1cf3ea0467
Update README.md
2019-04-21 16:49:00 -07:00
bc264269c9
Morph mnasnet impl into a generic mobilenet that covers Mnasnet, MobileNetV1/V2, ChamNet, FBNet, and related
...
* add an alternate RMSprop opt that applies eps like TF
* add bn params for passing through alternates and changing defaults to TF style
2019-04-21 15:54:28 -07:00
e9c7961efc
Fix pooling in mnasnet, more sensible default for AMP opt level
2019-04-17 18:06:37 -07:00
996c77aa94
Prep mnasnet for pretrained models, use the select global pool, some comment mistakes
2019-04-15 16:58:40 -07:00
6b4f9ba223
Add MNASNet A1, B1, and Small models as per the TF impl. Testing/training in progress...
2019-04-15 09:03:59 -07:00
c88e80081d
Fix missing cfg key check
2019-04-15 09:03:59 -07:00
073d31a076
Update README.md
2019-04-14 15:19:58 -07:00
7ba78aaaeb
Update README.md
2019-04-14 15:14:37 -07:00
e8e8bce335
Create README.md
2019-04-14 15:10:52 -07:00
9e296dbffb
Add seresnet26_32x4d cfg and weights + interpolation str->PIL enum fn
2019-04-14 13:43:46 -07:00
71afec86d3
Loader tweaks
2019-04-13 14:52:38 -07:00
79f615639e
Add pretrained weights for seresnet18
2019-04-13 14:52:21 -07:00
8a33a6c90a
Add checkpoint clean script, add link to pretrained resnext50 weights
2019-04-13 14:15:35 -07:00
6e9697eb9c
Fix small bug in seresnet input size and eval transform handling of img size
2019-04-13 10:06:43 -07:00
db1fe34d0c
Update a few comment, add some references
2019-04-12 23:16:49 -07:00
0562b91c38
Add per model crop pct, interpolation defaults, tie it all together
...
* create one resolve fn to pull together model defaults + cmd line args
* update attribution comments in some models
* test update train/validation/inference scripts
2019-04-12 22:55:24 -07:00
c328b155e9
Random erasing crash fix and args pass through
2019-04-11 22:06:43 -07:00
9c3859fb9c
Uniform pretrained model handling.
...
* All models have 'default_cfgs' dict
* load/resume/pretrained helpers factored out
* pretrained load operates on state_dict based on default_cfg
* test all models in validate
* schedule, optim factor factored out
* test time pool wrapper applied based on default_cfg
2019-04-11 21:32:16 -07:00
63e677d03b
Merge branch 'master' of github.com:rwightman/pytorch-models
2019-04-10 14:55:54 -07:00
0bc50e84f8
Lots of refactoring and cleanup.
...
* Move 'test time pool' to Module that can be used by any model, remove from DPN
* Remove ResNext model file and combine with ResNet
* Remove fbresnet200 as it was an old conversion and pretrained performance not worth param count
* Cleanup adaptive avgmax pooling and add back conctat variant
* Factor out checkpoint load fn
2019-04-10 14:53:34 -07:00
f1cd1a5ce3
Cleanup CheckpointSaver, add support for increasing or decreasing metric, switch to prec1 metric in train loop
2019-04-07 10:22:55 -07:00
c0e6e5f3db
Add common model interface to pnasnet and xception, update factory
2019-04-06 13:59:15 -07:00
f2029dfb65
Add smooth loss
2019-04-05 20:50:26 -07:00
b0158a593e
Fix distributed train script
2019-04-05 20:49:58 -07:00
183d8e4aef
Xception model working
2019-04-05 12:09:25 -07:00
1e23727f2f
Update inference script for new loader style
2019-04-05 11:58:16 -07:00
58571e992e
Change block avgpool in senets to mean for performance issues with NVIDIA and AMP especially
2019-04-05 10:53:13 -07:00
5180f94c7e
Distributed (multi-process) train, multi-gpu single process train, and NVIDIA AMP support
2019-04-05 10:53:04 -07:00
6f9a0c8ef2
Merge branch 'master' of github.com:rwightman/pytorch-models
2019-04-01 11:07:05 -07:00
5cb1a35c6b
Fixup Resnext, remove alternate shortcut types
2019-04-01 11:03:37 -07:00
d87824bd65
Merge branch 'master' of github.com:rwightman/pytorch-models
2019-03-17 09:57:36 -07:00
45cde6f0c7
Improve creation of data pipeline with prefetch enabled vs disabled, fixup inception_res_v2 and dpn models
2019-03-11 22:17:42 -07:00
321435e6b4
Update resnext init
2019-03-10 14:24:53 -07:00
2295cf56c2
Add some Nvidia performance enhancements (prefetch loader, fast collate), and refactor some of training and model fact/transforms
2019-03-10 14:23:16 -07:00
9d927a389a
Add adabound, random erasing
2019-03-01 22:03:42 -08:00
1577c52976
Resnext added, changes to bring it and seresnet in line with rest of models
2019-03-01 15:44:04 -08:00
e0cfeb7d8e
Add some models, remove a model, tweak some models
2019-03-01 13:08:35 -08:00
31055466fc
Fixup validate/inference script args, fix senet init for better test accuracy
2019-02-22 14:07:50 -08:00
b1a5a71151
Update schedulers
2019-02-17 12:50:15 -08:00
b5255960d9
Tweaking tanh scheduler, senet weight init (for BN), transform defaults
2019-02-13 23:11:09 -08:00
48360625f2
Cycle limit on tanh sched
2019-02-08 21:47:27 -08:00
824f42e75e
Forgot to include Tanh scheduler
2019-02-08 21:14:47 -08:00
a336e5bff3
Minor updates
2019-02-08 20:56:24 -08:00
cf0c280e1b
Cleanup tranforms, add custom schedulers, tweak senet34 model
2019-02-06 20:19:11 -08:00
c57717d325
Fix tta train bug, improve logging
2019-02-02 10:17:04 -08:00
72b4d162a2
Increase training performance
2019-02-01 22:48:31 -08:00
5855b07ae0
Initial commit, puting some ol pieces together
2019-02-01 22:07:34 -08:00
Ross Wightman
Ross Wightman