huggingface/pytorch-image-models
The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (ViT), MobileNet-V3/V2, RegNet, DPN, CSPNet, Swin Transformer, MaxViT, CoAtNet, ConvNeXt, and more
PythonApache-2.0
Issues
- 1
[FEATURE] Add ViT weights: RADIO
#2177 opened by seefun - 9
[FEATURE] Add Hiera
#2083 opened by raulcarlomagno - 1
Add mobilenetv4
#2172 opened by wenhui-ml - 3
[BUG] Unknown model
#2171 opened by eryk-mazus - 1
No pretrained weights exist
#2170 opened by FeU-aKlos - 0
[FEATURE] ImageNet1k weights for ViT Huge?
#2161 opened by NightMachinery - 1
Missing features on "timm" package from pypi
#2160 opened by skr3178 - 9
[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 by TheDarkKnight-21th - 1
[FEATURE] Modify SAM -> ViTDet
#2059 opened by L-Reichardt - 3
Rotary embeddings do not work properly in eva02_base_patch14_448.mim_in22k_ft_in1k
#2155 opened by bobyard-com - 10
[FEATURE] `features_only` method for ViT networks
#2131 opened by ioangatop - 1
- 2
- 1
- 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 by TheDarkKnight-21th - 1
- 4
Output dimension of FocalNet models does not match label dimension of ImageNet-22K-MS
#2140 opened by eringrant - 1
ModelEmaV3 update doesn't copy model to the same device before averaging the weights
#2127 opened by lodalicious - 2
- 4
- 0
typographical error in train.py
#2097 opened by Tyx-main - 0
- 1
[BUG] Broken hrnet instantiation
#2139 opened by rohitdavas - 2
Pytorch classification vit_model.py Class PatchEmbed forward function features size could have some problems?
#2135 opened by XiaoluJiayou - 5
[FEATURE] CPU inference benchmarks
#2112 opened by RuRo - 1
[BUG] Scheduler implicitly do not change lr
#2125 opened by fzyzcjy - 0
- 3
[FEATURE] Add image backbones from `MobileCLIP` paper
#2110 opened by rsomani95 - 1
- 2
DropPath Implementation
#2118 opened by IsmaelElsharkawi - 5
DINOv2 worse performance compared to the original version
#2094 opened by davissf - 2
[BUG] Pretrained resnet34 output changing significantly with different batch size in eval mode.
#2107 opened by jseia - 3
[BUG] significant performance discrepancy
#2106 opened by yuxiangwei0808 - 3
- 0
[FEATURE] License in csv
#2095 opened by nietras - 1
switch the GPU
#2081 opened by a1112 - 1
[BUG]Invalid pretrained tag
#2093 opened by yolandazhou1222 - 1
[BUG] unknown model
#2086 opened by yolandazhou1222 - 3
[FEATURE] Latest Meta Data
#2085 opened by david-klindt - 1
[FEATURE] Add ImageBind
#2084 opened by raulcarlomagno - 0
- 3
[FEATURE] Add Droppath to the Xception model
#2078 opened by lizhuoq - 2
[FEATURE] Text encoder for clip
#2073 opened by twmht - 0
- 0
[FEATURE] DINOv2 Feature Map extraction
#2066 opened by FLamefiREz - 2
[BUG] data transforms ResizeKeepRatio
#2063 opened by DLlearn - 1
VAE or VQ-VAE is needed
#2056 opened by amirshamaei - 5
- 3
- 1
can;t visit https://huggingface.co/docs/timm
#2054 opened by alanguo1234