issues Search Results · repo:huggingface/pytorch-image-models language:Python
Filter by
996 results
(58 ms)996 results
inhuggingface/pytorch-image-models (press backspace or delete to remove)Describe the bug
I am using model = timm.create_model( efficientnet_lite0 , pretrained=True) ;model.classifier =
torch.nn.Linear(1280, 1) to train a model. But when I convert the pth in to onnx , there ...
bug
stillbetter
- 2
- Opened 17 days ago
- #2573
Describe the bug When pretrained on in12k and then fintuned on in1k results are significantly better than only training
on in1k. I don t know if the default_cfg in eva.py was intentionally set to the in1k ...
bug
TonyCongqianWang
- 6
- Opened 21 days ago
- #2570
DINOv3: Self-supervised learning for vision at unprecedented scale weights for ViT and ConvNeXt released
img width= 1160 height= 984 alt= Image src=
https://github.com/user-attachments/assets/a209b2e9-ff5b-491b-99f5-fd3938a9c8df ...
enhancement
seefun
- 8
- Opened 23 days ago
- #2567
naflexvit_base_patch16_siglip and naflexvit_so400m_patch16_siglip pretrained weights is missing
Is it possible to convert them to the timm vision backbone weight
- https://huggingface.co/google/siglip2-base-patch16-naflex ...
enhancement
- 1
- Opened on Aug 3
- #2562
Describe the bug In hieradet_sam2, the init_values parameter is not being passed to MultiScaleBlock. As a result,
LayerScale layers are not created in either custom models or the predefined hieradet_small ...
bug
hassonofer
- Opened on Jul 26
- #2558
Describe the bug After updating timm to the latest version, I noticed that the behavior of update_time has changed
compared to previous versions. I m not sure if this is an intended change or a bug, but ...
bug
caojiaolong
- 3
- Opened on Jul 24
- #2556
Describe the bug import timm immediately results in an error with timm 1.0.18.
Python 3.9.21 (main, Jan 14 2025, 22:41:44) [MSC v.1929 64 bit (AMD64)] on win32
Type help , copyright , credits or ...
bug
KellyWalker
- 3
- Opened on Jul 23
- #2555
DPT decoder is widely used for various models. Could you support DPT decoder model?
enhancement
dqj5182
- 1
- Opened on Jul 16
- #2551
img width= 873 height= 265 alt= Image src=
https://github.com/user-attachments/assets/4b44711b-92a7-4e5f-95d6-5dd06f42c9f2 /
@rwightman Hi, will you consider supporting the latest released smaller versions ...
enhancement
Jacobew
- 1
- Opened on Jul 16
- #2550
Describe the bug Eva forward pass results in the following error:
File /home/suraj/Repositories/mm_seg/.venv/lib/python3.11/site-packages/torch/nn/modules/module.py , line 1739, in _wrapped_call_impl ...
bug
surajpaib
- 3
- Opened on Jul 16
- #2549
Learn how you can use GitHub Issues to plan and track your work.
Save views for sprints, backlogs, teams, or releases. Rank, sort, and filter issues to suit the occasion. The possibilities are endless.Learn more about GitHub IssuesProTip!
Press the /
key to activate the search input again and adjust your query.Learn how you can use GitHub Issues to plan and track your work.
Save views for sprints, backlogs, teams, or releases. Rank, sort, and filter issues to suit the occasion. The possibilities are endless.Learn more about GitHub IssuesProTip!
Press the /
key to activate the search input again and adjust your query.