pytorch-image-models

layers

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

pruned

…

__init__.py

Add initial EdgeNeXt import. Significant cleanup / reorg (like ConvNeXt). Fix #1320

2022-07-01 15:18:42 -07:00

beit.py

Remove some redundant requires_grad=True from nn.Parameter in third party code

2022-07-20 12:37:41 -07:00

byoanet.py

…

byobnet.py

…

cait.py

Remove some redundant requires_grad=True from nn.Parameter in third party code

2022-07-20 12:37:41 -07:00

coat.py

…

convit.py

…

convmixer.py

Significant model refactor and additions:

2022-02-28 13:56:23 -08:00

convnext.py

Add convnext_nano weights, 80.8 @ 224, 81.5 @ 288

2022-07-26 16:40:27 -07:00

crossvit.py

…

cspnet.py

Add weights for two 'Edge' block (3x3->1x1) variants of CS3 networks.

2022-07-26 16:40:27 -07:00

deit.py

Add DeiT-III 'medium' model defs and weights

2022-07-28 15:03:20 -07:00

densenet.py

…

dla.py

…

dpn.py

Fix correctness of some group matching regex (no impact on result), some formatting, missed forward_head for resnet

2022-03-19 14:58:54 -07:00

edgenext.py

x and xx small edgenext models do benefit from larger test input size

2022-07-08 10:53:27 -07:00

efficientnet_blocks.py

…

efficientnet_builder.py

Merge remote-tracking branch 'origin/master' into norm_norm_norm

2022-01-25 22:20:45 -08:00

efficientnet.py

…

factory.py

…

features.py

Significant model refactor and additions:

2022-02-28 13:56:23 -08:00

fx_features.py

Update type hint for register_notrace_module

2022-07-22 16:59:55 -05:00

ghostnet.py

…

gluon_resnet.py

…

gluon_xception.py

…

hardcorenas.py

…

helpers.py

no longer a point using kwargs for pretrain_cfg resolve, just pass explicit arg

2022-06-24 21:36:23 -07:00

hrnet.py

Ensure all model entrypoint fn default to pretrained=False (a few didn't)

2022-07-19 13:58:41 -07:00

hub.py

👽 use hf_hub_download instead of cached_download

2022-07-14 16:41:45 -04:00

inception_resnet_v2.py

…

inception_v3.py

Improve resolve_pretrained_cfg behaviour when no cfg exists, warn instead of crash. Improve usability ex #1311

2022-06-24 14:55:25 -07:00

inception_v4.py

…

levit.py

…

mlp_mixer.py

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

mobilenetv3.py

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

mobilevit.py

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

nasnet.py

…

nest.py

Fix correctness of some group matching regex (no impact on result), some formatting, missed forward_head for resnet

2022-03-19 14:58:54 -07:00

nfnet.py

…

pit.py

…

pnasnet.py

…

poolformer.py

Remove some redundant requires_grad=True from nn.Parameter in third party code

2022-07-20 12:37:41 -07:00

registry.py

…

regnet.py

Fix group_matcher regex for regnet.py

2022-05-09 10:40:40 -07:00

res2net.py

…

resnest.py

Significant model refactor and additions:

2022-02-28 13:56:23 -08:00

resnet.py

Ensure all model entrypoint fn default to pretrained=False (a few didn't)

2022-07-19 13:58:41 -07:00

resnetv2.py

Fix correctness of some group matching regex (no impact on result), some formatting, missed forward_head for resnet

2022-03-19 14:58:54 -07:00

rexnet.py

Fix correctness of some group matching regex (no impact on result), some formatting, missed forward_head for resnet

2022-03-19 14:58:54 -07:00

selecsls.py

…

senet.py

Fix correctness of some group matching regex (no impact on result), some formatting, missed forward_head for resnet

2022-03-19 14:58:54 -07:00

sequencer.py

Fix tests for rank-4 output where feature channels dim is -1 (3) and not 1

2022-05-09 15:20:24 -07:00

sknet.py

Significant model refactor and additions:

2022-02-28 13:56:23 -08:00

swin_transformer_v2_cr.py

Remove persistent buffers from Swin-V2. Change SwinV2Cr cos attn + tau/logit_scale to match official, add ckpt convert, init_value zeros resid LN weight by default

2022-05-13 10:50:59 -07:00

swin_transformer_v2.py

Add updated vit_relpos weights, and impl w/ support for official swin-v2 differences for relpos. Add bias control support for MLP layers

2022-05-13 13:53:57 -07:00

swin_transformer.py

Add initial swinv2 tiny / small weights

2022-04-03 15:22:55 -07:00

tnt.py

…

tresnet.py

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

twins.py

Fix correctness of some group matching regex (no impact on result), some formatting, missed forward_head for resnet

2022-03-19 14:58:54 -07:00

vgg.py

…

visformer.py

…

vision_transformer_hybrid.py

Vision Transformer refactoring and Rel Pos impl

2022-05-02 15:37:39 -07:00

vision_transformer_relpos.py

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

vision_transformer.py

Take no_emb_class into account when calling resize_pos_embed

2022-07-24 19:11:45 +08:00

volo.py

…

vovnet.py

…

xception_aligned.py

…

xception.py

Significant model refactor and additions:

2022-02-28 13:56:23 -08:00

xcit.py

Remove some redundant requires_grad=True from nn.Parameter in third party code

2022-07-20 12:37:41 -07:00