Ross Wightman
95cfc9b3e8
Merge remote-tracking branch 'origin/master' into norm_norm_norm
3 years ago
Ross Wightman
abc9ba2544
Transitioning default_cfg -> pretrained_cfg. Improving handling of pretrained_cfg source (HF-Hub, files, timm config, etc). Checkpoint handling tweaks.
3 years ago
Ross Wightman
cf4334391e
Update benchmark and validate scripts to output results in JSON with a fixed delimiter for use in multi-process launcher
3 years ago
Ross Wightman
f0f9eccda8
Add --fuser arg to train/validate/benchmark scripts to select jit fuser type
3 years ago
Ross Wightman
b669f4a588
Add ConvNeXt 22k->1k fine-tuned and 384 22k-1k fine-tuned weights after testing
3 years ago
Ross Wightman
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 )
3 years ago
Ross Wightman
e0b3a3fab3
Make test-pooling flag for validate.py opt in
3 years ago
Ross Wightman
5d6983c462
Batch validate a list of files if model is a text file with model per line
3 years ago
Ross Wightman
a04427d8ce
Add _in22k to bulk validate filter
4 years ago
Ross Wightman
a5310a3451
Merge remote-tracking branch 'origin/benchmark-fixes-vit_hybrids' into pit_and_vit_update
4 years ago
Ross Wightman
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
Ross Wightman
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
Ross Wightman
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
Ross Wightman
0356e773f5
Default to native PyTorch AMP instead of APEX amp. Too many APEX issues cropping up lately.
4 years ago
Ross Wightman
b4e216e377
Fix a few small things.
4 years ago
Csaba Kertesz
5114c214fc
Change the Python interpreter to Python 3.x in the scripts
4 years ago
Ross Wightman
2a8c4dc63b
Add validation script update for using test_input_size in model default_cfgs
4 years ago
Ross Wightman
38d8f67570
Fix potential issue with change to num_classes arg in train/validate.py defaulting to None (rely on model def / default_cfg)
4 years ago
Ross Wightman
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
4 years ago
Ross Wightman
59ec7e6a53
Merge branch 'master' into imagenet21k_datasets_more
4 years ago
Csaba Kertesz
e42b140ade
Add --input-size option to scripts to specify full input dimensions from command-line
4 years ago
Ross Wightman
ce69de70d3
Add 21k weight urls to vision_transformer. Cleanup feature_info for preact ResNetV2 (BiT) models
4 years ago
Ross Wightman
de6046e213
Initial commit for dataset / parser reorg to support additional datasets / types
4 years ago
Matthijs Hollemans
8ffdc5910a
test_time_pool would be set to a non-False value even if test-time pooling is not available
4 years ago
Ross Wightman
e8ca45854c
More models in sotabench, more control over sotabench run, dataset filename extraction consistency
4 years ago
Ross Wightman
751b0bba98
Add global_pool (--gp) arg changes to allow passing 'fast' easily for train/validate to avoid channels_last issue with AdaptiveAvgPool
4 years ago
Ross Wightman
9c297ec67d
Cleanup Apex vs native AMP scaler state save/load. Cleanup CheckpointSaver a bit.
4 years ago
Ross Wightman
c2cd1a332e
Improve torch amp support and add channels_last support for train/validate scripts
4 years ago
Ross Wightman
ad150e7018
Update results csv file rank/diff script and small validate script tweak for batch validation
4 years ago
Ross Wightman
ecdeb470f2
Cleanup real labels in validate.py, no need to track original, will do that via exteran script
4 years ago
Ross Wightman
c53ec33ae0
Add synset/label indices for results generation. Add 'valid labels' to validation script to support imagenet-a/r label subsets properly.
4 years ago
Ross Wightman
7995295968
Merge branch 'logger' into features. Change 'logger' to '_logger'.
4 years ago
Ross Wightman
1998bd3180
Merge branch 'feature/AB/logger' of https://github.com/antoinebrl/pytorch-image-models into logger
4 years ago
Ross Wightman
6c17d57a2c
Fix some attributions, add copyrights to some file docstrings
4 years ago
Ross Wightman
4e61c6a12d
Cleanup, refactoring of Feature extraction code, add tests, fix tests, non hook feature extraction working with torchscript
4 years ago
Ross Wightman
d23a2697d0
Working on feature extraction, interfaces refined, a number of models working, some in progress.
4 years ago
Ross Wightman
d3ee3de96a
Update validation script first batch prime and clear cuda cache between multi-model runs
4 years ago
Antoine Broyelle
78fa0772cc
Leverage python hierachical logger
...
with this update one can tune the kind of logs generated by timm but
training and inference traces are unchanged
5 years ago
Ross Wightman
88129b2569
Add set_layer_config contextmgr to adjust all layer configs at once, use in create_module with new args. Remove a few old warning causing constant annotations for jit.
5 years ago
Ross Wightman
eb7653614f
Monster commit, activation refactor, VoVNet, norm_act improvements, more
...
* refactor activations into basic PyTorch, jit scripted, and memory efficient custom auto
* implement hard-mish, better grad for hard-swish
* add initial VovNet V1/V2 impl, fix #151
* VovNet and DenseNet first models to use NormAct layers (support BatchNormAct2d, EvoNorm, InplaceIABN)
* Wrap IABN for any models that use it
* make more models torchscript compatible (DPN, PNasNet, Res2Net, SelecSLS) and add tests
5 years ago
Ross Wightman
02a30411ad
Replace fp16 with amp support for validate.py script
5 years ago
Ross Wightman
13cf68850b
Remove poorly named metrics from torch imagenet example origins. Use top1/top5 in csv output for consistency with existing validation results files, acc elsewhere. Fixes #111
5 years ago
Ross Wightman
53c47479c4
Batch validation batch size adjustment, tweak L2 crop pct
5 years ago
Ross Wightman
1daa303744
Add support to Dataset for class id mapping file, clean up a bit of old logic. Add results file arg for validation and update script.
5 years ago
Ross Wightman
40fea63ebe
Add checkpoint averaging script. Add headers, shebangs, exec perms to all scripts
5 years ago
Ross Wightman
4666cc9aed
Add --pin-mem arg to enable dataloader pin_memory (showing more benefit in some scenarios now), also add --torchscript arg to validate.py for testing models with jit.script
5 years ago
Ross Wightman
7a92caa560
Add basic image folder style dataset to read directly out of tar files, example in validate.py
5 years ago
Ross Wightman
6cdf35e670
Add explicit half/fp16 support to loader and validation script
5 years ago
Ross Wightman
edb425ea48
Add crop_pct arg to validate, extra fields to csv output, 'all' filters pretrained
5 years ago
Ross Wightman
c6b32cbe73
A number of tweaks to arguments, epoch handling, config
...
* reorganize train args
* allow resolve_data_config to be used with dict args, not just arparse
* stop incrementing epoch before save, more consistent naming vs csv, etc
* update resume and start epoch handling to match above
* stop auto-incrementing epoch in scheduler
5 years ago