How to train an Object detection classifier for Multiple Objects using Tensorflow (GPU) on Windows 10
This repo is adapted from https://github.com/EdjeElectronics/Tensorflow-Object-Detection-API-Tutorial-Train-Multiple-Objects-Windows-10. Almost all the steps are aligned to that repo.
Noted: The above repo works best with Python version 3.5 and Tensorflow (GPU) version v1.15
This repo makes the tutorial with minor changes, but the original idea is still kept the same that is How to use Tensorflow's Object Detection API to train an object detection classifier for multiple objects on Windows 10, 8 or 7. (It will work better in Linux with some changes).
The tutorial also has a Youtube video that walks through every step of it.
This Repo basically replicate the Repo of EdjieElectronics with changes where applicable:
- Installing Anaconda, CUDA, and cuDNN
- Setting up the Object Detection directory structure and Anaconda Virtual Environment
- Gathering and labeling pictures
- Generating training data
- Creating a label map and configuring training
- Training
- Exporting the inference graph
- Testing and using your newly trained object detection classifier