Super detailed explanation of CTC theory and actual combat

CTC introduction For speech recognition, the input of training data is a piece of audio and the output is its transcribed text, but we don't know how to align letters and speech. This makes training speech recognition more complex than it seems. It is very difficult and error prone for people to mark this alignment, because the boundaries ...

Posted by Poofman on Sat, 30 Apr 2022 05:37:58 +0300

Chapter 5 + Deformation

Chapter 5 Deformation import numpy as np import pandas as pd First, the deformation of the length and width table What is a long watch? What is a wide table? This concept is for a certain feature. For example: if a table stores gender in a certain column, then it is a long table about gender; if gender is used as a column name, and the ele ...

Posted by luked23 on Fri, 29 Apr 2022 19:07:00 +0300

Real-time face recognition and object recognition based on nodejs on Raspberry Pi 4B using tfjs-node

start I had this idea a few years ago. I wanted to be an assistant that can recognize faces and objects, and can recognize commands through simple dialogues. Similar to the offline enhanced version of Xiao Ai, I can monitor my cabin by the way. However, I was too busy at the end of the year and didn’t have the time and energy to toss. I ...

Posted by ludjer on Fri, 29 Apr 2022 15:52:37 +0300

openvino Series 6 Monocular depth estimation, input as picture

openvino Series 6 Monocular depth estimation, input as picture This case demonstrates how to use MidasNet for monocular depth estimation and input pictures in OpenVINO. Model information can be found in here Found. Environment Description: Operating environment of this case: Win10IDE: VSCodeopenvino version: 2022.1Code link,3-monodepth-im ...

Posted by shiva on Fri, 29 Apr 2022 15:20:25 +0300

Shell crawling

I've been learning to write crawlers in python for several days. Let's write a small crawler to verify the learning results. This article is suitable for Xiaobai to eat. You guys want to have fun~ Tip: This article is for learning and communication only, do not use it for illegal purposes!!! The text and pictures of this article come f ...

Posted by dickey on Fri, 29 Apr 2022 04:01:20 +0300

Neural network -- Understanding BP neural network from code

As soon as we mention the back-propagation algorithm, we unconsciously think of the derivation of random gradient descent, sigmoid activation function and the back-propagation law that makes the head bigger. Even after learning the principle of back-propagation neural network, we are still confused. Here, we recommend a textbook Python neural n ...

Posted by kendall on Thu, 28 Apr 2022 16:47:15 +0300

Bitcoin prediction with pytorch

1. Overview of bitcoin forecast Bitcoin prediction is the same as stock prediction. Bitcoin prediction is divided into two parts. The first is model training and the second is model prediction. In model training, I am divided into three parts: data reading, feature selection and model training. model training data fetchfeature selection mo ...

Posted by DillyDong on Thu, 28 Apr 2022 03:45:44 +0300

20 lines of code: image classification and prediction can be easily done in Python under Serverless architecture

Author Jiang Yu preface Image classification is a hot topic in the field of artificial intelligence. Popular interpretation is an image processing method that distinguishes different types of targets according to the different characteristics reflected in the image information. It uses computer to quantitatively analyze the image, and clas ...

Posted by newbeee on Thu, 28 Apr 2022 00:00:39 +0300

Single pass clustering algorithm for weather clustering

Introduction to clustering algorithm (1) Systematic clustering method The basic idea of systematic clustering method is that samples with short distance are clustered first, and samples with long distance are clustered later. According to the different definitions between classes, the system clustering method can be divided into 8 kind ...

Posted by neex1233 on Wed, 27 Apr 2022 13:53:03 +0300

[machine learning practice] - Titanic dataset -- Bagging promotion (random forest)

1. Write in front: This part belongs to the actual combat part, and pays more attention to the application of the algorithm in the actual project. For further understanding of the perceptron algorithm itself, please refer to the following links, which have played a great role in my learning process: [1]Hands-On Machine Learning with Scikit-Lear ...

Posted by vipul73 on Wed, 27 Apr 2022 10:28:32 +0300