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
...
Exclude results from possible packaging as it has .py now
4 years ago
Ross Wightman
0d5550c1e2
Merge pull request #183 from KushajveerSingh/results_diff
...
Add rank difference, and top-1/top-5 difference from ImageNet-1k validation for the 3 additional test sets
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:
...
* stage creation + make_layer moved to separate fn with more sensible dilation/output_stride calc
* drop path rate decay easy to impl with refactored block creation loops
* fix dilation + blur pool combo
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
Ross Wightman
d0113f9cdb
Fix a few issues that came up in tests
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
24e7535278
Remove tests from distrib
4 years ago
Ross Wightman
328339a086
Add ESE-VoVNet-19-DW weights
4 years ago
Ross Wightman
2d83752bc2
Fix default interpolation/crop of largest 2 ResNeSt models
4 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.
4 years ago
Ross Wightman
d1b5dddad1
Merge pull request #155 from rwightman/densenet_update_and_more
...
DenseNet updates, EvoNorms, VovNet, activation factory and more. Includes PR #142
4 years ago
Ross Wightman
39f27c1add
Almost ready to merge, vovnet typo, version bump, readme addition
4 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
4 years ago
Ross Wightman
6c7932fe75
Update sotabench.py, tweak VovNet cfg
4 years ago
Ross Wightman
d3ee3de96a
Update validation script first batch prime and clear cuda cache between multi-model runs
4 years ago
Ross Wightman
0aca08384f
Update regnet cfg keys to match model names so registry works properly
4 years ago
Ross Wightman
b41b8d0108
Update results csv files
4 years ago
Ross Wightman
13c0a6290e
Add ESE-VovNet39 weights, 79.32 top-1
4 years ago
Ross Wightman
4ddde1d3a4
Fix two regressions
4 years ago
Ross Wightman
a7e8cadd15
Remove pointless densenet configs, add an iabn version of 264 as it makes more sense to try someday...
4 years ago
Ross Wightman
e78daf586a
better densenet121 and densenetblur121d weights
4 years ago
Ross Wightman
7be299504f
Add missing feature_info() on MobileNetV3, make hook feature output order/type consistent with bottleneck (list, decreasing fmap size)
4 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.
4 years ago
Ross Wightman
f28170df3f
Fix an an untested change, remove a debug print
4 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
4 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