Commit Graph

944 Commits (8bf63b6c6cc2b4ba69030cb043bf33cd562b399c)
 

Author SHA1 Message Date
Ross Wightman c146b54abc Cleanup EfficientNet/MobileNetV3 feature extraction a bit, only two tap locations now, small mobilenetv3 models work
5 years ago
Ross Wightman 68fd8a267b Merge branch 'master' into features
5 years ago
Ross Wightman 4e61c6a12d Cleanup, refactoring of Feature extraction code, add tests, fix tests, non hook feature extraction working with torchscript
5 years ago
Ross Wightman 6eec3fb4a4 Move FeatureHooks into features.py, switch EfficientNet, MobileNetV3 to use build model helper
5 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.
5 years ago
Ross Wightman 298fba09ac Back out some activation hacks trialing upcoming pytorch changes
5 years ago
Ross Wightman 3b9004bef9 Lots of changes to model creation helpers, close to finalizing feature extraction / interfaces
5 years ago
Ross Wightman e2cc481310 Update CSP ResNets for cross expansion without activation. Fix VovNet IABN compatibility with fixed activation arg.
5 years ago
Ross Wightman 3b6cce4c95 Add initial impl of CrossStagePartial networks, yet to be trained, not quite the same as darknet cfgs.
5 years ago
Ross Wightman 3aebc2f06c Switch DPN to use BnAct layer, train a new DPN 68b model with RA to 79.21
5 years ago
Ross Wightman 17f4dd2778 Merge branch 'michalwols-docs'
5 years ago
Ross Wightman 022130d229 Merge branch 'docs' of https://github.com/michalwols/pytorch-image-models into michalwols-docs
5 years ago
Ross Wightman 31cf1251c1
Update setup.py
5 years ago
Ross Wightman 0d5550c1e2
Merge pull request #183 from KushajveerSingh/results_diff
5 years ago
KushajveerSingh 5699e8429f set precision=2 in param_count
5 years ago
KushajveerSingh 6526ccb4a7 set precision=3 in results
5 years ago
KushajveerSingh 856f6181f7 add {rank,top1,top5}_diff in results
5 years ago
Ross Wightman f122f0274b Significant ResNet refactor:
5 years ago
michal 2608918e8d configure mkdocs based documentation
5 years ago
Ross Wightman a66df5fb91 More model feature extraction support, start to deprecate senet.py, dilations added to regnet, add proper aligned xception
5 years ago
Ross Wightman 7729f40dca Fix another bug, update all gluon resnet models to use new creation method (feature support)
5 years ago
Ross Wightman d72ac0db25 Fix #173, lr cycle default 0 vs 1. Fix #177, mirror resnest weights for future stability.
5 years ago
Ross Wightman d0113f9cdb Fix a few issues that came up in tests
5 years ago
Ross Wightman d23a2697d0 Working on feature extraction, interfaces refined, a number of models working, some in progress.
5 years ago
Ross Wightman 24e7535278 Remove tests from distrib
5 years ago
Ross Wightman 328339a086 Add ESE-VoVNet-19-DW weights
5 years ago
Ross Wightman 2d83752bc2 Fix default interpolation/crop of largest 2 ResNeSt models
5 years ago
Ross Wightman f225ae8e59 Update README with model results and attribution. Make scheduler factory bit more robust to arg differences, add noise to plateau lr and fix min/max.
5 years ago
Ross Wightman d1b5dddad1
Merge pull request #155 from rwightman/densenet_update_and_more
5 years ago
Ross Wightman 39f27c1add Almost ready to merge, vovnet typo, version bump, readme addition
5 years ago
Ross Wightman 151679c2f1 Add custom grad tests, fix cut & paste error with hard_mish ME, add a few more pytorch act fns to factory
5 years ago
Ross Wightman 6c7932fe75 Update sotabench.py, tweak VovNet cfg
5 years ago
Ross Wightman d3ee3de96a Update validation script first batch prime and clear cuda cache between multi-model runs
5 years ago
Ross Wightman 0aca08384f Update regnet cfg keys to match model names so registry works properly
5 years ago
Ross Wightman b41b8d0108 Update results csv files
5 years ago
Antoine Broyelle 78fa0772cc Leverage python hierachical logger
5 years ago
Ross Wightman 13c0a6290e Add ESE-VovNet39 weights, 79.32 top-1
5 years ago
Ross Wightman 4ddde1d3a4 Fix two regressions
5 years ago
Ross Wightman a7e8cadd15 Remove pointless densenet configs, add an iabn version of 264 as it makes more sense to try someday...
5 years ago
Ross Wightman e78daf586a better densenet121 and densenetblur121d weights
5 years ago
Ross Wightman 7be299504f Add missing feature_info() on MobileNetV3, make hook feature output order/type consistent with bottleneck (list, decreasing fmap size)
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 f28170df3f Fix an an untested change, remove a debug print
5 years ago
Ross Wightman eb7653614f Monster commit, activation refactor, VoVNet, norm_act improvements, more
5 years ago
Ross Wightman ff94ffce61 Merge branch 'master' into densenet_update_and_more
5 years ago
Ross Wightman 5966654052 Update requirements so PyTorch 1.4 is min, add separate sotabench reqs to force 1.4 and prevent error with 1.5
5 years ago
Ross Wightman 0ea53cecc3 Merge branch 'master' into densenet_update_and_more
5 years ago
Ross Wightman 6441e9cc1b Fix memory_efficient mode for DenseNets. Add AntiAliasing (Blur) support for DenseNets and create one test model. Add lr cycle/mul params to train args.
5 years ago
Ross Wightman d79ac48626 Update sotabench.py
5 years ago
Ross Wightman e881383b4e
Merge pull request #154 from rwightman/tests_bugfixes
5 years ago