SAVRN
Search Contact SAVRN

Open-weight model · Image classification

traffic-sign-adverse-weather

by Yy xieyuy/traffic-sign-adverse-weather

Official model checkpoints for the solution in the Traffic Sign Recognition under Adverse Weather Competition. See classes.txt for the 25 traffic sign classes.

Parameters—
Context—
Weights912.9 MB
Licensemit
AccessOpen weights
Monthly Downloads—

Model Card

By Yy, published under mit, revision 8422ce23bb81.

Official model checkpoints for the solution in the Traffic Sign Recognition under Adverse Weather Competition. See classes.txt for the 25 traffic sign classes. For inference scripts, training code, and in-depth engineering retrospective, visit the GitHub Repository.

Read Yy's full model card

Traffic Sign Recognition under Adverse Weather

Official model checkpoints for the solution in the Traffic Sign Recognition under Adverse Weather Competition.

Model Checkpoints

Model Checkpoint File Parameters Input Resolution Val Macro-F1
ConvNeXt V2-Base convnextv2_base_best.pth 89M 384x384 0.938
Swin Transformer V2-Base swin_v2_b_best.pth 88M 256x256 0.916
EfficientNetV2-M efficientnet_v2_m_best.pth 54M 384x384 0.917

Classes

See classes.txt for the 25 traffic sign classes.

Quick Download via Python

from huggingface_hub import hf_hub_download

# Download ConvNeXt V2-Base checkpoint
checkpoint_path = hf_hub_download(
    repo_id="xieyuy/traffic-sign-adverse-weather",
    filename="convnextv2_base_best.pth",
    local_dir="./results"
)

For inference scripts, training code, and in-depth engineering retrospective, visit the GitHub Repository.

Identity and Version

Repository
xieyuy/traffic-sign-adverse-weather
Publisher
Yy
Task
Image classification
Modality
Image
Library
timm
Parameters
Not stated by the source
Languages
zh, en
Revision
8422ce23bb81566f75cc856c7c3e6b9e46bc70ac
First published
2026-09-18
Last updated
2026-09-18

Files and Weights

6 files, 912.9 MB in total. The weights are 3 files totalling 912.9 MB in pth.

Weights3 files · 912.9 MB
Documentation1 file · 1.6 KB
Other1 file · 790 B
Repository1 file · 1.5 KB
Every file
FileTypeSizeSHA-256
convnextv2_base_best.pthWeights351.0 MB 64ee69f661c7
efficientnet_v2_m_best.pthWeights213.2 MB 803937b8a43c
swin_v2_b_best.pthWeights348.7 MB dc8de9b7b0ad
README.mdDocumentation1.6 KB —
classes.txtOther790 B —
.gitattributesRepository1.5 KB —

License and Download

License
mit
Access
Open weights, no gate
Download size
912.9 MB
Download from Yy

Released by Yy through its official repository on Hugging Face. Read the license.

Memory Requirements

PrecisionWeights in memory
As published912.9 MB

Weights only, from the published parameter count; the key-value cache and runtime add to this.

Questions About traffic-sign-adverse-weather

Can I use traffic-sign-adverse-weather commercially?

Yes. traffic-sign-adverse-weather is released under MIT License. The MIT License is a short permissive license. It permits commercial use, modification and redistribution, provided the copyright notice and permission notice are included.

Similar Models

Model · Image classification

swinv2-tiny-patch4-window16-256

Microsoft

Swin Transformer v2 model pre-trained on ImageNet-1k at resolution 256x256. It was introduced in the paper Swin Transformer V2: Scaling Up Capacity and Resolution by Liu et al. and first released in this repository. Disclaimer: The team releasing Swin Transformer v2 did not write a model card for this model so this model card has been written by the Hugging Face team. The Swin Transformer is a type of Vision Transformer. It builds hierarchical feature maps by merging image patches (shown in gray) in deeper layers and has linear computation complexity to input image size due to computation of self-attention only within each local window (shown in red). It can thus serve as a general-purpose…

Open weights apache-2.0 transformers
View model

Model · Image classification

AI-image-detector

Matthew Maybe

NOTE: Unless you are trying to detect imagery generated using older models such as VQGAN+CLIP, please use the updated version of this detector instead. This model is a proof-of-concept demonstration of using a ViT model to predict whether an artistic image was generated using AI. It was created in October 2022, and as such, the training data did not include any samples generated by Midjourney 5, SDXL, or DALLE-3. It still may be able to correctly identify samples from these more recent models due to being trained on outputs of their predecessors. Furthermore the intended scope of this tool is artistic images; that is to say, it is not a deepfake photo detector, and general computer imagery…

Open weights cc-by-4.0 transformers
View model

Model · Image classification

tinyvit-5m-int8-imagenet

Core Epoch

TinyViT-5M (timm/tinyvit5m224.distin22kftin1k, Apache-2.0) quantized to INT8 with Kenosis — 128-image calibration, no retraining. 80.53% top-1 from a 9.2 MB single file, on ONNX Runtime or OpenVINO, CPU or GPU, no accelerator required. ImageNet-1K validation, 49,872 images (disjoint from the 128 calibration images). Measured on a CPU with AVX-VNNI; on CPUs without VNNI this model's INT8 top-1 sits ~0.9 below FP32 rather than 0.34. Input 1x3x224x224, RGB, /255, ImageNet mean/std. Output logits [1,1000], sorted-synset order. runclassify.py / evalimagenet.py reproduce the demo and table. tinyvit5m224int8kenosis.onnx (9,228,567 B) — SHA-256…

Open weights apache-2.0 onnx
View model

Model · Image classification

mmfm-breast-imaging-checkpoints

NFadlallah

ResNet-18 binary (benign vs. malignant) classification checkpoints, trained per-dataset on eight public breast-imaging sources spanning ultrasound, Full write-up, methodology, and comparison to each source paper's own These are single-modality baselines, not the 3-branch fusion model. Each checkpoint is models.SingleBackboneClassifier (one ResNet-18 backbone, ImageNet-pretrained, first conv adapted for non-RGB inputs where applicable) — see models/backbone.py / training/train.py in the repo for the loading code. For the 5-fold datasets, this is one fold's checkpoint, not an ensemble or the averaged model — reported accuracy is the 5-fold mean from the full report for context, not this…

Open weights cc-by-4.0
View model