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/Te... .

If you have questions, I usually respond more quickly on Twitter, so send me a tweet @EdjeElectronics !   / 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:    • How To Install TensorFlow (GPU versio...  
TensorFlow Object Detection API repository: https://github.com/tensorflow/models
TensorFlow Model Zoo page: https://github.com/tensorflow/models/...
LabelImg utility: https://github.com/tzutalin/labelImg#...

----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.... 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
  / coffee-house