Ross Wightman
1d4ac1b165
Bump version for pypi release. Fix #130
2020-04-27 18:02:40 -07:00
Ross Wightman
be7c784d21
Small TResNet simplification, just use SelectAdaptivePool, don't notice any perf difference
2020-04-27 17:50:19 -07:00
Ross Wightman
e3a98171b2
Remove some CRLF that made it into TResNet merge
2020-04-27 13:23:41 -07:00
Ross Wightman
0004f37d25
Some TResNet cleanup.
...
* allow use of global pool arg, test-time-pooling
* clean checkpoints to just contain state dict, add 448 res checkpoints
* support DataParallel via lazy filter creation for JIT Downsample
* some minor formatting (mostly alignment) preferences
2020-04-27 13:21:05 -07:00
Ross Wightman
64fe37d008
Remove old mean/std helper, rely fully on cmd line or default_cfg now. Fixes #126
2020-04-27 12:32:55 -07:00
Ross Wightman
e6f24e5578
Add 'momentum' optimizer (SGD w/o nesterov) for stable EfficientDet training defaults
2020-04-25 19:42:13 -07:00
Sepehr Sameni
20290b5b56
fix typo in eca
2020-04-14 15:20:35 +04:30
Ross Wightman
ebf82b84ac
Merge pull request #122 from mrT23/master
...
TResNet models
2020-04-12 18:23:46 -07:00
Alexey Chernov
bdb165a8a4
Merge changes in feature extraction interface to MobileNetV3
...
Experimental feature extraction interface seems to be changed
a little bit with the most up to date version apparently found
in EfficientNet class. Here these changes are added to
MobileNetV3 class to make it support it and work again, too.
2020-04-13 02:02:14 +03:00
talrid
8a63c1add8
finalizing
2020-04-12 19:08:35 +03:00
talrid
6209146738
TResNet models
2020-04-12 18:44:12 +03:00
Ross Wightman
13cf68850b
Remove poorly named metrics from torch imagenet example origins. Use top1/top5 in csv output for consistency with existing validation results files, acc elsewhere. Fixes #111
2020-04-10 14:41:08 -07:00
Ross Wightman
56608c9070
Bump version for pypi
2020-04-09 01:46:05 -07:00
Ross Wightman
1a8f5900ab
Update EfficientNet feature extraction for EfficientDet. Add needed MaxPoolSame as well.
2020-04-09 01:41:54 -07:00
Chris Ha
06a50a94a8
Fix minor typos in create_attn.py and resnet.py
...
'eca'->'ceca'
and
doest not-> does not
2020-04-07 21:15:57 +09:00
Ross Wightman
1a9ab07307
One too many changes at a time, fix missing C
2020-04-07 21:12:08 +09:00
Ross Wightman
f17b42bc33
Blur filter no longer a buffer
2020-04-07 21:12:08 +09:00
Ross Wightman
6cdeca24a3
Some cleanup and fixes for initial BlurPool impl. Still some testing and tweaks to go...
2020-04-07 21:12:08 +09:00
Chris Ha
acd1b6cccd
Implement Functional Blur on resnet.py
...
1. add ResNet argument blur=''
2. implement blur for maxpool and strided convs in downsampling blocks
2020-04-07 21:12:08 +09:00
Chris Ha
ce3d82b58b
Update blurpool.py
...
clean up code for PR
2020-04-07 21:12:07 +09:00
Chris Ha
3a287a6e76
Create blurpool.py
...
Initial implementation of blur layer.
currently tests as correct against Downsample of original github
2020-04-07 21:12:07 +09:00
Ross Wightman
c99a5abed4
Merge pull request #115 from rwightman/mobilenetv2-experiment
...
MobileNet-V2 experiments
2020-04-05 17:32:06 -07:00
Ross Wightman
e34074b4da
Add final weights for MobileNet-V2 experiments
2020-04-05 17:31:02 -07:00
Ross Wightman
a6a5565de7
Fiddling...
