Ross Wightman 61df3fde89 Wrong hybrid_medium in12k pool sizes

2024-07-25 15:39:21 -07:00

..

_pruned

…

layers

…

__init__.py

Merge branch 'main' of https://github.com/Beckschen/pytorch-image-models into Beckschen-vitamin

2024-06-02 14:16:30 -07:00

_builder.py

Support loading of paligemma weights into GAP variants of SigLIP ViT. Minor tweak to npz loading for packed transformer weights.

2024-05-14 15:44:37 -07:00

_efficientnet_blocks.py

Add mobilenet edgetpu defs for exp, add ol mobilenet v1 back for completeness / comparison

2024-06-13 17:33:04 -07:00

_efficientnet_builder.py

Add mobilenet edgetpu defs for exp, add ol mobilenet v1 back for completeness / comparison

2024-06-13 17:33:04 -07:00

_factory.py

Add support for passing model args via hf hub config

2023-11-19 15:16:01 -08:00

_features_fx.py

Fix jit.script breaking with features_fx

2024-06-28 03:58:51 +00:00

_features.py

Add AttentionExtract helper module

2024-05-04 14:10:00 -07:00

_helpers.py

_orig_mod still causing issues even though I thought it was fixed in pytorch, add unwrap / clean helpers

2024-07-19 11:03:45 -07:00

_hub.py

Change default serialization for push_to_hf_hub to 'both'

2024-06-07 13:40:31 -07:00

_manipulate.py

Swin and FocalNet weights on HF hub. Add model deprecation functionality w/ some registry tweaks.

2023-03-18 14:55:09 -07:00

_pretrained.py

Allow passing state_dict directly via pretrained cfg mechanism as an override

2023-05-08 15:15:44 -07:00

_prune.py

Fix consistency, testing for forward_head w/ pre_logits, reset_classifier, models with pre_logits size != unpooled feature size

2024-06-07 13:53:00 -07:00

_registry.py

Add forward_intermediates() to efficientnet / mobilenetv3 based models as an exercise.

2024-05-02 14:19:16 -07:00

beit.py

Add 'qkv_bias_separate' flag for EVA/beit/swinv2 attn modules to allow an override for easy quantization wrappers. Fix #2098

2024-07-08 13:48:38 -07:00

byoanet.py

…

byobnet.py

Add weights for test models

2024-07-22 10:08:57 -07:00

cait.py

Fix consistency, testing for forward_head w/ pre_logits, reset_classifier, models with pre_logits size != unpooled feature size

2024-06-07 13:53:00 -07:00

coat.py

Fix consistency, testing for forward_head w/ pre_logits, reset_classifier, models with pre_logits size != unpooled feature size

2024-06-07 13:53:00 -07:00

convit.py

set_input_size initial impl for vit & swin v1. Move HybridEmbed to own location in timm/layers

2024-07-17 15:25:48 -07:00

convmixer.py

Fix consistency, testing for forward_head w/ pre_logits, reset_classifier, models with pre_logits size != unpooled feature size

2024-06-07 13:53:00 -07:00

convnext.py

Fix consistency, testing for forward_head w/ pre_logits, reset_classifier, models with pre_logits size != unpooled feature size

2024-06-07 13:53:00 -07:00

crossvit.py

Fix consistency, testing for forward_head w/ pre_logits, reset_classifier, models with pre_logits size != unpooled feature size

2024-06-07 13:53:00 -07:00

cspnet.py

Remove separate ConvNormActAa class, merge with ConvNormAct

2024-06-10 12:05:35 -07:00

davit.py

cleanup davit padding

2024-06-22 12:06:46 -07:00

deit.py

…

densenet.py

Fix consistency, testing for forward_head w/ pre_logits, reset_classifier, models with pre_logits size != unpooled feature size

2024-06-07 13:53:00 -07:00

dla.py

Fix consistency, testing for forward_head w/ pre_logits, reset_classifier, models with pre_logits size != unpooled feature size

2024-06-07 13:53:00 -07:00

dpn.py

…

edgenext.py

Fix consistency, testing for forward_head w/ pre_logits, reset_classifier, models with pre_logits size != unpooled feature size

2024-06-07 13:53:00 -07:00

efficientformer_v2.py

Fix consistency, testing for forward_head w/ pre_logits, reset_classifier, models with pre_logits size != unpooled feature size

