a4497afa21
Update sotabench.py
2019-12-28 23:06:27 -08:00
53f578e16f
Update README with B3 training details
2019-12-28 17:51:08 -08:00
19fc205a4d
Update comments on the new SE-ResNeXt26 models
2019-12-28 17:33:10 -08:00
8894a6bc08
Update sotabench.py with latest seresnext26 and efficientnet_b3 models
2019-12-28 17:25:53 -08:00
acc3ed2b8c
Add EfficientNet-B3 weights, trained from scratch with RA.
2019-12-28 17:24:15 -08:00
2404361f62
correct asset paths
2019-12-28 23:32:20 +01:00
31939311f6
Added SelecSLS models
2019-12-28 23:06:00 +01:00
1f4498f217
Add ResNet deep tiered stem and model weights for seresnext26t_32x4d and seresnext26d_32x4d
2019-12-28 11:43:50 -08:00
32012a44fd
Added SelecSLS model
2019-12-28 20:41:55 +01:00
73b78459dc
Add update RandAugment MixNet-XL weights
2019-12-24 10:08:24 -08:00
3afc2a4dc0
Some cleanup/improvements to AugMix impl:
...
* make 'increasing' levels for Contrast, Color, Brightness, Saturation ops
* remove recursion from faster blending mix
* add config striing parsing for AugMix
2019-12-20 23:04:11 -08:00
232ab7fb12
Working on an implementation of AugMix with JensenShannonDivergence loss that's compatible with my AutoAugment and RandAugment impl
2019-12-20 23:04:11 -08:00
ff8688ca3d
Merge pull request #62 from rwightman/reduce-bn
...
Distribute BatchNorm stats
2019-12-19 23:22:16 -08:00
5719b493ad
Missed update dist-bn logic for EMA model
2019-12-19 23:03:04 -08:00
a435ea1327
Change reduce_bn to distribute_bn, add ability to choose between broadcast and reduce (mean). Add crop_pct arg to allow selecting validation crop while training.
2019-12-19 22:56:54 -08:00
3bff2b21dc
Add support for keeping running bn stats the same across distributed training nodes before eval/save
2019-12-05 22:35:40 -08:00
0161de0127
Switch RandoErasing back to on GPU normal sampling
2019-12-05 22:35:08 -08:00
5d7af97981
Update README.md
...
Update latest training hparam/command line with correct RandAugment config string (`noise` -> `mstd`)
2019-12-05 11:47:57 -08:00
3129bdb2c1
Update README.md
2019-12-04 11:13:25 -08:00
ff421e5e09
New PyTorch trained EfficientNet-B2 weights with my RandAugment impl
2019-12-04 11:09:47 -08:00
00b93407c7
Update results-all.csv with latest models/weights
2019-11-29 23:26:18 -08:00
5259dbcbb4
Update README.md with latest changes
2019-11-29 17:58:33 -08:00
3bef524f9c
Finish with HRNet, weights and models updated. Improve consistency in model classifier/global pool treatment.
2019-11-29 17:56:36 -08:00
3ceeedc441
Merge pull request #53 from rwightman/condconvs_and_features
...
Major model merge (EfficientNet-CondConv, EfficientNet-AdvProp, TF MobileNetV3, HRNet, more)
2019-11-28 18:05:32 -08:00
7b3c235ccc
Update sotabench with new models
2019-11-28 17:56:59 -08:00
6ca0828166
Update EfficientNet comments, MobileNetV3 non-TF create fns, fix factory arg checks, bump PyTorch version req to 1.2
2019-11-28 17:43:00 -08:00
eccbadca74
Update EfficientNet comments
2019-11-28 17:11:53 -08:00
902d32fb16
Renamed gen_efficientnet.py -> efficientnet.py
2019-11-28 17:04:35 -08:00
5a0a8de7e3
ResNet updates:
...
* remove redundant GluonResNet model/blocks and use the code in ResNet for Gluon weights
* change SEModules back to using AdaptiveAvgPool instead of mean, PyTorch issue long fixed
2019-11-28 17:04:35 -08:00
3b8f63084d
Clean checkpoint renames pth w/ SHA hash in a torch hub compatible way
2019-11-28 17:04:35 -08:00
a39cc43374
Bring EfficientNet and MobileNetV3 up to date with my gen-efficientnet repo
...
* Split MobileNetV3 and EfficientNet model files and put builder and blocks in own files (getting too large)
* Finalize CondConv EfficientNet variant
* Add the AdvProp weights files and B8 EfficientNet model
* Refine the feature extraction module for EfficientNet and MobileNetV3
2019-11-28 17:04:35 -08:00
ad93347548
Initial HRNet classification model commit
2019-11-28 17:00:52 -08:00
2393708650
Missed stashing of out_indices in model
2019-11-28 17:00:52 -08:00
35e8f0c5e7
Fixup a few comments, add PyTorch version aware Flatten and finish as_sequential for GenEfficientNet
2019-11-28 17:00:52 -08:00
7ac6db4543
Missed activations.py
2019-11-28 17:00:52 -08:00
506df0e3d0
Add CondConv support for EfficientNet into WIP for GenEfficientNet Feature extraction setup
2019-11-28 17:00:52 -08:00
db04677c94
Merge pull request #52 from rwightman/randaugment
...
RandAugment and more
2019-11-22 14:05:29 -08:00
576d360f20
Bring in JIT version of optimized swish activation from gen_efficientnet as default (while working on feature extraction functionality here).
2019-11-22 13:57:45 -08:00
1f39d15f15
Allow float decay epochs arg for training, works out with step lr math
2019-11-22 13:28:58 -08:00
7b83e67f77
Pass drop connect arg through to EfficientNet models
2019-11-22 13:27:43 -08:00
31453b039e
Update Auto/RandAugment comments, README, more.
...
* Add a weighted choice option for RandAugment
* Adjust magnitude noise/std naming, config
2019-11-22 13:24:52 -08:00
4243f076f1
Adding RandAugment to AutoAugment impl, some tweaks to AA included
2019-11-21 21:14:33 -08:00
4748c6dff2
Fix non-prefetch variant of Mixup. Fixes #50
2019-11-02 17:42:55 -07:00
0d58c50fb1
Add TF RandAug weights for B5/B7 EfficientNet models.
2019-10-30 16:49:17 -07:00
62105ed4a0
Better differentiate sotabench WSL, SSL, and SWSL models via model_desc
2019-10-20 13:17:25 -07:00
c099374771
Map pretrained checkpoint to cpu to avoid issue with some pretrained checkpoints still having CUDA tensors. Fixes #42
2019-10-19 17:27:46 -07:00
b93fcf0708
Add Facebook Research Semi-Supervised and Semi-Weakly Supervised ResNet model weights.
2019-10-19 17:05:37 -07:00
a9eb484835
Add memory efficient Swish impl
2019-10-19 14:48:30 -07:00
187ecbafbe
Add support for loading args from yaml file (and saving them with each experiment)
2019-09-09 17:56:45 -07:00
d3ba34ee7e
Fix Mobilenet V3 model name for sotabench. Minor res2net cleanup.
2019-09-05 15:47:56 -07:00
Ross Wightman
Ross Wightman
Dushyant Mehta