huggingface / pytorch-image-models

PyTorch image models, scripts, pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (ViT), MobileNet-V3/V2, RegNet, DPN, CSPNet, Swin Transformer, MaxViT, CoAtNet, ConvNeXt, and more

https://huggingface.co/docs/timm

huggingface/pytorch-image-models Issues

[FEATURE] Add TinyCLIP
Closed a month ago3
DINOv2 worse performance compared to the original version
Closed a month ago5
[FEATURE] Add Hiera
Updated 2 months ago3
[BUG] Inference API error in 'timm.models.maxxvit.MaxxVitConvCfg'
Closed 2 months ago3
typographical error in train.py
Updated 2 months ago
[FEATURE] Feature only support for Twins-PVT and Mvitv2
Updated 2 months ago1
[FEATURE] License in csv
Updated 2 months ago
switch the GPU
Closed 2 months ago1
[BUG]Invalid pretrained tag
Closed 3 months ago1
[BUG] unknown model
Closed 3 months ago1
[FEATURE] Latest Meta Data
Closed 3 months ago3
[FEATURE] Add ImageBind
Updated 3 months ago1
model.config.id2label = {id: label for label, id in config.label2id.items()}
Closed 3 months ago
[FEATURE] Add Droppath to the Xception model
Closed 3 months ago3
[FEATURE] Text encoder for clip
Closed 3 months ago2
[BUG] Inconsistent results of OpenAI CLIP models between open_clip and timm
Closed 5 months ago6
[FEATURE] timm.create_model() load pretrianed model from local path
Closed 3 months ago
[FEATURE] DINOv2 Feature Map extraction
Closed 3 months ago
[BUG] data transforms ResizeKeepRatio
Closed 3 months ago2
VAE or VQ-VAE is needed
Updated 4 months ago1
Cannot load the pretrained vit model offline using timm.create_model
Closed 4 months ago5
[FEATURE] Modify SAM -> ViTDet
Updated 4 months ago
AttributeError: type object 'Optimizer' has no attribute 'Adahessian'
Closed 4 months ago3
can;t visit https://huggingface.co/docs/timm
Closed 4 months ago1
[BUG] line 202 in timm.layers.patch_embed
Closed 5 months ago1
[BUG] The last n-batches in the log always show 0.00% accuracy
Closed 5 months ago2
[BUG] reg_token not working for ViT models
Closed 5 months ago3
[FEATURE] Early stopping when training
Updated 5 months ago1
[BUG] config.py references chans rather than in_chans
Closed 5 months ago1
Columns and DataType Not Explicitly Set on line 22 of generate_csv_results.py
Closed 5 months ago
[BUG] Latex compiling problem on some webpages
Closed 5 months ago3
how to run the efficientmit.py
Closed 5 months ago
[BUG] timm.create_model with pretrained=True not responsing (hangs indefinitely) with torch+cuda11.3 and torch+cuda12.1
Closed 5 months ago2
[BUG] SwinV2 traced inference (Jetson)
Closed 6 months ago2
[FEATURE] Add MetaCLIP weights
Closed 6 months ago2
[FEATURE] support for TinyVit (https://arxiv.org/pdf/2207.10666.pdf)
Closed 6 months ago2
[BUG] Wrong shape substitution in _pos_embed for ViTs
Closed 6 months ago2
[BUG] typos in `timm.layers.helpers.extend_tuple` and `CONTRIBUTING.md`
Closed 6 months ago
[BUG] TinyVit
Closed 7 months ago1
[FEATURE] Addition of missing typehints/docs
Updated 6 months ago2
[FEATURE] Add SigLIP weights
Closed 6 months ago2
[BUG] In what setting should I be concern for reproducibility or when should I be concern for reproducibility?
Closed 6 months ago5
[BUG] `test_optim` fail with pytorch 2.1.0
Closed 6 months ago5
[BUG] Getting completely different results for different version of torch.
Closed 6 months ago
[Q] Are there any ViT models available that were finetuned on COCO?
Closed 7 months ago2
Can k-fold cross validation be used in timm?
Closed 7 months ago2
Hugging Face hub model specified but package not installed. Run `pip install huggingface_hub`.
Closed 7 months ago1
[FEATURE] Add weights of Microsoft's BiomedCLIP
Updated 7 months ago
[FEATURE] Is it possible for adding hparams to model.default_cfg?
Updated 7 months ago
[BUG] Some model builder functions are missing guards for feature extraction
Closed 7 months ago2