Ross Wightman
2544d3b80f
ConvNeXt pico, femto, and nano, pico, femto ols (overlapping stem) weights and model defs
2022-08-05 17:05:50 -07:00
Ross Wightman
13565aad50
Add edgenext_base model def & weight link, update to improve ONNX export #1385
2022-08-05 16:58:34 -07:00
Ross Wightman
8ad4bdfa06
Allow ntuple to be used with string values
2022-07-28 16:18:18 -07:00
Ross Wightman
7430a85d07
Update README, bump version to 0.6.8
2022-07-28 15:07:11 -07:00
Ross Wightman
ec6a28830f
Add DeiT-III 'medium' model defs and weights
2022-07-28 15:03:20 -07:00
Ross Wightman
d875a1d3f6
version 0.6.7
2022-07-27 12:41:06 -07:00
Ross Wightman
6f103a442b
Add convnext_nano weights, 80.8 @ 224, 81.5 @ 288
2022-07-26 16:40:27 -07:00
Ross Wightman
4042a94f8f
Add weights for two 'Edge' block (3x3->1x1) variants of CS3 networks.
2022-07-26 16:40:27 -07:00
Ross Wightman
c8f69e04a9
Merge pull request #1365 from veritable-tech/fix-resize-pos-embed
...
Take `no_emb_class` into account when calling `resize_pos_embed`
2022-07-24 21:03:01 -07:00
Ceshine Lee
0b64117592
Take no_emb_class into account when calling resize_pos_embed
2022-07-24 19:11:45 +08:00
Jasha10
56c3a84db3
Update type hint for register_notrace_module
...
register_notrace_module is used to decorate types (i.e. subclasses of nn.Module).
It is not called on module instances.
2022-07-22 16:59:55 -05:00
Ross Wightman
1b278136c3
Change models with mean 0,0,0 std 1,1,1 from int to float for consistency as mentioned in #1355
2022-07-21 17:36:15 -07:00
Ross Wightman
909705e7ff
Remove some redundant requires_grad=True from nn.Parameter in third party code
2022-07-20 12:37:41 -07:00
Ross Wightman
c5e0d1c700
Add dilation support to convnext, allows output_stride=8 and 16 use. Fix #1341
2022-07-19 17:52:10 -07:00
Ross Wightman
dc376e3676
Ensure all model entrypoint fn default to pretrained=False (a few didn't)
2022-07-19 13:58:41 -07:00
Ross Wightman
23b102064a
Add cs3sedarknet_x weights w/ 82.65 @ 288 top1. Add 2 cs3 edgenet models (w/ 3x3-1x1 block), remove aa from cspnet blocks (not needed)
2022-07-19 13:56:44 -07:00
Ross Wightman
0dbd9352ce
Add bulk_runner script and updates to benchmark.py and validate.py for better error handling in bulk runs (used for benchmark and validation result runs). Improved batch size decay stepping on retry...
2022-07-18 18:04:54 -07:00
Ross Wightman
92b91af3bb
version 0.6.6
2022-07-15 17:00:18 -07:00
Ross Wightman
05313940e2
Add cs3darknet_x, cs3sedarknet_l, and darknetaa53 weights from TPU sessions. Move SE btwn conv1 & conv2 in DarkBlock. Improve SE/attn handling in Csp/DarkNet. Fix leaky_relu bug on older csp models.
2022-07-15 16:55:16 -07:00
nateraw
51cca82aa1
👽 use hf_hub_download instead of cached_download
2022-07-14 16:41:45 -04:00
Ross Wightman
324a4e58b6
disable nvfuser for jit te/legacy modes (for PT 1.12+)
2022-07-13 10:34:34 -07:00
Ross Wightman
2898cf6e41
version 0.6.5 for pypi release
2022-07-10 16:43:23 -07:00
Ross Wightman
a45b4bce9a
x and xx small edgenext models do benefit from larger test input size
2022-07-08 10:53:27 -07:00
Ross Wightman
a8e34051c1
Unbreak gamma remap impacting beit checkpoint load, version bump to 0.6.4
2022-07-07 23:07:43 -07:00
Ross Wightman
1c5cb819f9
bump version to 0.6.3 before merge
2022-07-07 22:05:56 -07:00
Ross Wightman
a1cb25066e
Add edgnext_small_rw weights trained with swin like recipe. Better than original 'small' but not the recent 'USI' distilled weights.
