Commit Graph

518 Commits (b1f1a54de92ef8629eb486f2b14035a8cb314766)
 

Author SHA1 Message Date
Ross Wightman b1f1a54de9 More uniform treatment of classifiers across all models, reduce code duplication.
4 years ago
Ross Wightman 9806f3e1ff autosquash github workflow didn't work out, removing
4 years ago
Ross Wightman b496b7bde9 Re-ran batch validation on all models across all sets
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 d72ddafe56 Fix some checkpoint / model str regressions
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 ac18adb9c3 Remove debug print from RexNet
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 ec4976fdba Add EfficientNet-Lite0 weights trained with this code by @hal-314, 75.484 top-1
4 years ago
Ross Wightman 9ecd16bd7b Add new seresnet50 (non-legacy) model weights, 80.274 top-1
4 years ago
Ross Wightman 4805dd1e79 Fix incorrect dataset name, add new datasets to results delta script
4 years ago
Ross Wightman ea58e0bc16 Disable big models for MacOS test since they are starting to fail frequently.
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 6be878c22a Update results README to include robustness and real labels tests. Include labels files used in results gen.
4 years ago
Ross Wightman 6c17d57a2c Fix some attributions, add copyrights to some file docstrings
4 years ago
Ross Wightman a69c0e04f0 Fix pool size in cspnet
4 years ago
Ross Wightman 14ef7a0dd6 Rename csp.py -> cspnet.py
4 years ago
Ross Wightman ec37008432 Add pretrained weight links to CSPNet for cspdarknet53, cspresnext50
4 years ago
Sangdoo Yun e93e571f7a Add `adamp` and 'sgdp' optimizers.
4 years ago
Ross Wightman 0915beddad Add autosquash workflow
4 years ago
Ross Wightman 08016e839d Cleanup FeatureInfo getters, add TF models sourced Xception41/65/71 weights
4 years ago
Ross Wightman 7ba5a384d3 Add ReXNet w/ remapped weights, feature support
4 years ago
Ross Wightman c9d54bc1c3 Add HRNet feature extraction, fix senet type, lower feature testing res to 96x96
4 years ago
Ross Wightman 2ac663f340 Add feature support to legacy senets, add 32x32 resnext models to exclude list for feature testing.
4 years ago
Ross Wightman 701dba303e Again
4 years ago
Ross Wightman 648ba41b4b Try again with the worfklow threads
4 years ago
Ross Wightman 52b6e72e86 Try defining num threads for github workflow tests explicity (2)
4 years ago
Ross Wightman c146b54abc Cleanup EfficientNet/MobileNetV3 feature extraction a bit, only two tap locations now, small mobilenetv3 models work
4 years ago
Ross Wightman 68fd8a267b Merge branch 'master' into features
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 6eec3fb4a4 Move FeatureHooks into features.py, switch EfficientNet, MobileNetV3 to use build model helper
4 years ago
Ross Wightman 9eba134d79 More models supporting feature extraction, xception, gluon_xception, inception_v3, inception_v4, pnasnet, nasnet, dla. Fix DLA unused projection params.
4 years ago
Ross Wightman 298fba09ac Back out some activation hacks trialing upcoming pytorch changes
4 years ago
Ross Wightman 3b9004bef9 Lots of changes to model creation helpers, close to finalizing feature extraction / interfaces
4 years ago
Ross Wightman e2cc481310 Update CSP ResNets for cross expansion without activation. Fix VovNet IABN compatibility with fixed activation arg.
4 years ago
Ross Wightman 3b6cce4c95 Add initial impl of CrossStagePartial networks, yet to be trained, not quite the same as darknet cfgs.
4 years ago
Ross Wightman 3aebc2f06c Switch DPN to use BnAct layer, train a new DPN 68b model with RA to 79.21
4 years ago
Ross Wightman 17f4dd2778 Merge branch 'michalwols-docs'
4 years ago
Ross Wightman 022130d229 Merge branch 'docs' of https://github.com/michalwols/pytorch-image-models into michalwols-docs
4 years ago
Ross Wightman 31cf1251c1
Update setup.py
4 years ago
Ross Wightman 0d5550c1e2
Merge pull request #183 from KushajveerSingh/results_diff
4 years ago
KushajveerSingh 5699e8429f set precision=2 in param_count
4 years ago
KushajveerSingh 6526ccb4a7 set precision=3 in results
4 years ago
KushajveerSingh 856f6181f7 add {rank,top1,top5}_diff in results
4 years ago
Ross Wightman f122f0274b Significant ResNet refactor:
4 years ago
michal 2608918e8d configure mkdocs based documentation
4 years ago
Ross Wightman a66df5fb91 More model feature extraction support, start to deprecate senet.py, dilations added to regnet, add proper aligned xception
4 years ago
Ross Wightman 7729f40dca Fix another bug, update all gluon resnet models to use new creation method (feature support)
4 years ago
Ross Wightman d72ac0db25 Fix #173, lr cycle default 0 vs 1. Fix #177, mirror resnest weights for future stability.
4 years ago