Tag：depth
-
Time：2020-5-23
Cats can understand the series Computer vision for deep learning Day 2 deploy a trained deep neural network Objective: be able to use the existing neural network model in your own code code Import Caffe is used to use deep neural network import matplotlib.pyplot as plt ## matplotlib.pyplot Used to output visual images Import CV2 […]
-
Time：2020-5-22
Recently, the Graphics Lab of the computer department of Tsinghua University announced a new open-source deep learning framework: jittor, which is also the first open-source deep learning framework developed by universities in China. According to the official website, this is a deep learning framework based on just in time, internal use of innovative meta operators […]
-
Time：2020-5-21
On the afternoon of March 25, Kuangshi technology, an AI company, officially released its end-to-end AI algorithm platform brain + +. It is reported that brain + + has large-scale algorithm research and development capabilities, including deep learning framework megengine (Tianyuan), deep learning cloud computing platform megcompute, and data management platform megdata, which respectively correspond […]
-
Time：2020-5-16
This paper interprets a new algorithm of deep attention, which is deep residual shrinkage network. In terms of function, the deep residual shrinkage network is a feature learning method for strong noise or highly redundant data. This paper first reviews the relevant basic knowledge, then introduces the motivation and implementation of the deep residual shrinkage […]
-
Time：2020-5-16
This is a series of articles that evaluate a question from various perspectives: “should I use AI for my business? Can I use AI? “ Current evaluation angle – black box Black box is a disadvantage of artificial intelligence Not all artificial intelligence is black box. The black box refers to the most popular and […]
-
Time：2020-5-7
1. Traditional Ajax requests var xhr = window.XMLHttpRequest ? new XMLHttpRequest() : new ActiveXObject(“Microsoft.XMLHTTP”) xhr.onreadystatechange = function() { if (xhr.readyState === 4 && xhr.status === 200) { // coding } } xhr.open(“GET”,”xxx”,true) xhr.send() Ajax can only be nested when there is a request in the request. This nested callback will cause poor code readability, which […]
-
Time：2020-5-6
Title Requirements Given a binary tree, find the leftmost value in the last row of the tree. Example 1: Input: 2 / \ 1 3 Output:1 Example 2: Input: 1 / \ 2 3 / / \ 4 5 6 / 7 Output:7 Note: You may assume the tree (i.e., the given root node) is […]
-
Time：2020-5-3
Abstract: tensorflow high level API High level encapsulation API Some students asked, we want to learn a set of tensorflow that can be used. Just call it like programming. We don’t want to learn the details of machine learning. Is there such a way? For models with mature solutions, what not?After a quick review of […]
-
Time：2020-4-29
Cats can understand Day3 In the last blog, we introduced the classification of images, and then we will see how to detect images. Method 1: scan pictures with code (no overlapping) ##The first step, like the previous blog, is to deploy the deep learning network import time Import numpy as NP Import matplotlib.pyplot as plot […]
-
Time：2020-4-29
Background: In mysql, if there is a limited level, for example, if we can determine the maximum depth of the tree in advance, then the depth of the tree with all nodes as roots will not exceed the maximum depth of the tree, then we can directly implement it through left join. But most of […]
-
Time：2020-4-24
1、 5 deep pits easy for beginners to step on 1. Mental state is easily influenced by learning state The first deep hole that beginners are easy to step on is their bad mentality. Some people are overconfident and believe in their learning ability. But when it comes to very difficult algorithms or reasoning, it’s […]
-
Time：2020-4-18
As we have written in the previous article, the development of artificial intelligence is not without twists and turns. In different historical stages, the mainstream research methods are different. At the beginning, if else Structure, simple logical judgment string matching, and exhaustive calculation in the later stage gradually develop to the mainstream research method of […]
