65a634626f
Switch random erasing to doing normal_() on CPU to avoid instability, remove a debug print
2019-06-29 10:03:13 -07:00
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
9d653b68a2
Make drop_connect rate scaling match official impl. Fixes #14
2019-06-25 09:30:36 -07:00
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
a0275cfa2f
Fix arg positions in two entrypoint aliases
2019-06-24 08:25:14 -07:00
fe59249701
Bump version to 0.1.2
2019-06-23 18:27:30 -07:00
171c0b88b6
Add model registry and model listing fns, refactor model_factory/create_model fn
2019-06-23 18:22:16 -07:00
8512436436
Add instagram pretrained ResNeXt models from https://pytorch.org/hub/facebookresearch_WSL-Images_resnext/ , update README
2019-06-23 12:29:02 -07:00
1202d053bc
markdown in setup.py
2019-06-21 14:08:43 -07:00
87b92c528e
Some pretrianed URL changes
...
* host some of Cadene's weights on github instead of .fr for speed
* add my old port of ensemble adversarial inception resnet v2
* switch to my TF port of normal inception res v2 and change FC layer back to 'classif' for compat with ens_adv
2019-06-21 13:57:08 -07:00
827a3d6010
Add current checkpoints output back to CheckpointSaver (via logger)
2019-06-21 11:57:43 -07:00
63961b36a2
Missed pnasnet entrypoint
2019-06-20 23:34:20 -07:00
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
b20bb58284
Distributed tweaks
...
* Support PyTorch native DDP as fallback if APEX not present
* Support SyncBN for both APEX and Torch native (if torch >= 1.1)
* EMA model does not appear to need DDP wrapper, no gradients, updated from wrapped model
2019-06-20 22:30:23 -07:00
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
1d7f2d93a6
Python >= 3.6 requirement
2019-06-19 17:28:08 -07:00
aa4354f466
Big re-org, working towards making pip/module as 'timm'
2019-06-19 17:20:51 -07:00
871f4c1b0c
Change some absolute imports to relative
2019-06-19 16:08:58 -07:00
b9f8d40b10
Fix pretrained override logic for validate, checkpoint always trump pretrained flag during model create
2019-06-19 15:23:16 -07:00
0e1fd11ad8
Merge pull request #12 from rwightman/ema-cleanup
...
Model weights Exponential Moving Average
2019-06-18 12:37:16 -07:00
1019414fd2
Add ported Tensorflow EfficientNet B4/B5 weights
2019-06-18 09:50:36 -07:00
c9a61b7d98
Add gitignore
2019-06-18 08:44:23 -07:00
c6b8259ad6
Update README.md
...
Add blurb about python environment
2019-06-14 10:51:54 -07:00
f3134973b5
Add the MnasNet-B1 variant weights, add A1/B1 model names as in the stand-alone repo, remove a bit of unused code
2019-06-14 09:08:02 -07:00
c1a84ecb22
dataset not passed through PrefetchLoader for inference script. Fix #10
...
* also, make top5 configurable for lower class count cases
2019-06-11 21:59:56 -07:00
2060e433c0
Add native PyTorch weights for SE-MnasNet aka MnasNet-A1
2019-06-11 08:54:54 -07:00
7dab6d1ec7
Default to img_size in model default_cfg, defer output folder creation until later in the init sequence
2019-06-10 13:34:42 -07:00
7d17394bdc
Add native PyTorch weights for EfficientNet-B0 w/ top-1 > 76.9
...
* also add pooling details to default cfg for efficiennets so testtimepool wrapper works
2019-06-10 13:11:36 -07:00
9bcd65181b
Add exponential moving average for model weights + few other additions and cleanup
...
* ModelEma class added to track an EMA set of weights for the model being trained
* EMA handling added to train, validation and clean_checkpoint scripts
* Add multi checkpoint or multi-model validation support to validate.py
* Add syncbn option (APEX) to train script for experimentation
* Cleanup interface of CheckpointSaver while adding ema functionality
2019-06-07 15:39:36 -07:00
105d5702d7
Update README.md
2019-06-04 10:23:36 -07:00
6688d0669f
PyTorch trained MobileNetV3 weights that match/best paper. Update fbnetc weights to improved copy.
2019-06-04 09:51:05 -07:00
89e77ec049
Merge pull request #7 from zhunzhong07/patch-2
...
Correct name
2019-06-03 13:00:19 -07:00
b32361c9f8
Correct name
2019-06-03 20:33:04 +10:00
ff99625603
Missed a few models in the model/_all_ list for senet
2019-05-31 10:51:18 -07:00
99122aac1c
Replace ResNet-34 default weights with a great result from my experiments.
2019-05-31 10:42:46 -07:00
48ab3cf070
Add Apache LICENSE file
2019-05-31 07:24:03 -07:00
4bb5e9b224
Ported Tensorflow pretrained EfficientNet weights and some model cleanup
...
* B0-B3 weights ported from TF with close to paper accuracy
* Renamed gen_mobilenet to gen_efficientnet since scaling params go well beyond 'mobile' specific
* Add Tensorflow preprocessing option for closer images to source repo
2019-05-30 17:55:35 -07:00
4efecfdc47
Add drop_connect impl to try during training, fix a few comments
2019-05-30 08:42:12 -07:00
0fc4cca2ff
Cleanup unused member with old name
2019-05-29 23:44:01 -07:00
7a6d61566e
Add EfficientNet impl, change existing depth_multipler -> channel_multiplier as definitions have been confused
2019-05-29 23:32:52 -07:00
6bff9c75dc
Cleanup model_factory imports, consistent __all__ for models, fixed inception_v4 weight url
2019-05-28 21:41:10 -07:00
e6c14427c0
More appropriate/correct loss name
2019-05-28 21:41:10 -07:00
99ab1b1276
Update README.md
2019-05-26 18:48:35 -07:00
c2de3a922b
Update README.md
2019-05-26 18:46:12 -07:00
337702d51b
Merge pull request #2 from zhunzhong07/patch-1
...
Fix bug for prefetcher
2019-05-26 09:31:40 -07:00
127487369f
Fix bug for prefetcher
...
Set input and target to Cuda when without using prefetcher.
2019-05-26 15:37:19 +10:00
e8cf619005
Update gluon_resnet.py
...
Update header comment
2019-05-24 00:01:37 -07:00
7419e9835f
Add MxNet Gluon ResNet variants w/ converted pretrained weights. Very well trained set of models.
2019-05-23 23:52:23 -07:00
2da0b4dbc1
Add inception_v3 models via torchvision, 4 different pretrained weight choices
2019-05-23 11:07:06 -07:00
af1a68d2e1
Update README.md
2019-05-20 14:55:56 -07:00
Ross Wightman
Ross Wightman
Zhun Zhong