ea9c9550b2
Fully move ViT hybrids to their own file, including embedding module. Remove some extra DeiT models that were for benchmarking only.
4 years ago
a5310a3451
Merge remote-tracking branch 'origin/benchmark-fixes-vit_hybrids' into pit_and_vit_update
4 years ago
7953e5d11a
Fix pos_embed scaling for ViT and num_classes != 1000 for pretrained distilled deit and pit models. Fix #426 and fix #433
4 years ago
a760a4c3f4
Some ViT cleanup, merge distilled model with main, fixup torchscript support for distilled models
4 years ago
0dfc5a66bb
Add PiT model from https://github.com/naver-ai/pit
4 years ago
51febd869b
Small tweak to tests for tnt model, reorder model imports.
4 years ago
b27a4e0d88
Merge branch 'master' of https://github.com/contrastive/pytorch-image-models into contrastive-master
4 years ago
6b18061773
Add GIST to docstring for quick access
4 years ago
de86314655
Update TNT
4 years ago
92b1db9a79
update docstrings and add check on and
4 years ago
b85be24054
update to work with fnmatch
4 years ago
cfc15283a4
Update TNT url
4 years ago
4a09bc851e
Add TNT model
4 years ago
20626e8387
Add to extract stats for SPP
4 years ago
cf5fec5047
Cleanup experimental vit weight init a bit
4 years ago
f42f1df26c
Improve evenness of per-worker split for validation set with TFDS
4 years ago
cbcb76d72c
Should have included Conv2d layers in original weight init. Lets see what the impact is...
4 years ago
4de57ccf01
Add weight init scheme that's closer to JAX impl
4 years ago
14ac4abf74
Change huggingface hub revision delimiter to '@', add hf_hub reference for eca_nfnet_l0 model as an example.
4 years ago
740f32c96a
Add ECA-NFNet-L0 weights and update model name. Update README and bump version to 0.4.6
4 years ago
5e2e4e7fb6
Merge pull request #502 from khatami-mehrdad/efficientnet_dg
...
adding efficientnet_el, efficientnet_es_pruned and efficientnet_el_pruned pre-trained models
4 years ago
45c048ba13
A few minor fixes and bit more cleanup on the huggingface hub integration.
4 years ago
97f49d163c
adding efficientnet_el, efficientnet_es_prunedefficientnet_es_pruned and efficientnet_el_pruned pretrained models to timm/models
4 years ago
ead80d33c5
Fix typo, naming consistency
4 years ago
d584e7f617
Support for huggingface hub via create_model and default_cfgs.
...
* improve consistency of model creation helper fns
* add comments to some of the model helpers
* support passing external default_cfgs so they can be sourced from hub
4 years ago
1f799afcb3
Remove capital letters in model names
4 years ago
82c1fe958a
added hardcorenas model
...
refactoring to support feature extraction
4 years ago
f57db99101
Update README, fix iabn pip version print.
4 years ago
7ef7788ee9
Fix CUDA crash w/ channels-last + CSP models. Remove use of chunk()
4 years ago
317ea3e599
Tweak NFNet, ResNetV2, RexNet feature extraction, use pre-act features for simplicty. Update tests for pytorch 1.8. 0.4.5 version bump.
4 years ago
17cdee7354
Fix C&P patch_size error, and order of op patch_size arg resolution bug. Remove a test vit model.
4 years ago
0706d05d52
Benchmark models listed in txt file. Add more hybrid vit variants for testing
4 years ago
2db2d87ff7
Add epoch-repeats arg to multiply the number of dataset passes per epoch. Currently for iterable datasets (read TFDS wrapper) only.
4 years ago
de97be9146
Spell out diff between my small and deit small vit models.
4 years ago
f0ffdf89b3
Add numerous experimental ViT Hybrid models w/ ResNetV2 base. Update the ViT naming for hybrids. Fix #426 for pretrained vit resizing.
