Region Based Convolutional Neural Networks

Article on Selective Search Algorithm:

https://www.geeksforgeeks.org/selective-search-for-object-detection-r-cnn/

RCNN:

Last changed by

Introduction Mask R-CNN is a masterpiece of He Kaiming God in 2017. It performs instance segmentation while performing target detection, and has achieved excellent results. It has won the COCO 2016 championship without any tricks. The design of its network is also relatively simple. On the basis of Faster R-CNN, a branch is added to the original two branches (classification + coordinate regression) for semantic segmentation , as shown in the following figure Mask R-CNN detailed Introduction So why does this network have such good results, and what are the network details? The following are introduced one by one in detail. Before introducing Mask R-CNN, first understand what is segmentation, because Mask R-CNN does this, so this must be figured out first, see the following figure, which mainly introduces several different segmentation, of which Mask RCNN does Among theminstance segmentation. Semantic segmentation: classify pixel by pixel in an image.

Jan 25, 2022

Comparison of YOLO1, YOLO2, and YOLO3

YOLO1 1.The main ideas of target detection Unlike the RCNN series, YOLO treats target detection as a regression problem, and directly uses a network for classification and box regression. The specific method is: divide the image into S * S grids, and each grid predicts the positions (x, y, w, h) of B bboxes, confidence (confidence is the intersection ratio), and class probability. The output dimension is S * S * (B * 5 + C), and C is the number of categories. No matter how many boxes are contained in the grid, each grid only predicts a set of class probabilities. During the test, the conditional class probability and the confidence of the prediction box are multiplied to indicate that each box contains the confidence of a certain type of object. This score can represent the category probability and prediction accuracy of the box at the same time. 2. Overall network structure The basic network model is GoogLe Net, but instead of using its inception module, it uses 1 * 1 and 3 * 3 convolutional layers alternately.

Jan 3, 2022

Linux

User: Regular user (only has access in their home directory only) Root user or Super user (Admin) $ : Regular User (#) : Sudo user/Super user Absolute Path : cd/bin/fo1

Nov 13, 2021

Inception (Also Known as GoogleNet)

Also known as GoogLeNet , it is a 22-layer network that won the 2014 ILSVRC Championship. The original intention of the design is to expand the width and depth on its basis . which is designed motives derived from improving the performance of the depth of the network generally can increase the size of the network and increase the size of the data set to increase, but at the same time cause the network parameters and easily fit through excessive , computing resources inefficient and The production of high-quality data sets is an expensive issue. Its design philosophy is to change the full connection to a sparse architecture and try to change it to a sparse architecture inside the convolution. The main idea is to design an inception module and increase the depth and width of the network by continuously copying these inception modules , but GooLeNet mainly extends these inception modules in depth.

Nov 11, 2021