当前位置:网站首页>Deep learning, "grain and grass" first--On the way to obtain data sets
Deep learning, "grain and grass" first--On the way to obtain data sets
2022-08-04 06:21:00 【language】
Event address: CSDN 21-day Learning Challenge
Tuesday August 2nd, 2022 partly cloudy
Creative Project
Opportunity: Record the growth of Deep Learning Xiaobai
Expectation: At least 21 days/article output to share deep learning related notes
Vision: To be able to keep writing and keep updating
time | Theme | Content | Progress |
---|---|---|---|
2022-08-01 | Hello world,Hello CNN MNIST! | Deep learning cloud environment experience, understand the deep learning framework | Completed |
2022-08-02 | Deep learning, "grass and grass" first - Talking about the way to obtain data sets | Master the way to obtain data sets and understand the processing methods of data sets in the deep learning framework | Completed |
2022-08-03 | Late night learning, just for "volume" - a detailed introduction to convolutional neural networks | Take weather recognition and clothing image classification as examples to explain convolutional neural networks | To learn |
Data
As early as the CCF-GAIR 2020 summit, Professor Zhihua Zhou pointed out in his report titled "Abductive Learning" that the three elements for the role of artificial intelligence technology - data, algorithms, and computing power, in previous yearsIn the "big data era", big data itself does not necessarily mean great value. Data is a resource. To obtain the value of resources, effective data analysis must be carried out, and effective data analysis mainly relies on machine learning algorithms. Machine learning algorithmsIn China, deep learning technology has made great progress and exerted great power with the support of big data and large computing power.
Today, data is stillA prerequisite for AI development,
"To be continued, looking forward to reunification..."
边栏推荐
- 2020-10-19
- Copy Siege Lion 5-minute online experience MindIR format model generation
- 度量学习(Metric learning)—— 基于分类损失函数(softmax、交叉熵、cosface、arcface)
- PCL1.12 解决memory.h中EIGEN处中断问题
- yolov3 data reading (2)
- 图像resize
- 深度学习理论 —— 初始化、参数调节
- [Go language entry notes] 13. Structure (struct)
- MNIST手写数字识别 —— 基于Mindspore快速构建感知机实现十分类
- 光条提取中的连通域筛除
猜你喜欢
arm-3-中断体系结构
Windows10重置MySQL用户密码
YOLOV4流程图(方便理解)
MNIST Handwritten Digit Recognition - Building a Perceptron from Zero for Two-Classification
PP-LiteSeg
数据库的简述与常用操作指南
AWS使用EC2降低DeepRacer的训练成本:DeepRacer-for-cloud的实践操作
AWS uses EC2 to reduce the training cost of DeepRacer: DeepRacer-for-cloud practical operation
亚马逊云科技 Build On 2022 - AIot 第二季物联网专场实验心得
arm交叉编译
随机推荐
tensorRT教程——tensor RT OP理解(实现自定义层,搭建网络)
PCL1.12 解决memory.h中EIGEN处中断问题
Thunderbolt turns off automatic updates
TensorFlow: tf.ConfigProto() and Session
Postgresql snapshot
Attention Is All You Need(Transformer)
0, deep learning 21 days learning challenge 】 【 set up learning environment
arm-3-中断体系结构
Copy攻城狮5分钟在线体验 MindIR 格式模型生成
arm-2-基础阶段
计算某像素点法线
[Go language entry notes] 13. Structure (struct)
MNIST手写数字识别 —— 从感知机到卷积神经网络
度量学习(Metric learning)—— 基于分类损失函数(softmax、交叉熵、cosface、arcface)
Comparison of oracle's number and postgresql's numeric
MNIST Handwritten Digit Recognition - Building a Perceptron from Zero for Two-Classification
【Copy攻城狮日志】飞浆学院强化学习7日打卡营-学习笔记
DRA821 环境搭建
【CV-Learning】Object Detection & Instance Segmentation
【论文阅读】Further Non-local and Channel Attention Networks for Vehicle Re-identification