4 years ago
0e16d4e9fb
Add benchmark.py script, and update optimizer factory to be more friendly to use outside of argparse interface.
4 years ago
4bc103f504
Fix CUDA crash w/ channels-last + CSP models. Remove use of chunk()
4 years ago
8563609b28
Update notes in ScaledStdConv impl
4 years ago
678ba4e0a2
Add NFNet-F model weights ported from DeepMind Haiku impl and new set of models w/ compatible config.
4 years ago
9de2ec5e44
Update README for AGC and bump version to 0.4.4
4 years ago
4f49b94311
Initial AGC impl. Still testing.
4 years ago
5f9aff395c
Fix stem width in NFNet-F models, add some more comments, add some 'light' NFNet models for testing.
4 years ago
d86dbe45c2
Update README.md and few more comments
4 years ago
0d253e2c5e
Fix issue with nfnet tests, bit more cleanup.
4 years ago
cb06c7a910
Add NFNet-F models and tweak existing NF models.
4 years ago
e4de077021
Add first 'Normalizer Free' models. nf_regnet_b1 79.3 @ 288x288 test, and nf_resnet50 80.3 @ 256x256 test (80.68 @ 288x288).
4 years ago
d8e69206be
Merge pull request #419 from rwightman/byob_vgg_models
...
More models, GPU-Efficient Nets, RepVGG, classic VGG, and flexible Byob backbone.
4 years ago
ca9b078ac7
Update README.md and docs. Version bumped to 0.4.3
4 years ago
6853b07bbd
Improve RegVGG block identity/vs non for clariy and fix attn usage. Add comments.
4 years ago
0356e773f5
Default to native PyTorch AMP instead of APEX amp. Too many APEX issues cropping up lately.
4 years ago
94ca140b67
update collections.abc import
4 years ago
b4e216e377
Fix a few small things.
4 years ago
dc85e5a237
Add ByobNet w/ GPU-EfficientNets and RepVGG. Also add classic vgg models.
4 years ago
1bcc69e0ad
Use in_channels for depthwise groups, allows using `out_channels=N * in_channels` (does not impact existing models). Fix #354 .
4 years ago
9811e229f7
Fix regression in models with 1001 class pretrained weights. Improve batchnorm arg and BatchNormAct layer handling in several models.
4 years ago
a39c3ee216
Merge branch 'master' into eca-weights
4 years ago
e9d6fe293c
Update README for new weights. Version 0.4.2
4 years ago
666de85cf1
Move stride in EdgeResidual block to 3x3 expansion conv. Fix #414
4 years ago
3b57490a63
Fix some half removed resnet model defs, pooling for ecaresnet269d
4 years ago
68a4144882
Add new weights for ecaresnet26t/50t/269d models. Remove distinction between 't' and 'tn' (tiered models), tn is now t. Add test time img size spec to default cfg.
4 years ago
b9843f954b
Merge pull request #282 from tigert1998/patch-1
...
Add symbolic for SwishJitAutoFn to support onnx
4 years ago
7a4be5c035
add operator HardSwishJitAutoFn export to onnx
5 years ago
4203efa36d
Fix #387 so that checkpoint saver works with max history of 1. Add checkpoint-hist arg to train.py.
5 years ago
f0e65e37b7
Fix NF-ResNet101 model defs
5 years ago
2c988c3b6e
Update README.md for NF-nets, bump version to 0.4.1 for merge
5 years ago
2de54d174a
Fix pool size defs for NFNet models, add a comment.
5 years ago
90980de4a9
Fix up a few details in NFResNet models, managed stable training. Add support for gamma gain to be applied in activation or ScaleStdConv. Some tweaks to ScaledStdConv.
5 years ago
5a8e1e643e
Initial Normalizer-Free Reg/ResNet impl. A bit of related layer refactoring.
