huggingface/pytorch-image-models

Issues

• [BUG] Loading state dict in a feature extraction network

  #2215 opened 6 months ago
  1

• [FEATURE] Add Florence-2 model weights

  #2212 opened 6 months ago
  6

• How to Replicate Official Model Accuracy

  #2211 opened 6 months ago
  1

• [FEATURE] Please add inetern image model

  #2210 opened a month ago
  1

• [FEATURE] Training Scripts of MobileNetv4

  #2204 opened 6 months ago
  1

• [BUG] Swin transformer

  #2201 opened 7 months ago
  1

• [BUG] TypeError: forward_head() got an unexpected keyword argument 'pre_logits'

  #2194 opened 7 months ago
  3

• [FEATURE] Support resizing rectangular pos_embed

  #2190 opened 5 months ago
  3

• [BUG] Bug in NextVit reparameterize

  #2187 opened 7 months ago
  1

• [FEATURE] Chaining pooled output to classifier

  #2186 opened 7 months ago
  2

• Is there a compressed model of ViTForImageClassification.from_pretrained('google/vit-base-patch16-224-in21k')?

  #2185 opened 7 months ago
  1

• [FEATURE] Add ViT weights: RADIO

  #2177 opened 7 months ago
  2

• Add mobilenetv4

  #2172 opened 7 months ago
  3

• [BUG] Unknown model

  #2171 opened 8 months ago
  3

• No pretrained weights exist

  #2170 opened 8 months ago
  1

• [FEATURE] ImageNet1k weights for ViT Huge?

  #2161 opened 8 months ago
  0

• Missing features on "timm" package from pypi

  #2160 opened 8 months ago
  1

• Rotary embeddings do not work properly in eva02_base_patch14_448.mim_in22k_ft_in1k

  #2155 opened 8 months ago
  3

• [BUG] There is the error in timm/train.py when i use the Webdataset (timm/imagent-w21-wds in huggingface) with class map

  #2154 opened 8 months ago
  9

• i want to load data not only .tar file but also .tar.gz

  #2151 opened 8 months ago
  1

• [BUG] Mismatch in Swin Transformer pretrained weights mapping.

  #2150 opened 8 months ago
  2

• [BUG] list_pretrained returns more models than list_models

  #2149 opened 8 months ago
  1

• [BUG] Issue title...UserWarning: Grad strides do not match bucket view strides. This may indicate grad was not created according to the gradient layout contract, or that the param's strides changed since DDP was constructed. This is not an error, but may impair performance.

  #2147 opened 8 months ago
  1

• Output dimension of FocalNet models does not match label dimension of ImageNet-22K-MS

  #2140 opened 9 months ago
  4

• [BUG] Broken hrnet instantiation

  #2139 opened 9 months ago
  1

• Pytorch classification vit_model.py Class PatchEmbed forward function features size could have some problems?

  #2135 opened 9 months ago
  2

• [BUG] AttributeError: module 'torch._C' has no attribute 'set_grad_enabled'

  #2132 opened 9 months ago
  0

• [FEATURE] `features_only` method for ViT networks

  #2131 opened 9 months ago
  10

• [BUG] Issue converting any of the maxvit models to tensorrt

  #2129 opened 9 months ago
  4

• ModelEmaV3 update doesn't copy model to the same device before averaging the weights

  #2127 opened 9 months ago
  1

• [BUG] Scheduler implicitly do not change lr

  #2125 opened 9 months ago
  1

• provide the pretrained model of cs3darknet_focus_s.c2ns_in1k

  #2122 opened a month ago
  1

• [BUG] Changing patch size does not work with CLIP/OpenCLIP ViT

  #2120 opened 9 months ago
  1

• DropPath Implementation

  #2118 opened 9 months ago
  2

• By using timm.create, how to download weights from url instead of HF?

  #2114 opened 9 months ago
  2

• [FEATURE] CPU inference benchmarks

  #2112 opened 9 months ago
  5

• [FEATURE] Add image backbones from `MobileCLIP` paper

  #2110 opened 6 months ago
  7

• [BUG] Pretrained resnet34 output changing significantly with different batch size in eval mode.

  #2107 opened 10 months ago
  2

• [BUG] significant performance discrepancy

  #2106 opened 10 months ago
  3

• [BUG] Inference API error in 'timm.models.maxxvit.MaxxVitConvCfg'

  #2103 opened 10 months ago
  3

• typographical error in train.py

  #2097 opened 9 months ago
  0

• [FEATURE] License in csv

  #2095 opened 10 months ago
  0

• DINOv2 worse performance compared to the original version

  #2094 opened 9 months ago
  5

• [BUG]Invalid pretrained tag

  #2093 opened a year ago
  1

• [BUG] unknown model

  #2086 opened a year ago
  1

• [FEATURE] Latest Meta Data

  #2085 opened a year ago
  3

• [FEATURE] Add ImageBind

  #2084 opened 4 months ago
  1

• [FEATURE] Add Hiera

  #2083 opened 7 months ago
  9

• switch the GPU

  #2081 opened a year ago
  1

• model.config.id2label = {id: label for label, id in config.label2id.items()}

  #2080 opened a year ago
  0