Faster R-CNN on Custom Dataset | Custom Object Detector

Learn how to build your Custom Object Detector Using Faster RCNN. Also explained how to prepare custom dataset for Faster RCNN

OID v4 GitHub link: https://github.com/EscVM/OIDv4_ToolKit

GitHub link of video’s code: https://github.com/AarohiSingla/Faster-R-CNN-on-Custom-Dataset

Recommended to check these videos to understand Faster RCNN in depth.

Faster R CNN Basics: https://youtu.be/iHf2xHQ2VYo

RPN Explanation: https://youtu.be/if1tzf1p0gA

ROI Explanation : https://youtu.be/MDyqrSTtbgM
A Faster R-CNN object detection network is composed of a feature extraction network which is typically a pretrained CNN. This is then followed by two subnetworks which are trainable.
The first is a Region Proposal Network (RPN), which is, as its name suggests, used to generate object proposals and the second is used to predict the actual class of the object.

The architecture of Faster R-CNN is complex.
We provide input image, from which we want to obtain:
a list of bounding boxes.
a label assigned to each bounding box.
a probability for each label and bounding box.

We will use VGG as a base network for extracting features.

Anchor Boxes:
Anchor boxes are some of the most important concepts in Faster R-CNN. These are responsible for providing a predefined set of bounding boxes of different sizes and ratios that are used for reference when first predicting object locations for the RPN.
Anchors are fixed bounding boxes that are placed throughout the image with different sizes and ratios that are going to be used for reference when first predicting object locations.

Non-maximum suppression (NMS)
NMS is the second stage of filtering used to get rid of overlapping boxes, because even after filtering by thresholding over the classes scores, we still end up with a lot of overlapping boxes.

Видео Faster R-CNN on Custom Dataset | Custom Object Detector канала Code With Aarohi