Ross Wightman
447677616f
version 0.5.5
2022-01-20 21:18:30 -08:00
Ross Wightman
83b40c5a58
Last batch of small model weights (for now). mobilenetv3_small 050/075/100 and updated mnasnet_small with lambc/lamb optimizer.
2022-01-19 10:02:02 -08:00
Mi-Peng
cdcd0a92ca
fix lars
2022-01-19 17:49:43 +08:00
Ross Wightman
1aa617cb3b
Add AvgPool2d anti-aliasing support to ResNet arch (as per OpenAI CLIP models), add a few blur aa models as well
2022-01-18 21:57:24 -08:00
Ross Wightman
f0f9eccda8
Add --fuser arg to train/validate/benchmark scripts to select jit fuser type
2022-01-17 13:54:25 -08:00
Ross Wightman
010b486590
Add Dino pretrained weights (no head) for vit models. Add support to tests and helpers for models w/ no classifier (num_classes=0 in pretrained cfg)
2022-01-17 12:20:02 -08:00
Ross Wightman
738a9cd635
unbiased=False for torch.var_mean path of ConvNeXt LN. Fix #1090
2022-01-17 09:25:06 -08:00
Ross Wightman
e0c4eec4b6
Default conv_mlp to False across the board for ConvNeXt, causing issues on more setups than it's improving right now...
2022-01-16 14:20:08 -08:00
Ross Wightman
b669f4a588
Add ConvNeXt 22k->1k fine-tuned and 384 22k-1k fine-tuned weights after testing
2022-01-15 15:44:36 -08:00
Ross Wightman
e967c72875
Update REAMDE.md. Sneak in g/G (giant / gigantic?) ViT defs from scaling paper
2022-01-14 16:28:27 -08:00
Ross Wightman
9ca3437178
Add some more small model weights lcnet, mnas, mnv2
2022-01-14 16:28:27 -08:00
Ross Wightman
fa6463c936
Version 0.5.4
2022-01-14 16:28:27 -08:00
Ross Wightman
fa81164378
Fix stem width for really small mobilenetv3 arch defs
2022-01-14 16:28:27 -08:00
Ross Wightman
edd3d73695
Add missing dropout for head reset in ConvNeXt default head
2022-01-14 16:28:27 -08:00
Ross Wightman
b093dcb46d
Some convnext cleanup, remove in place mul_ for gamma, breaking symbolic trace, cleanup head a bit...
2022-01-14 16:28:27 -08:00
Ross Wightman
18934debc5
Add initial ConvNeXt impl (mods of official code)
2022-01-14 16:28:27 -08:00
Ross Wightman
656757d26b
Fix MobileNetV2 head conv size for multiplier < 1.0. Add some missing modification copyrights, fix starting date of some old ones.
2022-01-14 16:28:27 -08:00
Ross Wightman
ccfeb06936
Fix out_indices handling breakage, should have left as per vgg approach.
2022-01-07 19:30:51 -08:00
Ross Wightman
a9f91483a6
Fix #1078 , DarkNet has 6 feature maps. Make vgg and darknet out_indices handling/comments equivalent
2022-01-07 15:08:32 -08:00
Ross Wightman
c21b21660d
visformer supports spatial feat map, update pool_size in pretrained cfg to match
2022-01-07 14:31:43 -08:00
Ross Wightman
9c11dfd9cb
Fix fbnetv3 pretrained cfg changes
2022-01-07 14:09:50 -08:00
Ross Wightman
1406cddc2e
FBNetV3 timm trained weights added for b/d/g variants. Update version to 0.5.2 for pypi release.
2022-01-07 12:05:08 -08:00
Ross Wightman
02ae11e526
Leaving repeat aug sampler indices as tensor thrashes worker shared process memory
2022-01-06 22:33:09 -08:00
Ross Wightman
4df51f3932
Add lcnet_100 and mnasnet_small weights
2022-01-06 22:21:05 -08:00
Ross Wightman
5ccf682a8f
Remove deprecated bn-tf train arg and create_model handler. Add evos/evob models back into fx test filter until norm_norm_norm branch merged.
