http://blog.csdn.net/wang4959520/article/details/51831637

我們?cè)谑褂胏affe訓(xùn)練過(guò)程中會(huì)生成.caffemodel和.solverstate文件，一個(gè)是模型文件，一個(gè)是中間狀態(tài)文件（生成多少個(gè)取決于你自己設(shè)定的snapshot）。當(dāng)訓(xùn)練過(guò)程中斷，你想繼續(xù)運(yùn)行數(shù)據(jù)學(xué)習(xí)，此時(shí)只需要調(diào)用.solverstate文件即可。

使用方式代碼，我使用的是.sh直接運(yùn)行，配置和官方給的文件train_caffenet.sh差不多，稍微添加點(diǎn)內(nèi)容就可以了。

[plain]?view plain?copy ?

./build/tools/caffe?train?\??

?????--solver=examples/test/solver.prototxt?--snapshot=examples/test/test_100000.solverstate??

上述配置根據(jù)個(gè)人文件路徑實(shí)際情況相應(yīng)修改即可。

The solverstate file, as its name conveys, stores the state of the solver and not any information related to classification results. The model is saved as caffemodel file, which you can use to obtain classification results for your data. If you want to fine-tune your network you may use a pre-trained caffemodel file. This will save time as your network does not need to learn from scratch. But, in case your present training needs to be halted, due to a power cut or an unexpected reboot, you may resume your training form the previous snapshot of the solverstate. The difference between using the solverstate and the caffemodel files is that the former allows you to complete your training in the pre-determined manner while the latter may require changes in certain training parameters such as the maximum number of iterations.

總結(jié)

以上是生活随笔為你收集整理的solverstate的使用的全部?jī)?nèi)容，希望文章能夠幫你解決所遇到的問(wèn)題。

如果覺(jué)得生活随笔網(wǎng)站內(nèi)容還不錯(cuò)，歡迎將生活随笔推薦給好友。