thtrieu/darkflow

Rate of validation dataset ?

Open

#97 opened on Mar 22, 2017

View on GitHub
 (5 comments) (0 reactions) (0 assignees)Python (6,120 stars) (2,102 forks)batch import
help wanted

Description

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,

Contributor guide

Tech stack
pythontensorflow
Domain
machine learning
Issue type
documentation
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
2
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
under 1 hour
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
stale
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
mostly clear
Prerequisites
basic machine learning concepts
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
70
Research direction
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.