mrT23
|
98a7403ed4
|
Merge pull request #1 from rwightman/master
merge master
|
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
|
56608c9070
|
Bump version for pypi
|
5 years ago |
|
Ross Wightman
|
0ebcd2eca1
|
No default img size for inference script. Fixes #109
|
5 years ago |
|
Ross Wightman
|
1a8f5900ab
|
Update EfficientNet feature extraction for EfficientDet. Add needed MaxPoolSame as well.
|
5 years ago |
|
Ross Wightman
|
e01ccb88ce
|
Merge pull request #117 from VRandme/typo_eca
minor PR to fix typos found in #116 and resnet.py
|
5 years ago |
|
Chris Ha
|
06a50a94a8
|
Fix minor typos in create_attn.py and resnet.py
'eca'->'ceca'
and
doest not-> does not
|
5 years ago |
|
Ross Wightman
|
1a9ab07307
|
One too many changes at a time, fix missing C
|
5 years ago |
|
Ross Wightman
|
f17b42bc33
|
Blur filter no longer a buffer
|
5 years ago |
|
Ross Wightman
|
6cdeca24a3
|
Some cleanup and fixes for initial BlurPool impl. Still some testing and tweaks to go...
|
5 years ago |
|
Chris Ha
|
acd1b6cccd
|
Implement Functional Blur on resnet.py
1. add ResNet argument blur=''
2. implement blur for maxpool and strided convs in downsampling blocks
|
5 years ago |
|
Chris Ha
|
ce3d82b58b
|
Update blurpool.py
clean up code for PR
|
5 years ago |
|
Chris Ha
|
3a287a6e76
|
Create blurpool.py
Initial implementation of blur layer.
currently tests as correct against Downsample of original github
|
5 years ago |
|
Ross Wightman
|
c99a5abed4
|
Merge pull request #115 from rwightman/mobilenetv2-experiment
MobileNet-V2 experiments
|
5 years ago |
|
Ross Wightman
|
e34074b4da
|
Add final weights for MobileNet-V2 experiments
|
5 years ago |
|
Ross Wightman
|
a6a5565de7
|
Fiddling...
|
5 years ago |
|
Ross Wightman
|
5a16c533ff
|
Add better resnext50_32x4d weights trained by andravin
|
5 years ago |
|
Ross Wightman
|
bc998cad91
|
Experimenting with some MobileNetV2 variations to compare against EfficientNet-Lite
|
5 years ago |
|
Ross Wightman
|
71b5cd67da
|
Merge pull request #105 from rwightman/efficientnet-lite
EfficientNet-Lite
|
5 years ago |
|
Ross Wightman
|
ef30e7f2b6
|
Update sotabench with EffNet Lite models
|
5 years ago |
|
Ross Wightman
|
3406e582cf
|
Add EfficientNet-Lite results, update README
|
5 years ago |
|
Ross Wightman
|
bd05258f7b
|
EfficientNet-Lite model added w/ converted checkpoints, validation in progress...
|
5 years ago |
|
Ross Wightman
|
7deacf5477
|
Merge pull request #99 from andravin/save-last
Modified save_checkpoint to always save last checkpoint. Fixes #98.
|
5 years ago |
|
Andrew Lavin
|
d92cc4da54
|
Modified save_checkpoint to always save last checkpoint. Fixes #98.
|
5 years ago |
|
Ross Wightman
|
56e2ac3a6d
|
Merge pull request #94 from rwightman/lr_noise
Learning rate noise, MobileNetV3 weights, and activate MobileNetV3/EfficientNet weight init change
|
5 years ago |
|
Ross Wightman
|
c16f25ced2
|
Add MobileNetV3 Large weights, results, update README and sotabench for merge
|
5 years ago |
|
Ross Wightman
|
c60069c1eb
|
Annotate types on drop fns to avoid torchscript error
|
5 years ago |
|
Ross Wightman
|
9fee316752
|
Enable fixed fanout calc in EfficientNet/MobileNetV3 weight init by default. Fix #84
|
5 years ago |
|
Ross Wightman
|
27b3680d49
|
Revamp LR noise, move logic to scheduler base. Fixup PlateauLRScheduler and add it as an option.
|
5 years ago |
|
Ross Wightman
|
cc5a11abba
|
version bump for PyPi update
|
5 years ago |
|
Ross Wightman
|
514b0938c4
|
Experimenting with per-epoch learning rate noise w/ step scheduler
|
5 years ago |
|
Ross Wightman
|
d77f45a6f6
|
Forgot to add skresnet34 to sotabench
|
5 years ago |
|
Ross Wightman
|
6620770665
|
Simpler approach to loading entrypoints in hubconf works properly
|
5 years ago |
|
Ross Wightman
|
e0685dd415
|
Merge pull request #88 from rwightman/attention
A lot of attention and much more
|
5 years ago |
|
Ross Wightman
|
f1860ef3a5
|
Update README.md, check in hubconf experiment (fully dynamic)
|
5 years ago |
|
Ross Wightman
|
43225d110c
|
Unify drop connect vs drop path under 'drop path' name, switch all EfficientNet/MobilenetV3 refs to 'drop_path'. Update factory to handle new drop args.
|
5 years ago |
|
Ross Wightman
|
f1d5f8a6c4
|
Update comments for Selective Kernel and DropBlock/Path impl, add skresnet34 weights
|
5 years ago |
|
Ross Wightman
|
670c61b28f
|
Some cutmix/mixup cleanup/fixes
|
5 years ago |
|
Ross Wightman
|
b3cb5f3275
|
Working on CutMix impl as per #8, integrating with Mixup, currently experimenting...
|
5 years ago |
|
Ross Wightman
|
569419b38d
|
Tweak some comments, add SKNet models with weights to sotabench, remove an unused branch
|
5 years ago |
|
Ross Wightman
|
91e2b33d72
|
Update results with latest NoisyStudent models and SelectiveKernel models
|
5 years ago |
|
Ross Wightman
|
53c47479c4
|
Batch validation batch size adjustment, tweak L2 crop pct
|
5 years ago |
|
Ross Wightman
|
08553e16b3
|
Merge branch 'master' into attention
|
5 years ago |
|
Ross Wightman
|
fa38f24967
|
Update SK network configs, add weights for skresnet8 and skresnext50
|
5 years ago |
|
Ross Wightman
|
f098fda2ca
|
Add map_location='cpu' to ModelEma resume, should improve #72
|
5 years ago |
|
Ross Wightman
|
b9496995d8
|
Add L2-475 PyTorch preprocessing result, update sotabench for new weights
|
5 years ago |
|
Ross Wightman
|
ba15ca47e8
|
Add ported EfficientNet-L2, B0-B7 NoisyStudent weights from TF TPU
|
5 years ago |
|
Ross Wightman
|
5e6dbbaf30
|
Add CBAM for experimentation
|
5 years ago |
|
Ross Wightman
|
d725991870
|
Remove debug print from ECA module
|
5 years ago |
|
Ross Wightman
|
2a7d256fd5
|
Re-enable mem-efficient/jit activations after torchscript tests
|
5 years ago |
