标签：数据集 -o net run 训练 file http 技术分享 should
git clone https://github.com/weiliu89/caffe.git cd caffe git checkout ssd #确保当前的分支是origin/ssd cp Makefile.config.example Makefile.config make -j8 # Make sure to include $CAFFE_ROOT/python to your PYTHONPATH. make pycaffe make test -j8 # (Optional) make runtest -j8
./data/VOC0712/create_list.sh
./data/VOC0712/create_data.sh
# It will create model definition files and save snapshot models in: # - $CAFFE_ROOT/models/VGGNet/VOC0712/SSD_300x300/ # and job file, log file, and the python script in: # - $CAFFE_ROOT/jobs/VGGNet/VOC0712/SSD_300x300/ # and save temporary evaluation results in: # - $HOME/data/VOCdevkit/results/VOC2007/SSD_300x300/ # It should reach 77.* mAP at 120k iterations. python examples/ssd/ssd_pascal.py
senya@senya-PC:~/Desktop/Senya-Win/DL/caffe/jobs/VGGNet/VOC0712/SSD_300x300$ ls
deploy.prototxt test.prototxt VGG_VOC0712_SSD_300x300.sh
solver.prototxt train.prototxt
ssd_pascal.py VGG_VOC0712_SSD_300x300.log
从上面的jobs文件夹的内容不难看出，该文件夹保留了模型的结构，分别保存在不同的prototxt文件中。
标签：数据集 -o net run 训练 file http 技术分享 should
原文地址：https://www.cnblogs.com/cdyforever/p/9378648.html
