Ross Wightman
2393708650
Missed stashing of out_indices in model
2019-11-28 17:00:52 -08:00
Ross Wightman
35e8f0c5e7
Fixup a few comments, add PyTorch version aware Flatten and finish as_sequential for GenEfficientNet
2019-11-28 17:00:52 -08:00
Ross Wightman
506df0e3d0
Add CondConv support for EfficientNet into WIP for GenEfficientNet Feature extraction setup
2019-11-28 17:00:52 -08:00
Ross Wightman
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
Ross Wightman
0d58c50fb1
Add TF RandAug weights for B5/B7 EfficientNet models.
2019-10-30 16:49:17 -07:00
Ross Wightman
a9eb484835
Add memory efficient Swish impl
2019-10-19 14:48:30 -07:00
Ross Wightman
73fbd97ed4
Add weights for my MixNet-XL creation, include README updates for EdgeTPU models
2019-08-24 19:57:42 -07:00
Ross Wightman
51a2375b0c
Experimenting with a custom MixNet-XL and MixNet-XXL definition
2019-08-24 19:57:42 -07:00
Ross Wightman
9ec6824bab
Finally got around to adding EdgeTPU EfficientNet variant
2019-08-24 13:39:49 -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
e879cf52fa
Update validation scores for new TF EfficientNet weights.
2019-07-31 14:38:55 -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
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
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
9b0070edc9
Add two comments back, fix typo
2019-06-29 16:44:25 -07:00
Ross Wightman
c3287aafb3
Slight improvement in EfficientNet-B2 native PyTorch weights
2019-06-29 16:17:29 -07:00
Ross Wightman
c6b32cbe73
A number of tweaks to arguments, epoch handling, config
...
* reorganize train args
* allow resolve_data_config to be used with dict args, not just arparse
* stop incrementing epoch before save, more consistent naming vs csv, etc
* update resume and start epoch handling to match above
* stop auto-incrementing epoch in scheduler
2019-06-28 13:49:20 -07:00
Ross Wightman
9d653b68a2
Make drop_connect rate scaling match official impl. Fixes #14
2019-06-25 09:30:36 -07:00
Ross Wightman
13c19e213d
Add native PyTorch EfficientNet B1 and B2 weights. Not quite where I want them, but hitting the brick wall and moving on to other projects...
2019-06-24 13:12:04 -07:00
Ross Wightman
a0275cfa2f
Fix arg positions in two entrypoint aliases
2019-06-24 08:25:14 -07:00
Ross Wightman
171c0b88b6
Add model registry and model listing fns, refactor model_factory/create_model fn
2019-06-23 18:22:16 -07:00
Ross Wightman
6cc214bd7a
Consistency in model entrypoints
...
* move pretrained entrypoint arg to first pos to be closer to torchvision/hub
* change DPN weight URLS to my github location
2019-06-20 23:29:44 -07:00
Ross Wightman
6fc886acaf
Remove all prints, change most to logging calls, tweak alignment of batch logs, improve setup.py
2019-06-20 17:29:25 -07:00
Ross Wightman
aa4354f466
Big re-org, working towards making pip/module as 'timm'
2019-06-19 17:20:51 -07:00
