license non-commercial
部分网站可能需要翻墙才能打开。
该车型检测使用的是开源的模型,Paper见下:
A Large-Scale Car Dataset for Fine-Grained Categorization and Verification
L. Yang, P. Luo, C. C. Loy, X. Tang, arXiv:1506.08959, 2015
一、该模型需要一个已经训练好的caffemodel,地址在caffe Model Zoo里面,名字叫做GoogLeNet_cars,下载链接为
http://mmlab.ie.cuhk.edu.hk/datasets/comp_cars/googlenet_finetune_web_car_iter_10000.caffemodel
二、需要
https://github.com/bogger/caffe-multigpu/blob/multigpu/models/finetune_web_car/
matlab/make_model_names_cls.mat
CSDN地址:http://download.csdn.net/download/s9434/10163226
五.找到一张自己的测试图片,输入路径即可,例子如下:
./build/examples/cpp_classification/classification.bin \
models/bvlc_reference_caffenet/Comp_cars_deploy.prototxt \
models/bvlc_reference_caffenet/googlenet_finetune_web_car_iter_10000.caffemodel \
data/ilsvrc12/imagenet_mean.binaryproto \
data/ilsvrc12/CompCars_make_model_names_cls.txt \
examples/images/1.jpg
亲测可行!