722 Commits

Author SHA1 Message Date
Ross Wightman
9816ca3ab4 Add EdgeTPU models to sotabench, remove some unicode chars from model names 2019-08-24 14:42:51 -07:00
Ross Wightman
9ec6824bab Finally got around to adding EdgeTPU EfficientNet variant 2019-08-24 13:39:49 -07:00
Ross Wightman
daeaa113e2 Add initial sotabench attempt. Split create_transform out of create_loader. Update requirements.txt 2019-08-12 23:06:19 -07:00
Ross Wightman
66634d2200 Add support to split random erasing blocks into randomly selected number with --recount arg. Fix random selection of aspect ratios. 2019-08-12 16:01:58 -07:00
Ross Wightman
6946281fde Experimenting with random erasing changes 2019-08-12 16:01:58 -07:00
Ross Wightman
aeaaad7304
Merge pull request #24 from rwightman/gluon_xception
Port Gluon Aligned Xception models
2019-08-11 23:08:21 -07:00
Ross Wightman
3b4868f6dc A few more additions to Gluon Xception models to match interface of others. 2019-08-11 23:06:23 -07:00
Ross Wightman
f937e2a600
Merge pull request #23 from aovoc/patch-1
Update helpers.py
2019-08-10 15:47:40 -07:00
Ross Wightman
4d505e0785 Add working Gluon Xception-65 model. Some cleanup still needed. 2019-08-10 13:52:01 -07:00
Minqin Chen
4e7a854dd0
Update helpers.py
Fixing out of memory error by loading the checkpoint onto the CPU.
2019-08-11 04:21:39 +08:00
Ross Wightman
0c874195db Update results csv files, bump version for timm pip release 2019-08-05 11:33:17 -07:00
Ross Wightman
9b35818811
Update README.md 2019-08-03 09:32:08 -07:00
Ross Wightman
4fe2da558c Add MixNet Small and Large PyTorch native weights (no same padding) 2019-08-02 23:22:48 -07:00
Ross Wightman
15e66863b1
Update README.md 2019-07-31 14:41:31 -07:00
Ross Wightman
e879cf52fa Update validation scores for new TF EfficientNet weights. 2019-07-31 14:38:55 -07:00
Ross Wightman
b35050a144
Update README.md 2019-07-30 18:33:40 -07:00
Ross Wightman
77e2e0c4e3 Add new auto-augmentation Tensorflow EfficientNet weights, incl B6 and B7 models. Validation scores still pending but looking good. 2019-07-30 18:31:02 -07:00
Ross Wightman
857f33015a Add native PyTorch weights for MixNet-Medium with no SAME padding necessary. Remove unused block of code. 2019-07-29 11:59:15 -07:00
Ross Wightman
e7c8a37334 Make min-lr and cooldown-epochs cmdline args, change dash in color_jitter arg for consistency 2019-07-26 09:35:31 -07:00
Ross Wightman
d4debe6597 Update version, results csv files, and move remaining dropbox weights to github 2019-07-25 16:54:44 -07:00
Ross Wightman
dfa9298b4e Add MixNet (https://arxiv.org/abs/1907.09595) with pretrained weights converted from Tensorflow impl
* refactor 'same' convolution and add helper to use MixedConv2d when needed
* improve performance of 'same' padding for cases that can be handled statically
* add support for extra exp, pw, and dw kernel specs with grouping support to decoder/string defs for MixNet
* shuffle some args for a bit more consistency, a little less clutter overall in gen_efficientnet.py
2019-07-25 11:42:01 -07:00
Ross Wightman
7a92caa560 Add basic image folder style dataset to read directly out of tar files, example in validate.py 2019-07-25 10:51:03 -07:00
Ross Wightman
d6ac5bbc48 EfficientNet and related cleanup
* remove folded_bn support and corresponding untrainable tflite ported weights
* combine bn args into dict
* add inplace support to activations and use where possible for reduced mem on large models
2019-07-22 09:29:58 -07:00
Ross Wightman
c11973602d
Merge pull request #19 from rwightman/resnet-refactor
Resnet refactoring
2019-07-20 08:47:21 -07:00
Ross Wightman
d97510fd4a Add new results csv and update README with 3 new ResNet weight results 2019-07-20 08:45:05 -07:00
Ross Wightman
3d9be78fc6 A bit more ResNet cleanup.