2024-06-07 13:53:00 -07:00

efficientformer.py

Fix consistency, testing for forward_head w/ pre_logits, reset_classifier, models with pre_logits size != unpooled feature size

2024-06-07 13:53:00 -07:00

efficientnet.py

Add latest mobilenetv4 and baseline updates for mobilenetv1 and efficientnet_b0 weights

2024-07-25 14:20:54 -07:00

efficientvit_mit.py

Fix consistency, testing for forward_head w/ pre_logits, reset_classifier, models with pre_logits size != unpooled feature size

2024-06-07 13:53:00 -07:00

efficientvit_msra.py

…

eva.py

Add 'qkv_bias_separate' flag for EVA/beit/swinv2 attn modules to allow an override for easy quantization wrappers. Fix #2098

2024-07-08 13:48:38 -07:00

factory.py

Add a deprecation phase to module re-org

2022-12-09 14:39:45 -08:00

fastvit.py

Prepping for final MobileCLIP weight locations (#2199)

2024-06-13 16:55:49 -07:00

features.py

…

focalnet.py

…

fx_features.py

Add a deprecation phase to module re-org

2022-12-09 14:39:45 -08:00

gcvit.py

Fix consistency, testing for forward_head w/ pre_logits, reset_classifier, models with pre_logits size != unpooled feature size

2024-06-07 13:53:00 -07:00

ghostnet.py

Some missed reset_classifier() type annotations

2024-06-16 10:39:27 -07:00

hardcorenas.py

Add typing to all model entrypoint fns, add old cache check env var to builder

2023-05-08 08:52:38 -07:00

helpers.py

Add a deprecation phase to module re-org

2022-12-09 14:39:45 -08:00

hgnet.py

Fix consistency, testing for forward_head w/ pre_logits, reset_classifier, models with pre_logits size != unpooled feature size

2024-06-07 13:53:00 -07:00

hiera.py

Add to 'abswin' hiera models for train trials

2024-07-19 11:05:31 -07:00

hrnet.py

Fix typo in type annotations in timm.models.hrnet

2024-07-08 00:53:16 +02:00

hub.py

Update hub.py

2023-05-12 21:48:46 +02:00

inception_next.py

Fix consistency, testing for forward_head w/ pre_logits, reset_classifier, models with pre_logits size != unpooled feature size

2024-06-07 13:53:00 -07:00

inception_resnet_v2.py

Fix consistency, testing for forward_head w/ pre_logits, reset_classifier, models with pre_logits size != unpooled feature size

2024-06-07 13:53:00 -07:00

inception_v3.py

Fix consistency, testing for forward_head w/ pre_logits, reset_classifier, models with pre_logits size != unpooled feature size

2024-06-07 13:53:00 -07:00

inception_v4.py

Some missed reset_classifier() type annotations

2024-06-16 10:39:27 -07:00

levit.py

…

maxxvit.py

Fix consistency, testing for forward_head w/ pre_logits, reset_classifier, models with pre_logits size != unpooled feature size

2024-06-07 13:53:00 -07:00

metaformer.py

Some missed reset_classifier() type annotations

2024-06-16 10:39:27 -07:00

mlp_mixer.py

…

mobilenetv3.py

Wrong hybrid_medium in12k pool sizes

2024-07-25 15:39:21 -07:00

mobilevit.py

…

mvitv2.py

Fix consistency, testing for forward_head w/ pre_logits, reset_classifier, models with pre_logits size != unpooled feature size

2024-06-07 13:53:00 -07:00

nasnet.py

Some missed reset_classifier() type annotations

2024-06-16 10:39:27 -07:00

nest.py

Fix consistency, testing for forward_head w/ pre_logits, reset_classifier, models with pre_logits size != unpooled feature size

2024-06-07 13:53:00 -07:00

nextvit.py

Fix consistency, testing for forward_head w/ pre_logits, reset_classifier, models with pre_logits size != unpooled feature size

2024-06-07 13:53:00 -07:00

nfnet.py

Fix consistency, testing for forward_head w/ pre_logits, reset_classifier, models with pre_logits size != unpooled feature size

2024-06-07 13:53:00 -07:00

pit.py

Fix consistency, testing for forward_head w/ pre_logits, reset_classifier, models with pre_logits size != unpooled feature size