2020-03-19 10:20:20 -07:00
Ross Wightman
5a16c533ff
Add better resnext50_32x4d weights trained by andravin
2020-03-18 14:43:50 -07:00
Ross Wightman
bc998cad91
Experimenting with some MobileNetV2 variations to compare against EfficientNet-Lite
2020-03-18 13:54:06 -07:00
Ross Wightman
3406e582cf
Add EfficientNet-Lite results, update README
2020-03-18 13:12:30 -07:00
Ross Wightman
bd05258f7b
EfficientNet-Lite model added w/ converted checkpoints, validation in progress...
2020-03-17 23:31:45 -07:00
Andrew Lavin
d92cc4da54
Modified save_checkpoint to always save last checkpoint. Fixes #98 .
2020-03-09 22:41:33 -07:00
Ross Wightman
56e2ac3a6d
Merge pull request #94 from rwightman/lr_noise
...
Learning rate noise, MobileNetV3 weights, and activate MobileNetV3/EfficientNet weight init change
2020-02-29 20:41:05 -08:00
Ross Wightman
c16f25ced2
Add MobileNetV3 Large weights, results, update README and sotabench for merge
2020-02-29 20:37:20 -08:00
Ross Wightman
c60069c1eb
Annotate types on drop fns to avoid torchscript error
2020-02-27 09:30:23 -08:00
Ross Wightman
9fee316752
Enable fixed fanout calc in EfficientNet/MobileNetV3 weight init by default. Fix #84
2020-02-24 15:11:26 -08:00
Ross Wightman
27b3680d49
Revamp LR noise, move logic to scheduler base. Fixup PlateauLRScheduler and add it as an option.
2020-02-22 16:23:15 -08:00
Ross Wightman
cc5a11abba
version bump for PyPi update
2020-02-22 10:26:19 -08:00
Ross Wightman
514b0938c4
Experimenting with per-epoch learning rate noise w/ step scheduler
2020-02-21 11:51:05 -08:00
Ross Wightman
43225d110c
Unify drop connect vs drop path under 'drop path' name, switch all EfficientNet/MobilenetV3 refs to 'drop_path'. Update factory to handle new drop args.
2020-02-18 14:00:26 -08:00
Ross Wightman
f1d5f8a6c4
Update comments for Selective Kernel and DropBlock/Path impl, add skresnet34 weights
2020-02-18 13:58:30 -08:00
Ross Wightman
670c61b28f
Some cutmix/mixup cleanup/fixes
2020-02-17 11:00:54 -08:00
Ross Wightman
b3cb5f3275
Working on CutMix impl as per #8 , integrating with Mixup, currently experimenting...
2020-02-16 20:09:11 -08:00
Ross Wightman
569419b38d
Tweak some comments, add SKNet models with weights to sotabench, remove an unused branch
2020-02-15 21:18:25 -08:00
Ross Wightman
53c47479c4
Batch validation batch size adjustment, tweak L2 crop pct
2020-02-15 20:37:04 -08:00
Ross Wightman
08553e16b3
Merge branch 'master' into attention
2020-02-14 18:24:21 -08:00
Ross Wightman
fa38f24967
Update SK network configs, add weights for skresnet8 and skresnext50
2020-02-14 15:37:00 -08:00
Ross Wightman
f098fda2ca
Add map_location='cpu' to ModelEma resume, should improve #72
2020-02-12 13:23:56 -08:00
Ross Wightman
ba15ca47e8
Add ported EfficientNet-L2, B0-B7 NoisyStudent weights from TF TPU
2020-02-12 11:26:38 -08:00
Ross Wightman
5e6dbbaf30
Add CBAM for experimentation
2020-02-10 16:23:09 -08:00
Ross Wightman
d725991870
Remove debug print from ECA module
2020-02-10 16:21:33 -08:00
Ross Wightman
2a7d256fd5
Re-enable mem-efficient/jit activations after torchscript tests
2020-02-10 11:59:36 -08:00
Ross Wightman
f902bcd54c
Layer refactoring continues, ResNet downsample rewrite for proper dilation in 3x3 and avg_pool cases
...
* select_conv2d -> create_conv2d
* added create_attn to create attention module from string/bool/module
* factor padding helpers into own file, use in both conv2d_same and avg_pool2d_same
* add some more test eca resnet variants
* minor tweaks, naming, comments, consistency
2020-02-10 11:55:03 -08:00
