转载请注明:http://blog.youkuaiyun.com/forest_world
ubuntu:~/fast-rcnn$ ./tools/train_net.py --cpu 0 --solver models/CaffeNet/solver.prototxt --weights data/imagenet_models/CaffeNet.v2.caffemodel --imdb imagenet_train
caffe-fast-rcnn(Caffe、FSRCNN、FastRCNN)
参考资料:
http://blog.sina.com.cn/s/blog_855a82cd0102vnjq.html 【深度学习】研究Fast rcnn代码
http://blog.youkuaiyun.com/u010668907/article/details/50991664 fast-rcnn 训练自己数据集以及demo代码解读和总结(面向fast-rcnn初学者)
http://blog.youkuaiyun.com/u014696921/article/details/52565772 使用caffe中的imagenet对自己的图片进行分类训练(超级详细版)
http://sunshineatnoon.github.io/Train-fast-rcnn-model-on-imagenet-without-matlab/ How to train fast rcnn on imagenet
I’ve been playing with fast-rcnn for a while. This amazing and wonderful project helps me understand more about deep learning and its beautiful power. However, there’s only a pre-trained fast rcnn model for pascal voc with 20 classes. To use this project in real applications, I need to train a model on the ImageNet detection dataset( For time’s sake, I only chose two classes out of 200 classes). So this blog records what to be done to train a fast rcnn on ImangeNet.
http://blog.youkuaiyun.com/xjz18298268521/article/details/52683330 Faster_rcnn训练自己的数据集