5 years ago
38d8f67570
Fix potential issue with change to num_classes arg in train/validate.py defaulting to None (rely on model def / default_cfg)
5 years ago
587780e56b
Update README.md and bump version to 0.4.0
5 years ago
bb50ac4708
Add DeiT distilled weights and distilled model def. Remove some redudant ViT model args.
5 years ago
c16e965037
Add some ViT comments and fix a few minor issues.
5 years ago
22748f1a2d
Convert samples/targets in ParserImageInTar to numpy arrays, slightly less mem usage for massive datasets. Add a few more se/eca model defs to resnet.py
5 years ago
5d4c3d0af3
Add enhanced ParserImageInTar that can read images from tars within tars, folders with multiple tars, etc. Additional comment cleanup.
5 years ago
55f7dfa9ea
Refactor vision_transformer entrpy fns, add pos embedding resize support for fine tuning, add some deit models for testing
5 years ago
d55bcc0fee
Finishing adding stochastic depth support to BiT ResNetV2 models
5 years ago
855d6cc217
More dataset work including factories and a tensorflow datasets (TFDS) wrapper
...
* Add parser/dataset factory methods for more flexible dataset & parser creation
* Add dataset parser that wraps TFDS image classification datasets
* Tweak num_classes handling bug for 21k models
* Add initial deit models so they can be benchmarked in next csv results runs
5 years ago
20516abc18
Fix some broken tests for ResNetV2 BiT models
5 years ago
59ec7e6a53
Merge branch 'master' into imagenet21k_datasets_more
5 years ago
e7a9ddf982
Merge pull request #334 from kecsap/links
...
Follow symbolic links during dataset scanning
5 years ago
7cae7e7035
Follow links during dataset scanning
5 years ago
c96e9f99a0
Update version to 0.3.3
5 years ago
4e2533db77
Add 320x320 model default cfgs for 101D and 152D ResNets. Add SEResNet-152D weights and 320x320 cfg.
5 years ago
0167f749d3
Remove some old __future__ imports
5 years ago
e35e9760a6
More work on dataset / parser split and imagenet21k (tar) support
5 years ago
ce69de70d3
Add 21k weight urls to vision_transformer. Cleanup feature_info for preact ResNetV2 (BiT) models
5 years ago
231d04e91a
ResNetV2 pre-act and non-preact model, w/ BiT pretrained weights and support for ViT R50 model. Tweaks for in21k num_classes passing. More to do... tests failing.
5 years ago
de6046e213
Initial commit for dataset / parser reorg to support additional datasets / types
5 years ago
392595c7eb
Add pool_size to default cfgs for new models to prevent tests from failing. Add explicit 200D_320 model entrypoint for next benchmark run.
5 years ago
b1f1228a41
Add ResNet101D, 152D, and 200D weights, remove meh 66d model
5 years ago
7c56c718f3
Configure create_optimizer with args.opt_args
...
Closes #301
5 years ago
9a25fdf3ad
Merge pull request #297 from rwightman/ema_simplify
...
Simplified JIT compatible Ema module. Fixes for SiLU export and torchscript training w/ Linear layer.
5 years ago
de15b43865
Fix a bug with accuracy retrieving from RealLabels
5 years ago
cd72e66eff
Bug in last mod for features_only default_cfg
5 years ago
867a0e5a04
Add default_cfg back to models wrapped in feature extraction module as per discussion in #294 .
5 years ago
4ca52d73d8
Add separate set and update method to ModelEmaV2
5 years ago
2ed8f24715
A few more changes for 0.3.2 maint release. Linear layer change for mobilenetv3 and inception_v3, support no bias for linear wrapper.
5 years ago
6504a42832
Version 0.3.2
5 years ago
460eba7f24
Work around casting issue with combination of native torch AMP and torchscript for Linear layers
5 years ago
5f4b6076d8
Fix inplace arg compat for GELU and PreLU via activation factory
5 years ago
Ross Wightman