How To Train an Object Detection Neural Network Using TensorFlow (GPU) on Windows 10

Video Description

This tutorial shows you how to train your own object detector for multiple objects using Google's TensorFlow Object Detection API on Windows. An updated written version of the tutorial is available at https://github.com/EdjeElectronics/TensorFlow-Object-Detection-API-Tutorial-Train-Multiple-Objects-Windows-10 . If you have questions, I usually respond more quickly on Twitter, so send me a tweet @EdjeElectronics ! https://twitter.com/EdjeElectronics Here's the relevant specs of the PC I used for training. GPU: GeForce GTX 1060 6Gb CPU: Intel i5-7600 RAM: 16GB DDR4-2133 -----Other links referenced in the video------ How to Install TensorFlow on Windows: https://youtu.be/RplXYjxgZbw TensorFlow Object Detection API repository: https://github.com/tensorflow/models TensorFlow Model Zoo page: https://github.com/tensorflow/models/blob/master/research/object_detection/g3doc/tf1_detection_zoo.md LabelImg utility: https://github.com/tzutalin/labelImg#installation -----Time links to each step in the video----- 1:54 Step 1. Install TensorFlow-GPU 3:14 Step 2. Set up Object Detection directory and Anaconda virtual environment 15:21 Step 3. Gather and label pictures 18:35 Step 4. Generate training data 20:16 Step 5. Create label map and configure training 23:46 Step 6. Train object detector 26:54 Step 7. Export inference graph 27:45 Step 8. Try out your object detector!! Credit goes to Dat Tran for writing the xml_to_csv.py and generate_tfrecord.py scripts, which I took from his Raccoon Detector tutorial (https://towardsdatascience.com/how-to-train-your-own-object-detector-with-tensorflows-object-detector-api-bec72ecfe1d9). Thanks also goes out to Sentdex (www.pythonprogramming.net) for writing a tutorial on how to use the Object Detection API on Linux. Music: Mason Donovan - Coffee House https://soundcloud.com/user-94567791/coffee-house