* add inplace=True back
* minor comment improvements
* few clarity changes
2019-07-19 16:44:35 -07:00
Ross Wightman
33436fafad Add weights for ResNeXt50d model 2019-07-19 14:09:10 -07:00
Ross Wightman
e78cd79073 Move ResNet additions for Gluon into main ResNet impl. Add ResNet-26 and ResNet-26d models with weights. 2019-07-14 18:17:35 -07:00
Ross Wightman
c37cb0f2b7 ImageNet-1k vs ImageNet-v2 comparison 2019-07-06 17:19:56 -07:00
Ross Wightman
6cdf35e670 Add explicit half/fp16 support to loader and validation script 2019-07-05 13:52:25 -07:00
Ross Wightman
5684c6af32
Update README.md
Add blurb about results csv
2019-07-04 10:52:03 -07:00
Ross Wightman
a6b2f6eca5 Update README, bump version 2019-07-03 22:48:33 -07:00
Ross Wightman
2a1d09b4c0 Add result csv with summary of all pretrained models 2019-07-03 22:34:36 -07:00
Ross Wightman
edb425ea48 Add crop_pct arg to validate, extra fields to csv output, 'all' filters pretrained 2019-07-03 22:28:07 -07:00
Ross Wightman
949b7a81c4 Fix typo in Densenet default resolutions 2019-07-03 22:11:26 -07:00
Ross Wightman
da52fcf78a Add NASNet-Large model 2019-07-03 22:10:50 -07:00
Ross Wightman
f632190fd9 Add .gitattributes 2019-07-01 21:44:50 -07:00
Ross Wightman
5bc0ed3d7c Grammar 2019-07-01 15:15:21 -07:00
Ross Wightman
c89acdfc02
Update EffResNetComparison.ipynb 2019-07-01 14:57:11 -07:00
Ross Wightman
73642f7462 Adjust notebook path 2019-07-01 14:16:18 -07:00
Ross Wightman
c30f625215 Update EffResNetComparison 2019-07-01 14:07:47 -07:00
Ross Wightman
c4916897f8 EfficientNet vs ResNet comparison in Colaboratory 2019-07-01 13:55:47 -07:00
Ross Wightman
6057496409 Register dpn107 2019-06-30 09:57:06 -07:00
Ross Wightman
3d1a66b6fc Version 0.1.6 2019-06-30 09:55:23 -07:00
Ross Wightman
a6878b5218 Fix DPN config keys that I broke 2019-06-30 09:54:52 -07:00
Ross Wightman
8a05b8d555
Merge pull request #16 from rwightman/misc-epoch
Weights, arguments, epoch counting, and more
2019-06-29 16:59:11 -07:00
Ross Wightman
9b0070edc9 Add two comments back, fix typo 2019-06-29 16:44:25 -07:00
Ross Wightman
188aeae8f4 Bump version 0.1.4 2019-06-29 16:17:54 -07:00
Ross Wightman
c3287aafb3 Slight improvement in EfficientNet-B2 native PyTorch weights 2019-06-29 16:17:29 -07:00
Ross Wightman
b8762cc67d Model updates. Add my best ResNet50 weights top-1=78.47. Add some other torchvision weights.
* Remove some models that don't exist as pretrained an likely never will (se)resnext152
* Add some torchvision weights as tv_ for models that I have added better weights for
* Add wide resnet recently added to torchvision along with resnext101-32x8d
* Add functionality to model registry to allow filtering on pretrained weight presence
2019-06-29 15:50:33 -07:00