masafumi
047a5ec05f
Fix bugs that Mixup does not work device=cpu
2021-10-12 23:51:46 +09:00
Ross Wightman
cd34913278
Remove some outdated comments, botnet networks working great now.
2021-10-11 22:43:41 -07:00
Ross Wightman
6ed4cdccca
Update lambda_resnet26t weights with better set
2021-10-10 16:32:54 -07:00
ICLR Author
44d6d51668
Add ConvMixer
2021-10-09 21:09:51 -04:00
Ross Wightman
a85df34993
Update lambda_resnet26rpt weights to 78.9, add better halonet26t weights at 79.1 with tweak to attention dim
2021-10-08 17:44:13 -07:00
Ross Wightman
b544ad4d3f
regnetz model default cfg tweaks
2021-10-06 21:14:59 -07:00
Ross Wightman
e5da481073
Small post-merge tweak for freeze/unfreeze, add to __init__ for utils
2021-10-06 17:00:27 -07:00
Ross Wightman
5ca72dcc75
Merge branch 'freeze-functionality' of https://github.com/alexander-soare/pytorch-image-models into alexander-soare-freeze-functionality
2021-10-06 16:51:03 -07:00
Ross Wightman
e2b8d44ff0
Halo, bottleneck attn, lambda layer additions and cleanup along w/ experimental model defs
...
* align interfaces of halo, bottleneck attn and lambda layer
* add qk_ratio to all of above, control q/k dim relative to output dim
* add experimental haloregnetz, and trionet (lambda + halo + bottle) models
2021-10-06 16:32:48 -07:00
Alexander Soare
431e60c83f
Add acknowledgements for freeze_batch_norm inspiration
2021-10-06 14:28:49 +01:00
Ross Wightman
fbf59c04ee
Change crop ratio on correct resnet50 variant.
2021-10-04 22:31:08 -07:00
Ross Wightman
ae1ff5792f
Clean a1/a2/3 rsb _0 checkpoints properly, fix v2 loading.
2021-10-04 16:46:00 -07:00
Ross Wightman
93901e992f
Version bump to 0.5.0 for pending release post RSB and ATTN updates
2021-10-03 17:34:57 -07:00
Ross Wightman
da0d39bedd
Update default crop_pct for byoanet
2021-10-03 17:33:16 -07:00
Ross Wightman
cc9bedf373
Add initial ResNet Strikes Back weights for ResNet50 and ResNetV2-50 models
2021-10-03 17:32:02 -07:00
Ross Wightman
64495505b7
Add updated lambda resnet26 and botnet26 checkpoints with fixes applied
2021-10-03 17:31:39 -07:00
Ross Wightman
b2094f4ee8
support bits checkpoints in avg/load
2021-10-03 17:31:22 -07:00
Ross Wightman
007bc39323
Some halo and bottleneck attn code cleanup, add halonet50ts weights, use optimal crop ratios
2021-10-02 15:51:42 -07:00
Alexander Soare
65c3d78b96
Freeze unfreeze functionality finalized. Tests added
2021-10-02 15:55:08 +01:00
Alexander Soare
0cb8ea432c
wip
2021-10-02 15:55:08 +01:00
Ross Wightman
b1c2e3eb92
Match rel_pos_indices attr rename in conv branch
2021-09-30 23:19:05 -07:00
Ross Wightman
b49630a138
Add relative pos embed option to LambdaLayer, fix last transpose/reshape.
2021-09-30 22:45:09 -07:00
Ross Wightman
d657e2cc0b
Remove dead code line from efficientnet
2021-09-30 21:54:42 -07:00
Ross Wightman
0ca687f224
Make 'regnetz' model experiments closer to actual RegNetZ, bottleneck expansion, expand from in_chs, no shortcut on stride 2, tweak model sizes
2021-09-30 21:49:38 -07:00
leondgarse
51eaf9360d
Remove a duplicate layer creation in byobnet.py
...
`self.conv2_kxk` is repeated in `byobnet.py`. Remove the duplicate code.
