caffe的.solverstate文件:实现训练中断后,继续之前的训练
重新调用的命令:
./build/tools/caffe train —solver=examples/test/solver.prototxt —snapshot=examples/test/test_100000.solverstate
参考:
https://blog.csdn.net/cs24k1993/article/details/78884270
https://blog.csdn.net/wang4959520/article/details/51831637
https://blog.csdn.net/baidu_32173921/article/details/72470019
https://blog.csdn.net/laoxuan2011/article/details/51594155
还没有评论,来说两句吧...