stanford-cars 开源项目推荐（27 个）

Yangyangii /GAN-Tutorial

使用 PyTorch 简单实现多种 GAN 模型。

ZF4444 /MMAL-Net

这是一篇PyTorch实现的论文《多分支和多尺度注意力学习用于细粒度视觉分类（MMAL-Net）》（张范、李孟、翟桂生、刘一昭）。

lvyilin /pytorch-fgvc-dataset

PyTorch 自定义数据集 API——CUB-200-2011、斯坦福犬、斯坦福汽车、FGVC 飞机、NABirds、Tiny ImageNet、iNaturalist2017

deanwetherby /tf_oda_stanford_cars

Train a TensorFlow deep learning model to detect vehicle make/model.

vivekkalyan /fine-grained-image-classification

该项目在 GitHub 上没有填写描述

codope /aiforsea-cv-cars

Fine-Grained Visual Classification on Stanford Cars Dataset

mouniraziz /MsKPRN

The source code for Multi-Scale Kronecker-Product Relation Networks for Few-Shot Learning

arasgungore /car-brand-recognition

Final project assigned for the Introduction to Image Processing (EE 475) course in the Spring 2023 semester.

haksorus /mobilenetv2-cars-classification

PyTorch MobileNetV2 Stanford Cars Dataset Classification (0.85 Accuracy)

DanRuta /Stanford-Cars-Deep-Learning

Deep Learning experiments for the Stanford Cars dataset

Simula-COMPLEX /pure

Uncertainty quantification method and tool for object detection models

morrisfl /stanford_cars_refined

Enhanced class label granularity of the Stanford Cars dataset.

mouniraziz /AGLRs

Official implementation of the paper: Learn to aggregate global and local representations for few-shot learning

HilthonTT /Car-GAN

DCGAN in PyTorch that generates 64×64 car images, trained on the Stanford Cars dataset. Includes pretrained weights, a CLI and a step-by-step notebook.

watchcat2077 /car-model-recognition

Fine-grained car recognition on Stanford Cars (196 classes) with PyTorch transfer learning: ResNet-34 reaches 90.8% top-1 / 98.7% top-5; ResNet-18 vs ResNet-34 trade-off, learning-rate sweep and error analysis.

mohshakhatreh /car-image-classification

Car image classification using ResNet50 transfer learning on the Stanford Cars dataset (196 classes). Achieves 71.4% Top-1 and 91.2% Top-5 accuracy with a 4-phase progressive unfreezing strategy.

dimgag /stanford_car_classification

Multi-class classification on Stanford Cars Dataset

ablanco1950 /CarsModels_Resnet_Pytorch

Project that detects the model of a car, between 1 and 196 models ( the 196 modelss of Stanford car file), that appears in a photograph with a success rate of more than 70% (using a test file that has not been involved in the training as a valid or training file, "unseen data") and can be implemented on a personal computer.

sameer-n012 /resnet-car-classification

该项目在 GitHub 上没有填写描述

DuhItzAniket /SEMEVIA

Fine-grained vehicle recognition on Stanford Cars (196 classes): YOLO11 detection, classical / deep / hybrid make-model-year classification, and an Identity Evidence Passport with calibrated candidate sets and a six-region Evidence Challenge. FastAPI + Docker.