Tag：Part one
-
Time：2020-12-8
1、 Face detection 1. Face detection using OpenCV Opencv uses the algorithm of object detection framework named Viola Jones for face detection. Step 1: Download opencv Library pip install opencv-python -i https://pypi.tuna.tsinghua.edu.cn/simple Step 2: find the default pre training weight file 1. Generally, there is a haarcascade in / lib / python3.7/site-packages/cv2/data directory of the […]
-
Time：2020-12-2
This article is learning notes Participation: Wang bokings, Sophia Recently concluded CVPR 2020 has made a great contribution to the promotion of object detection. In this article, we will introduce some particularly impressive papers. 1. A hierarchical graph network for 3D object detection on point clouds Hgnet consists of three main components: U-shaped network based […]
-
Time：2020-10-29
Continued:Deep residual network + adaptive parameterized relu activation function (parameter adjustment record 1)https://blog.csdn.net/dangqin… This paper is still testing the deep residual network + adaptive parameterized relu activation function. The number of residual modules is increased to 27, and the others remain unchanged. The number of convolution kernels is still 8, 16 to 32. Continue to […]
-
Time：2020-8-21
Adaptive parameterized relu is a kind of dynamic relu, which was submitted to IEEE Transactions on industrial electronics on May 3, 2019 and accepted on January 24, 2020,Published on IEEE website on February 13, 2020。 In this paper, on the basis of parameter adjustment record 6, we continue to adjust the super parameters and test […]
-
Time：2020-8-20
Adaptive parametric relu is a kind of dynamic relu, which was submitted to IEEE Transactions on industrial electronics on May 3, 2019 and accepted on January 24, 2020,Published on IEEE website on February 13, 2020。 In this paper, on the basis of parameter adjustment Record 9, shear is added to the data enhancement part_ Range […]
-
Time：2020-8-15
Adaptive parametric relu is a kind of dynamic relu, which was submitted to IEEE Transactions on industrial electronics on May 3, 2019 and accepted on January 24, 2020,Published on IEEE website on February 13, 2020。 In this paper, on the basis of parameter adjustment record 15, the number of convolution kernels of the first residual […]
-
Time：2020-8-14
Adaptive parameterized relu is a kind of dynamic relu, which was submitted to IEEE Transactions on industrial electronics on May 3, 2019 and accepted on January 24, 2020,Published on IEEE website on February 13, 2020。 On the basis of parameter adjustment record 16, two residual modules are added in this paper to test its effect […]
-
Time：2020-8-4
In this paper, on the basis of parameter tuning record 25, the number of neurons in adaptive parameterized relu middle layer is increased from 2 to 4, and a dropout layer is added to test its effect on cifar10 dataset. The basic principle of adaptive parametric relu is as follows Keras program: #!/usr/bin/env python3 # […]