2022-07-07 22:02:57 -07:00
Ross Wightman
7c7ecd2492
Add --use-train-size flag to force use of train input_size (over test input size) for validation. Default test-time pooling to use train input size (fixes issues).
2022-07-07 22:01:24 -07:00
Ross Wightman
ce65a7b29f
Update vit_relpos w/ some additional weights, some cleanup to match recent vit updates, more MLP log coord experiments.
2022-07-07 21:33:25 -07:00
Ross Wightman
58621723bd
Add CrossStage3 DarkNet (cs3) weights
2022-07-07 17:43:38 -07:00
Ross Wightman
9be0c84715
Change set -> dict w/ None keys for dataset split synonym search, so always consistent if more than 1 exists. Fix #1224
2022-07-07 15:33:53 -07:00
Ross Wightman
db0cee9910
Refactor cspnet configuration using dataclasses, update feature extraction for new cs3 variants.
2022-07-07 14:43:27 -07:00
Ross Wightman
eca09b8642
Add MobileVitV2 support. Fix #1332 . Move GroupNorm1 to common layers (used in poolformer + mobilevitv2). Keep ol custom ConvNeXt LayerNorm2d impl as LayerNormExp2d for reference.
2022-07-07 14:41:01 -07:00
Ross Wightman
06307b8b41
Remove experimental downsample in block support in ConvNeXt. Experiment further before keeping it in.
2022-07-07 14:37:58 -07:00
Ross Wightman
bfc0dccb0e
Improve image extension handling, add methods to modify / get defaults. Fix #1335 fix #1274 .
2022-07-07 14:23:20 -07:00
Ross Wightman
7d4b3807d5
Support DeiT-3 (Revenge of the ViT) checkpoints. Add non-overlapping (w/ class token) pos-embed support to vit.
2022-07-04 22:25:22 -07:00
Ross Wightman
d0c5bd5722
Rename cs2->cs3 for darknets. Fix features_only for cs3 darknets.
2022-07-03 08:32:41 -07:00
Ross Wightman
d765305821
Remove first_conv for resnetaa50 def
2022-07-02 15:56:17 -07:00
Ross Wightman
dd9b8f57c4
Add feature_info to edgenext for features_only support, hopefully fix some fx / test errors
2022-07-02 15:20:45 -07:00
Ross Wightman
377e9bfa21
Add TPU trained darknet53 weights. Add mising pretrain_cfg for some csp/darknet models.
2022-07-02 15:18:52 -07:00
Ross Wightman
c170ba3173
Add weights for resnet10t, resnet14t, and resnetaa50 models. Fix #1314
2022-07-02 15:18:06 -07:00
Ross Wightman
188c194b0f
Left some experiment stem code in convnext by mistake
2022-07-02 15:17:28 -07:00
Ross Wightman
70d6d2c484
support test_crop_size in data config resolve
2022-07-02 15:17:05 -07:00
Ross Wightman
6064d16a2d
Add initial EdgeNeXt import. Significant cleanup / reorg (like ConvNeXt). Fix #1320
...
* edgenext refactored for torchscript compat, stage base organization
* slight refactor of ConvNeXt to match some EdgeNeXt additions
* remove use of funky LayerNorm layer in ConvNeXt and just use nn.LayerNorm and LayerNorm2d (permute)
2022-07-01 15:18:42 -07:00
Ross Wightman
7a9c6811c9
Add eps arg to LayerNorm2d, add 'tf' (tensorflow) variant of trunc_normal_ that applies scale/shift after sampling (instead of needing to move a/b)
2022-07-01 15:15:39 -07:00
Ross Wightman
82c311d082
Add more experimental darknet and 'cs2' darknet variants (different cross stage setup, closer to newer YOLO backbones) for train trials.
2022-07-01 15:14:01 -07:00
Ross Wightman
a050fde5cd
Add resnet10t (basic block) and resnet14t (bottleneck) with 1,1,1,1 repeats
2022-07-01 15:03:28 -07:00
Ross Wightman
e6d7df40ec
no longer a point using kwargs for pretrain_cfg resolve, just pass explicit arg
2022-06-24 21:36:23 -07:00
Ross Wightman
07d0c4ae96
Improve repr for DropPath module
2022-06-24 14:58:15 -07:00
Ross Wightman
e27c16b8a0
Remove unecessary code for synbn guard
2022-06-24 14:57:42 -07:00
Ross Wightman
0da3c9ebbf
Remove SiLU layer in default args that breaks import on old old PyTorch
2022-06-24 14:56:58 -07:00
