1 Object Detection Using Faster R-CNN

Explained Faster R-Cnn theoretically .Practical Implementation of Faster R-CNN: https://www.youtube.com/watch?v=cReOzRvlLVA Yolo Algorithm: 1- https://youtu.be/k7B2ZqffDRE 2- https://youtu.be/xtn5D7yXF-4 Follow the steps below to complete the Faster R-CNN tutorial Step 1: Learn What is Faster R-CNN Follow this video: https://youtu.be/iHf2xHQ2VYo Step 2: Now Learn how to prepare dataset for Faster R-CNN Follow this video: https://youtu.be/cReOzRvlLVA Related code: https://github.com/AarohiSingla/Faster-R-CNN/blob/main/data_prep.ipynb Dataset used is Imagenet. This is the dataset used in this tutorial. You can download the dataset from below given links: https://storage.googleapis.com/openimages/2018_04/train/train-annotations-bbox.csv https://storage.googleapis.com/openimages/2018_04/train/train-images-boxable-with-rotation.csv https://storage.googleapis.com/openimages/v5/class-descriptions-boxable.csv Step 3: What is RPN ? Follow this video: https://youtu.be/if1tzf1p0gA Related code: https://github.com/AarohiSingla/Faster-R-CNN/blob/main/rpn_layer.ipynb Step 4: What is ROI? Follow this video: https://youtu.be/MDyqrSTtbgM Related Code: https://github.com/AarohiSingla/Faster-R-CNN/blob/main/classifier.ipynb Using the previous mail codes and videos, just understand the concepts. But to implement the whole algorithm use the code which I have mentioned in this email and follow the video link mentioned below. FOllow video: https://youtu.be/dA4pVGQ1isk Code: https://github.com/AarohiSingla/Faster-R-CNN-on-Custom-Dataset If you have any questions with what we covered in this video then feel free to ask in the comment section below & I'll do my best to answer your queries. 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. 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. 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. Please consider clicking the SUBSCRIBE button to be notified for future videos & thank you all for watching. Channel: https://www.youtube.com/channel/UCgHD... Support my channel 🙏 by LIKE ,SHARE & SUBSCRIBE Check the complete Machine Learning Playlist : https://www.youtube.com/playlist?list... Check the complete Deep Learning Playlist : https://www.youtube.com/playlist?list... Subscribe my channel: https://www.youtube.com/channel/UCgHD... Support my channel 🙏 by LIKE ,SHARE & SUBSCRIBE Contact: [email protected] #Faster-Rcnn #R-cnn #RCNN#PifordTechnologies #AI #ArtificialIntelligence #DeepLearning #ConvolutionalNeuralNetwork #CNN #ComputerVision #