简体   繁体   English

我怎样才能停止模型训练并恢复它?

[英]How can i stop model training and resume it?

I am working on object detection with autonomous datasets .我正在使用自主数据集进行对象检测。 I want to train my model with 10000 train images,2000 test,2000 validation images.I will use object detection tensorflow lite model maker.我想用 10000 个训练图像、2000 个测试、2000 个验证图像来训练我的模型。我将使用对象检测 tensorflow lite 模型制造商。

Project link : tensorflow.org/lite/tutorials/model_maker_object_detection项目链接:tensorflow.org/lite/tutorials/model_maker_object_detection

After setting batch size 32, the training takes 50 epochs and continues for 2 days(Step 3).I can't keep my computer on for two days.I am running the project in jupyter notebook设置批量大小 32 后,训练需要 50 个 epoch 并持续 2 天(第 3 步)。我不能让我的电脑两天开机。我正在 jupyter notebook 中运行该项目

How can i stop model training and again resume it ?我怎样才能停止模型训练并再次恢复它? (eg stop the 10th epoch and continue one day later) (例如停止第 10 个 epoch 并在一天后继续)

I sure it depend on your code you working on.我确定这取决于您正在处理的代码。 You can do that with tensorflow check How to Pause / Resume Training in Tensorflow您可以使用 tensorflow 检查如何在 Tensorflow 中暂停/恢复训练

a sleep mode is a better option.睡眠模式是更好的选择。 it will make your pc rest for some time and your work will be resumed after you log in again它会让您的电脑休息一段时间,您的工作将在您再次登录后恢复

声明:本站的技术帖子网页,遵循CC BY-SA 4.0协议,如果您需要转载,请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.

 
粤ICP备18138465号  © 2020-2024 STACKOOM.COM