thtrieu/darkflow

Rate of validation dataset ?

Open

#97 创建于 2017年3月22日

在 GitHub 查看
 (5 评论) (0 反应) (0 负责人)Python (6,120 star) (2,102 fork)batch import
help wanted

描述

Hello

I readed many documents in the literatures and I saw that most of them said, that we need data for training and data for test validation, and my question is in the code where is the part that do the validation test. and how can we fix the rate between the test validation and the train data. For example if I have 20 images what is the rate of validation images and the train images

Thanks,

贡献者指南

技术栈
pythontensorflow
领域
machine learning
议题类型
documentation
难度面向新贡献者的预计实现难度，1 表示很小改动，5 表示专家级工作。
2
预计时间有经验贡献者完成调查、实现、测试并准备 pull request 的粗略时间范围。
under 1 hour
活动状态议题当前的可参与程度：新鲜、活跃、陈旧、阻塞或等待维护者输入。
stale
清晰度议题是否清楚说明期望改动、验收标准和下一步。
mostly clear
前置要求
basic machine learning concepts
新手友好度1-100 的估计分数，表示该议题对首次贡献者的友好程度。
70
研究方向
The issue asks about the validation split rate during training. In darkflow, validation data can be specified via command line options or in the config file. Look at the training script (e.g., train.py) or the configuration files to see how validation or train parameters are handled. Comments in the issue suggest that the user should refer to the documentation or the README for details on data splitting. Provide a clear explanation of how to set the validation ratio, possibly by modifying the training command or config.