2024-06-07 13:53:00 -07:00

pnasnet.py

Some missed reset_classifier() type annotations

2024-06-16 10:39:27 -07:00

pvt_v2.py

Fix consistency, testing for forward_head w/ pre_logits, reset_classifier, models with pre_logits size != unpooled feature size

2024-06-07 13:53:00 -07:00

registry.py

Add a deprecation phase to module re-org

2022-12-09 14:39:45 -08:00

regnet.py

Some missed reset_classifier() type annotations

2024-06-16 10:39:27 -07:00

repghost.py

Fix consistency, testing for forward_head w/ pre_logits, reset_classifier, models with pre_logits size != unpooled feature size

2024-06-07 13:53:00 -07:00

repvit.py

Fix consistency, testing for forward_head w/ pre_logits, reset_classifier, models with pre_logits size != unpooled feature size

2024-06-07 13:53:00 -07:00

res2net.py

Add typing to all model entrypoint fns, add old cache check env var to builder

2023-05-08 08:52:38 -07:00

resnest.py

Add typing to all model entrypoint fns, add old cache check env var to builder

2023-05-08 08:52:38 -07:00

resnet.py

Make channels for classic resnet configurable

2024-07-22 10:47:40 -07:00

resnetv2.py

Fix consistency, testing for forward_head w/ pre_logits, reset_classifier, models with pre_logits size != unpooled feature size

2024-06-07 13:53:00 -07:00

rexnet.py

Some missed reset_classifier() type annotations

2024-06-16 10:39:27 -07:00

selecsls.py

Some missed reset_classifier() type annotations

2024-06-16 10:39:27 -07:00

senet.py

Some missed reset_classifier() type annotations

2024-06-16 10:39:27 -07:00

sequencer.py

Fix consistency, testing for forward_head w/ pre_logits, reset_classifier, models with pre_logits size != unpooled feature size

2024-06-07 13:53:00 -07:00

sknet.py

Add typing to all model entrypoint fns, add old cache check env var to builder

2023-05-08 08:52:38 -07:00

swin_transformer_v2_cr.py

remove swin debug prints

2024-07-24 21:05:56 -07:00

swin_transformer_v2.py

remove swin debug prints

2024-07-24 21:05:56 -07:00

swin_transformer.py

set_input_size(), always_partition, strict_img_size, dynamic mask option for all swin models. More flexibility in resolution, window resizing.

2024-07-24 16:41:31 -07:00

tiny_vit.py

…

tnt.py

…

tresnet.py

Remove separate ConvNormActAa class, merge with ConvNormAct

2024-06-10 12:05:35 -07:00

twins.py

Fix consistency, testing for forward_head w/ pre_logits, reset_classifier, models with pre_logits size != unpooled feature size

2024-06-07 13:53:00 -07:00

vgg.py

…

visformer.py

Fix consistency, testing for forward_head w/ pre_logits, reset_classifier, models with pre_logits size != unpooled feature size

2024-06-07 13:53:00 -07:00

vision_transformer_hybrid.py

set_input_size initial impl for vit & swin v1. Move HybridEmbed to own location in timm/layers

2024-07-17 15:25:48 -07:00

vision_transformer_relpos.py

Some missed reset_classifier() type annotations

2024-06-16 10:39:27 -07:00

vision_transformer_sam.py

Some missed reset_classifier() type annotations

2024-06-16 10:39:27 -07:00

vision_transformer.py

Add weights for test models

2024-07-22 10:08:57 -07:00

vitamin.py

set_input_size initial impl for vit & swin v1. Move HybridEmbed to own location in timm/layers

2024-07-17 15:25:48 -07:00

volo.py

Fix consistency, testing for forward_head w/ pre_logits, reset_classifier, models with pre_logits size != unpooled feature size

2024-06-07 13:53:00 -07:00

vovnet.py

Some missed reset_classifier() type annotations

2024-06-16 10:39:27 -07:00

xception_aligned.py

Some missed reset_classifier() type annotations

2024-06-16 10:39:27 -07:00

xception.py

Some missed reset_classifier() type annotations

2024-06-16 10:39:27 -07:00

xcit.py

Fix consistency, testing for forward_head w/ pre_logits, reset_classifier, models with pre_logits size != unpooled feature size

2024-06-07 13:53:00 -07:00