Training an R-CNN object detector with Keras and TensorFlow

Hi,

In today's brand-new tutorial, you will learn how to build an R-CNN object detector using Keras and TensorFlow:

Today's tutorial is the final part in our 4-part series on deep learning and object detection:

• Part 1: Turning any deep learning image classifier into an object detector with Keras and TensorFlow
• Part 2: OpenCV Selective Search for Object Detection
• Part 3: Region proposal for object detection with OpenCV, Keras, and TensorFlow
• Part 4: R-CNN object detection with Keras and TensorFlow (today's tutorial)

Last week, you learned how to use region proposals and Selective Search to replace the traditional computer vision object detection pipeline of image pyramids and sliding windows:

1. Using Selective Search, we generated candidate regions (called "proposals") that could contain an object of interest.
2. These proposals were passed in to a pre-trained CNN to obtain the actual classifications.
3. We then processed the results by applying confidence filtering and non-maxima suppression.

Our method worked well enough — but it raised some questions:

"What if we wanted to train an object detection network on our own custom datasets?

How can we train that network using Selective Search search?

And how will using Selective Search change our object detection inference script?"

In fact, these are the same questions that Girshick et al. had to consider in their seminal deep learning object detection paper Rich feature hierarchies for accurate object detection and semantic segmentation.

Each of these questions will be answered in today's tutorial — and by the time you're done reading it, you'll have a fully functioning R-CNN, similar (yet simplified) to the one Girshick et al. implemented!

Click here to see the full tutorial — you won't want to miss it!