Bump timm from 0.9.7 to 1.0.3

[dependabot]

Bumps timm from 0.9.7 to 1.0.3.

Release notes

Sourced from timm's releases.

Release v1.0.3

May 14, 2024

• Support loading PaliGemma jax weights into SigLIP ViT models with average pooling.
• Add Hiera models from Meta (https://github.com/facebookresearch/hiera).
• Add normalize= flag for transorms, return non-normalized torch.Tensor with original dytpe (for chug)
• Version 1.0.3 release

May 11, 2024

• Searching for Better ViT Baselines (For the GPU Poor) weights and vit variants released. Exploring model shapes between Tiny and Base.

model	top1	top5	param_count	img_size
vit_mediumd_patch16_reg4_gap_256.sbb_in12k_ft_in1k	86.202	97.874	64.11	256
vit_betwixt_patch16_reg4_gap_256.sbb_in12k_ft_in1k	85.418	97.48	60.4	256
vit_mediumd_patch16_rope_reg1_gap_256.sbb_in1k	84.322	96.812	63.95	256
vit_betwixt_patch16_rope_reg4_gap_256.sbb_in1k	83.906	96.684	60.23	256
vit_base_patch16_rope_reg1_gap_256.sbb_in1k	83.866	96.67	86.43	256
vit_medium_patch16_rope_reg1_gap_256.sbb_in1k	83.81	96.824	38.74	256
vit_betwixt_patch16_reg4_gap_256.sbb_in1k	83.706	96.616	60.4	256
vit_betwixt_patch16_reg1_gap_256.sbb_in1k	83.628	96.544	60.4	256
vit_medium_patch16_reg4_gap_256.sbb_in1k	83.47	96.622	38.88	256
vit_medium_patch16_reg1_gap_256.sbb_in1k	83.462	96.548	38.88	256
vit_little_patch16_reg4_gap_256.sbb_in1k	82.514	96.262	22.52	256
vit_wee_patch16_reg1_gap_256.sbb_in1k	80.256	95.360	13.42	256
vit_pwee_patch16_reg1_gap_256.sbb_in1k	80.072	95.136	15.25	256
vit_mediumd_patch16_reg4_gap_256.sbb_in12k	N/A	N/A	64.11	256
vit_betwixt_patch16_reg4_gap_256.sbb_in12k	N/A	N/A	60.4	256

• AttentionExtract helper added to extract attention maps from timm models. See example in Visualize attention map for vision transformer huggingface/pytorch-image-models#1232 (comment)
• forward_intermediates() API refined and added to more models including some ConvNets that have other extraction methods.
• 1017 of 1047 model architectures support features_only=True feature extraction. Remaining 34 architectures can be supported but based on priority requests.
• Remove torch.jit.script annotated functions including old JIT activations. Conflict with dynamo and dynamo does a much better job when used.

April 11, 2024

• Prepping for a long overdue 1.0 release, things have been stable for a while now.
• Significant feature that's been missing for a while, features_only=True support for ViT models with flat hidden states or non-std module layouts (so far covering 'vit_*', 'twins_*', 'deit*', 'beit*', 'mvitv2*', 'eva*', 'samvit_*', 'flexivit*')
• Above feature support achieved through a new forward_intermediates() API that can be used with a feature wrapping module or direclty.

model = timm.create_model('vit_base_patch16_224')
final_feat, intermediates = model.forward_intermediates(input) 
output = model.forward_head(final_feat)  # pooling + classifier head
print(final_feat.shape)
torch.Size([2, 197, 768])
for f in intermediates:
print(f.shape)
torch.Size([2, 768, 14, 14])
torch.Size([2, 768, 14, 14])
torch.Size([2, 768, 14, 14])
</tr></table>

... (truncated)

Commits

• cb0e439 Release 1.0.3
• 27fd2f3 Merge pull request #2181 from huggingface/Delaunay-dist-backend
• e57625e Tweak dist_backend to use device_type (before possible :)
• 6ca9257 Merge branch 'patch-1' of https://github.com/Delaunay/pytorch-image-models in...
• cd0e7b1 Merge pull request #2180 from yvonwin/main
• 83aee5c Add explicit GAP (avg pool) variants of other SigLIP models.
• 58f2f79 Remove a duplicate function in mobilenetv3.py: _gen_lcnet is repeated in mo...
• f04802f Update README.md
• 6653747 Merge pull request #2178 from huggingface/pali_siglip
• 7b3b11b Support loading of paligemma weights into GAP variants of SigLIP ViT. Minor t...
• Additional commits viewable in compare view

Dependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting @dependabot rebase.

---

Dependabot commands and options

You can trigger Dependabot actions by commenting on this PR:

• @dependabot rebase will rebase this PR
• @dependabot recreate will recreate this PR, overwriting any edits that have been made to it
• @dependabot merge will merge this PR after your CI passes on it
• @dependabot squash and merge will squash and merge this PR after your CI passes on it
• @dependabot cancel merge will cancel a previously requested merge and block automerging
• @dependabot reopen will reopen this PR if it is closed
• @dependabot close will close this PR and stop Dependabot recreating it. You can achieve the same result by closing it manually
• @dependabot show <dependency name> ignore conditions will show all of the ignore conditions of the specified dependency
• @dependabot ignore this major version will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself)
• @dependabot ignore this minor version will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself)
• @dependabot ignore this dependency will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself)

[dependabot]

Superseded by #888.