MORPH
SIGN IN SIGN UP
huggingface / pytorch-image-models UNCLAIMED

The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (ViT), MobileNetV4, MobileNet-V3 & V2, RegNet, DPN, CSPNet, Swin Transformer, MaxViT, CoAtNet, ConvNeXt, and more

0 0 0 Python

COMMITS

/ validate.py
diff_parallel
December 1, 2025
R
Remove apex AMP use from scripts
Ross Wightman committed
fee045e
September 4, 2025
R
f1/p/r -> 0..100 to match existing accuracy range
Ross Wightman committed
40042b7
August 15, 2025
D
feat(validate): add extra metrics, JSON export, and latency/memory tracking
DASH committed
74425f9
July 18, 2025
R
Fix model patch sizes != 16 in validate.py for naflex_loader use
Ross Wightman committed
68790f9
July 3, 2025
G
Update no_grad usage to inference_mode if possible
GuillaumeErhard committed
8630947
June 19, 2025
R
Refactor and cleanup NaFlex pos embed methods. Make interface more consistent, add factorized grid_sample and fixed grid size methods.
Ross Wightman committed
41058e9
April 25, 2025
R
Add naflex loader support to validate.py, fix bug in naflex pos embed add, classic vit weight loading for naflex model
Ross Wightman committed
3dc90ed
January 28, 2025
R
Fix missing model key in bulk validate results on error
Ross Wightman committed
b1752ee
January 20, 2025
J
Fix metavar for --input-size
Josua Rieder committed
634b68a
January 9, 2025
R
Avoid unecessary compat break btw train script and nearby timm versions w/ dtype addition.
Ross Wightman committed
eeee38e
January 7, 2025
R
Fix dtype log when default (None) is used w/o AMP
Ross Wightman committed
1969528
R
Add half-precision (bfloat16, float16) support to train & validate scripts. Should push dtype handling into model factory / pretrained load at some point...
Ross Wightman committed
92f610c
November 8, 2024
A
Add --dataset-trust-remote-code to the train.py and validate.py scripts
Augustin Godinot committed
2dff16f
October 18, 2024
R
Remove extra space
Ross Wightman committed
c3992d5
R
Merge branch 'MengqingCao-npu_support' into device_amp_cleanup
Ross Wightman committed
015fbe4
R
Cleanup some amp related behaviour to better support different (non-cuda) devices
Ross Wightman committed
1766a01
October 17, 2024
M
fix device check
MengqingCao committed
37c731c
October 16, 2024
M
add npu support
MengqingCao committed
234f975
October 2, 2024
R
Add --torchcompile-mode args to train, validation, inference, benchmark scripts
Ross Wightman committed
4d4bdd6
January 5, 2024
R
Significant transforms, dataset, dataloading enhancements.
Ross Wightman committed
be0944e
August 23, 2023
R
MobileOne and FastViT weights on HF hub, more code cleanup and tweaks, features_only working. Add reparam flag to validate and benchmark, support reparm of all models with fuse(), reparameterize() or switch_to_deploy() methods on modules
Ross Wightman committed
5242ba6
June 1, 2023
L
Changed help_string of --worker
Lorenzo Baraldi committed
13d5b21
March 22, 2023
R
Improve filtering behaviour for tag + non-tagged model wildcard consistency.
Ross Wightman committed
b3e816d
March 18, 2023
R
Use gather (fancy indexing) for valid labels instead of bool mask in validate.py
Ross Wightman committed
3448cc6
January 6, 2023
R
Pass through --model-kwargs (and --opt-kwargs for train) from command line through to model __init__. Update some models to improve arg overlay. Cleanup along the way.
Ross Wightman committed
e861b74
December 9, 2022
R
Merge remote-tracking branch 'origin/main' into refactor-imports
Ross Wightman committed
d5e7d6b
L
Put validation loss under amp_autocast
Lorenzo Baraldi committed
3d6bc42
December 6, 2022
R
Major module / path restructure, timm.models.layers -> timm.layers, add _ prefix to all non model modules in timm.models
Ross Wightman committed
927f031
December 2, 2022
R
Update scripts to support torch.compile(). Make --results_file arg more consistent across benchmark/validate/inference. Fix #1570
Ross Wightman committed
dbe7531
November 22, 2022
R
Add crop_mode for pretraind config / image transforms. Add support for dynamo compilation to benchmark/train/validate
Ross Wightman committed
9da7e3a
October 14, 2022
R
Update validate.py to use updated amp args for impl/dtype
Ross Wightman committed
eb333d6
September 23, 2022
R
Refactor device handling in scripts, distributed init to be less 'cuda' centric. More device args passed through where needed.
Ross Wightman committed
87939e6
August 26, 2022
R
Add --fast-norm arg to benchmark.py, train.py, validate.py
Ross Wightman committed
ff6a919
August 1, 2022
R
jit trace comparisons snuck into torchscript part of validate.py, fixed
Ross Wightman committed
56596e4
July 19, 2022
R
Add bulk_runner script and updates to benchmark.py and validate.py for better error handling in bulk runs (used for benchmark and validation result runs). Improved batch size decay stepping on retry...
Ross Wightman committed
0dbd935
July 8, 2022
R
Add --use-train-size flag to force use of train input_size (over test input size) for validation. Default test-time pooling to use train input size (fixes issues).
Ross Wightman committed
7c7ecd2
July 7, 2022
R
Add --aot-autograd (functorch efficient mem fusion) support to validate.py
Ross Wightman committed
500c190
May 24, 2022
Y
fix a function parameter typo(cropt_pct -> crop_pct)
Yonghye Kwon committed
57f8361
January 26, 2022
R
Merge remote-tracking branch 'origin/master' into norm_norm_norm
Ross Wightman committed
95cfc9b
R
Transitioning default_cfg -> pretrained_cfg. Improving handling of pretrained_cfg source (HF-Hub, files, timm config, etc). Checkpoint handling tweaks.
Ross Wightman committed
abc9ba2
January 24, 2022
R
Update benchmark and validate scripts to output results in JSON with a fixed delimiter for use in multi-process launcher
Ross Wightman committed
cf43343
January 17, 2022
R
Add --fuser arg to train/validate/benchmark scripts to select jit fuser type
Ross Wightman committed
f0f9ecc
January 15, 2022
R
Add ConvNeXt 22k->1k fine-tuned and 384 22k-1k fine-tuned weights after testing
Ross Wightman committed
b669f4a
November 10, 2021
R
Dataset work
Ross Wightman committed
ba65dfe
October 6, 2021
R
Make test-pooling flag for validate.py opt in
Ross Wightman committed
e0b3a3f
September 23, 2021
R
Batch validate a list of files if model is a text file with model per line
Ross Wightman committed
5d6983c
April 17, 2021
R
Add _in22k to bulk validate filter
Ross Wightman committed
a04427d
April 1, 2021
R
Merge remote-tracking branch 'origin/benchmark-fixes-vit_hybrids' into pit_and_vit_update
Ross Wightman committed
a5310a3
March 17, 2021
R
Support for huggingface hub via create_model and default_cfgs.
Ross Wightman committed
d584e7f
February 24, 2021
R
Add epoch-repeats arg to multiply the number of dataset passes per epoch. Currently for iterable datasets (read TFDS wrapper) only.
Ross Wightman committed
2db2d87