PyTorch norm layers, will break weight compat for any existing use (likely minimal, easy to fix).
3 years ago
Ross Wightman
af607b75cc
Prep a set of ResNetV2 models with GroupNorm, EvoNormB0, EvoNormS0 for BN free model experiments on TPU and IPU
3 years ago
Ross Wightman
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.
3 years ago
Ross Wightman
f2006b2437
Cleanup qkv_bias cat in beit model so it can be traced
3 years ago
Ross Wightman
1076a65df1
Minor post FX merge cleanup
3 years ago
Ross Wightman
32c9937dec
Merge branch 'fx-feature-extract-new' of https://github.com/alexander-soare/pytorch-image-models into alexander-soare-fx-feature-extract-new
3 years ago
Ross Wightman
78b36bf46c
Places365 doesn't exist in some still used torchvision version
3 years ago
Alexander Soare
65d827c7a6
rename notrace registration and standardize trace_utils imports
3 years ago
Ross Wightman
9b2daf2a35
Add ResNeXt-50 weights 81.1 top-1 @ 224, 82 @ 288 with A1 'high aug' recipe
3 years ago
Ross Wightman
9b5d6dc7e2
Merge branch 'add-vit-b8' of https://github.com/martinsbruveris/pytorch-image-models into martinsbruveris-add-vit-b8
3 years ago
Ross Wightman
cfa414cad2
Matching two bits_and_tpu changes for TFDs wrapper
...
* change 'samples' -> 'examples' for tfds wrapper to match tfds naming
* add class_to_idx for image classification datasets in tfds wrapper
3 years ago
Martins Bruveris
5220711d87
Added B/8 models to ViT.
3 years ago
Alexander Soare
0262a0e8e1
fx ready for review
3 years ago
Ross Wightman
871cef4198
version 0.5.1
3 years ago
Ross Wightman
4f338556d8
Fixes and improvements for metrics, tfds parser, loader / transform handling
...
* add back ability to create transform with loader
* change 'samples' -> 'examples' for tfds wrapper to match tfds naming
* add support for specifying feature names for input and target in tfds wrapper
* add class_to_idx for image classification datasets in tfds wrapper
* add accumulate_type to avg meters and metrics to allow float32 or float64 accumulation control with lower prec data
* minor cleanup, log output rate prev and avg
3 years ago
Alexander Soare
d2994016e9
Add try/except guards
3 years ago