2021-09-30 18:30:48 +08:00
Ross Wightman
b81e79aae9
Fix bottleneck attn transpose typo, hopefully these train better now..
2021-09-28 16:38:41 -07:00
Ross Wightman
80075b0b8a
Add worker_seeding arg to allow selecting old vs updated data loader worker seed for (old) experiment repeatability
2021-09-28 16:37:45 -07:00
Ross Wightman
6478bcd02c
Fix regnetz_d conv layer name, use inception mean/std
2021-09-26 14:54:17 -07:00
Ross Wightman
0387e6057e
Update binary cross ent impl to use thresholding as an option (convert soft targets from mixup/cutmix to 0, 1)
2021-09-23 15:45:39 -07:00
Ross Wightman
f8a63a3b71
Add worker_init_fn to loader for numpy seed per worker
2021-09-23 15:44:38 -07:00
Ross Wightman
515121cca1
Use reshape instead of view in std_conv, causing issues in recent PyTorch in channels_last
2021-09-23 15:43:48 -07:00
Ross Wightman
da06cc61d4
ResNetV2 seems to work best without zero_init residual
2021-09-23 15:43:22 -07:00
Ross Wightman
8e11da0ce3
Add experimental RegNetZ(ish) models for training / perf trials.
2021-09-23 15:42:57 -07:00
Alexander Soare
6bbc50beb4
make it possible to provide norm_layer via create_model
2021-09-21 10:19:04 +01:00
Ross Wightman
cf5ac2800c
BotNet models were still off, remove weights for bad configs. Add good SE-HaloNet33-TS weights.
2021-09-13 17:18:59 -07:00
Ross Wightman
24720abe3b
Merge branch 'master' into attn_update
2021-09-13 16:51:10 -07:00
Ross Wightman
1c9284c640
Add BeiT 'finetuned' 1k weights and pretrained 22k weights, pretraining specific (masked) model excluded for now
2021-09-13 16:38:23 -07:00
Ross Wightman
f8a215cfe6
A few more crossvit tweaks, fix training w/ no_weight_decay names, add crop option for scaling, adjust default crop_pct for large img size to 1.0 for better results
2021-09-13 14:17:34 -07:00
Ross Wightman
7ab2491ab7
Better handling of crossvit for tests / forward_features, fix torchscript regression in my changes
2021-09-13 13:01:05 -07:00
Ross Wightman
f1808e0970
Post crossvit merge cleanup, change model names to reflect input size, cleanup img size vs scale handling, fix tests
2021-09-13 11:49:54 -07:00
Ross Wightman
4027412757
Add resnet33ts weights, update resnext26ts baseline weights
2021-09-09 14:46:41 -07:00
Richard Chen
9fe5798bee
fix bug for reset classifier and fix for validating the dimension
2021-09-08 21:58:17 -04:00
Richard Chen
3718c5a5bd
fix loading pretrained model
2021-09-08 11:53:05 -04:00
Richard Chen
bb50b69a57
fix for torch script
2021-09-08 11:20:59 -04:00
Ross Wightman
5bd04714e4
Cleanup weight init for byob/byoanet and related
2021-09-05 15:34:05 -07:00
Ross Wightman
8642401e88
Swap botnet 26/50 weights/models after realizing a mistake in arch def, now figuring out why they were so low...
2021-09-05 15:17:19 -07:00
Ross Wightman
5f12de4875
Add initial AttentionPool2d that's being trialed. Fix comment and still trying to improve reliability of sgd test.
2021-09-05 12:41:14 -07:00
Ross Wightman
76881d207b
Add baseline resnet26t @ 256x256 weights. Add 33ts variant of halonet with at least one halo in stage 2,3,4
2021-09-04 14:52:54 -07:00
Ross Wightman
484e61648d
Adding the attn series weights, tweaking model names, comments...
2021-09-03 18:09:42 -07:00
Ross Wightman
fb94350896
Update training script and loader factory to allow use of scheduler updates, repeat augment, and bce loss
2021-09-01 17:46:40 -07:00
