Application example of PCA dimensionality reduction algorithm -- kaggle handwritten numeral recognition

preface In the previous blog post, we learned Dimension reduction algorithm PCA , and Parameters of PCA . This article is based on the premise of having a certain foundation for PCA. This paper mainly introduces the application of PCA algorithm in practice. Including the selection of PCA parameters, the use of PCA in training set and test ...

Added by racing_fire on Thu, 20 Jan 2022 00:55:16 +0200

3d machine learning open3d learning record -- point cloud 2

preface Follow the previous section Point cloud 1 Data address of this section: link: https://pan.baidu.com/s/1O4s8tFOvExhuKMl2OCv4Kg Extraction code: 82u1 1. Point cloud clipping Code first import open3d as o3d pcd=o3d.io.read_point_cloud("./test_data/Crop/fragment.ply") val=o3d.visualization.read_selection_polygon_volume("./test_data ...

Added by project168 on Thu, 20 Jan 2022 00:29:55 +0200

Operation processing record of artificial neural network course in 2021

§ 01 job handling In the autumn of 2021 artificial neural network The course consists of two classes: Internal courses of Tsinghua University;Courses of Shenzhen Research Institute; 1.1 operation requirements There are four assignments and a course paper in the whole semester. 1.1.1 requirements for four operations Neu ...

Added by lexx on Wed, 19 Jan 2022 15:30:18 +0200

System joint commissioning test and deployment

Rimeng Society AI AI:Keras PyTorch MXNet TensorFlow PaddlePaddle deep learning real combat (irregular update) Intelligent dialogue system: Unit dialogue API Introduction to the overall architecture and tools of online chat: Flask web, Redis, Gunicorn service component, Supervisor service monitor, Neo4j diagram database linux Installation n ...

Added by johnsonzhang on Wed, 19 Jan 2022 12:10:36 +0200

New features of BigQuery ML: unsupervised anomaly detection of time series and non time series data

When it comes to anomaly detection, the main challenge is that it is difficult to define anomalies. For example, how can we define and predict abnormal network intrusion, system defects and security fraud? If known exception data has been marked, we can choose from the various types of supervised machine learning models (see the link below fo ...

Added by fizix on Wed, 19 Jan 2022 06:11:15 +0200

Opencv -- image processing

Grayscale image output: import cv2 #The format read by opencv is BGR import numpy as np import matplotlib.pyplot as plt#Matplotlib is RGB %matplotlib inline img=cv2.imread('miku.png') img_gray = cv2.cvtColor(img,cv2.COLOR_BGR2GRAY) img_gray.shape cv2.imshow("img_gray", img_gray) cv2.waitKey(0) cv2.destroyAllWindows() Picture output: ...

Added by ssjskipp on Wed, 19 Jan 2022 03:14:04 +0200

[github excellent AI project] realize 4K60 frame video human body real-time matting

Project address: https://github.com/PeterL1n/RobustVideoMatting article: Robust Video Matting in PyTorch, TensorFlow, TensorFlow.js, ONNX, CoreML! Powerful video matting function in PyTorch, TensorFlow and TensorFlow. js,ONNX,CoreML! Stable video matting (RVM) Thesis Robust High-Resolution Video Matting with Temporal Guidance The offi ...

Added by cybercog on Tue, 18 Jan 2022 15:47:28 +0200

One hot coding of category tensors by PyTorch

One hot coding of category tensors by PyTorchThis article has authorized the platform of the polar city and is the official account of the polar platform. No second reprint is allowed without permissionOriginal document: https://www.yuque.com/lart/ugkv9f/src5w8Code warehouse: https://github.com/lartpang/CodeForArticle/tree/main/OneHotEncoding.P ...

Added by robinhood on Tue, 18 Jan 2022 14:28:12 +0200

Summary of the most complete Python machine learning and deep learning library in Station C (containing a large number of examples, recommended Collection)

preface At present, with the popularity of artificial intelligence, it has attracted the attention of many industries to artificial intelligence. At the same time, it has also ushered in waves of artificial intelligence learning upsurge. Although the principles behind artificial intelligence can not be introduced in detail in a short artic ...

Added by nologin666 on Mon, 17 Jan 2022 20:41:00 +0200

day5 - loop exercises and lists

Python list 1. What is a list ① What does a list look like: a list is a container data type (sequence); Take [] as the flag of the container, in which multiple elements are separated by commas: [element 1, element 2, element 3,...] ② Characteristics of list: the list is variable (the number, value and order of elements are variable) - add, de ...

Added by softnmedia on Mon, 17 Jan 2022 19:36:14 +0200