2022-01-06 18:08:39 -08:00
Ross Wightman
b9a715c86a
Add more small model defs for MobileNetV3/V2/LCNet
2022-01-06 16:06:43 -08:00
Ross Wightman
b27c21b09a
Update drop_path and drop_block (fast impl) to be symbolically traceable, slightly faster
2022-01-06 16:04:58 -08:00
Ross Wightman
214c84a235
Disable use of timm nn.Linear wrapper since AMP autocast + torchscript use appears fixed
2022-01-06 16:01:51 -08:00
Hyeongchan Kim
a0b2657497
Use torch.repeat_interleave() to generate repeated indices faster ( #1058 )
...
* update: use numpy to generate repeated indices faster
* update: use torch.repeat_interleave() instead of np.repeat()
* refactor: remove unused import, numpy
* refactor: torch.range to torch.arange
* update: tensor to list before appending the extra samples
* update: concatenate the paddings with torch.cat
2022-01-02 14:01:06 -08:00
Ross Wightman
450ac6a0f5
Post merge tinynet fixes for pool_size, feature extraction
2021-12-21 23:51:54 -08:00
Ross Wightman
a04164cd75
Merge branch 'tinynet' of https://github.com/rsomani95/pytorch-image-models into rsomani95-tinynet
2021-12-21 22:45:56 -08:00
Rahul Somani
31bcd36e46
add tinynet models
2021-12-14 19:34:04 +05:30
KAI ZHAO
b4b8d1ec18
fix hard-coded strides
2021-12-14 17:22:54 +08:00
Ross Wightman
3dc71695bf
Merge pull request #989 from martinsbruveris/feat/resmlp-dino
...
Added DINO pretrained ResMLP models.
2021-11-24 09:26:07 -08:00
Ross Wightman
480c676ffa
Fix FX breaking assert in evonorm
2021-11-24 09:24:47 -08:00
Martins Bruveris
85c5ff26d7
Added DINO pretrained ResMLP models.
2021-11-24 15:02:46 +02:00
Ross Wightman
d633a014e6
Post merge cleanup. Fix potential security issue passing kwargs directly through to serialized web data.
2021-11-23 16:54:01 -08:00
Nathan Raw
b18c9e323b
Update helpers.py
2021-11-22 23:43:44 -05:00
Nathan Raw
308d0b9554
Merge branch 'master' into hf-save-and-push
2021-11-22 23:39:27 -05:00
Ross Wightman
f0507f6da6
Fix k_decay default arg != 1.0 in poly scheduler
2021-11-22 09:37:36 -08:00
Ross Wightman
1f53db2ece
Updated lamhalobotnet weights, 81.5 top-1
2021-11-21 19:49:51 -08:00
Ross Wightman
15ef108eb4
Add better halo2botnet50ts weights, 82 top-1 @ 256
2021-11-21 14:09:12 -08:00
Ross Wightman
734b2244fe
Add RegNetZ-D8 (83.5 @ 256, 84 @ 320) and RegNetZ-E8 (84.5 @ 256, 85 @ 320) weights. Update names of existing RegZ models to include group size.
2021-11-20 15:52:04 -08:00
Ross Wightman
93cc08fdc5
Make evonorm variables 1d to match other PyTorch norm layers, will break weight compat for any existing use (likely minimal, easy to fix).
2021-11-20 15:50:51 -08:00
Ross Wightman
af607b75cc
Prep a set of ResNetV2 models with GroupNorm, EvoNormB0, EvoNormS0 for BN free model experiments on TPU and IPU
2021-11-19 17:37:00 -08:00
Ross Wightman
c976a410d9
Add ResNet-50 w/ GN (resnet50_gn) and SEBotNet-33-TS (sebotnet33ts_256) model defs and weights. Update halonet50ts weights w/ slightly better variant in1k val, more robust to test sets.
2021-11-19 14:24:43 -08:00
Ross Wightman
f2006b2437
Cleanup qkv_bias cat in beit model so it can be traced
2021-11-18 21:25:00 -08:00
Ross Wightman
1076a65df1
Minor post FX merge cleanup
2021-11-18 19:47:07 -08:00
Ross Wightman
32c9937dec
Merge branch 'fx-feature-extract-new' of https://github.com/alexander-soare/pytorch-image-models into alexander-soare-fx-feature-extract-new
2021-11-18 16:31:29 -08:00
Ross Wightman
78b36bf46c
Places365 doesn't exist in some still used torchvision version
2021-11-18 14:59:51 -08:00
