当前位置:网站首页>ML7自学笔记
ML7自学笔记
2022-07-29 05:22:00 【十九岁的花季少女】
机器学习处理实力问题的套路
1. HTTP检测任务与数据挖掘任务的核心
原始数据。对于一项任务,不应该自己只负责自己部分,应该尽量熟悉这一整个项目的流程,顶层架构,这让才会让自己有更大的收获。
2. 论文的重要程度
对于一份数据,提取特征十分重要。但是提取特征不能只靠个人列举,可以借鉴论文。
论文等级ABC,C一般是硕士毕业论文;A类的非常有价值值得借鉴;第一段介绍论文做了什么,第二段大环境;第三段介绍当前提出的方法,怎么做的,详细讲解算法;第四段实验证明。
找论文:百度网盘、各大网库、学校内网VPN。
3. BenchMark概述
一般不从知网找论文。而且一个东西不要自己从无到有做起来,一定有前人做好的部分可以借鉴。
benchmark。MPII相当于是一个最新的数据库。里面有论文,还有源码,有可能还有已经训练好的模型,那就可以直接用了。要慢慢找benchmark。可以搜“关键词+benchmark”
边栏推荐
- 3、 How to read video?
- 五、图像像素统计
- 【Transformer】SegFormer:Simple and Efficient Design for Semantic Segmentation with Transformers
- 【bug】XLRDError: Excel xlsx file; not supported
- 【比赛网站】收集机器学习/深度学习比赛网站(持续更新)
- 【Attention】Visual Attention Network
- 【目标检测】Generalized Focal Loss V1
- C # judge whether the user accesses by mobile phone or computer
- 【Transformer】ACMix:On the Integration of Self-Attention and Convolution
- [convolution kernel design] scaling up your kernels to 31x31: revising large kernel design in CNN
猜你喜欢

虚假新闻检测论文阅读(三):Semi-supervised Content-based Detection of Misinformation via Tensor Embeddings

Reporting Services- Web Service

【Transformer】AdaViT: Adaptive Vision Transformers for Efficient Image Recognition

ML16-神经网络(2)

ReportingService WebService form authentication
![[target detection] KL loss: bounding box progression with uncertainty for accurate object detection](/img/8c/1a561fab040730ae29901a04b70ac4.png)
[target detection] KL loss: bounding box progression with uncertainty for accurate object detection

【目标检测】6、SSD

C # judge whether the user accesses by mobile phone or computer
![[overview] image classification network](/img/2b/7e3ba36a4d7e95cb262eebaadee2f3.png)
[overview] image classification network

迁移学习——Transfer Joint Matching for Unsupervised Domain Adaptation
随机推荐
Spring, summer, autumn and winter with Miss Zhang (3)
【语义分割】语义分割综述
[overview] image classification network
1、 Pytorch Cookbook (common code Collection)
【综述】图像分类网络
【Transformer】SOFT: Softmax-free Transformer with Linear Complexity
Isaccessible() method: use reflection techniques to improve your performance several times
Flink connector Oracle CDC synchronizes data to MySQL in real time (oracle12c)
二、多并发实现接口压力测试
【语义分割】Fully Attentional Network for Semantic Segmentation
虚假新闻检测论文阅读(二):Semi-Supervised Learning and Graph Neural Networks for Fake News Detection
【pycharm】pycharm远程连接服务器
[target detection] generalized focal loss v1
ML15 neural network (1)
Operation commands in anaconda, such as removing old environment, adding new environment, viewing environment, installing library, cleaning cache, etc
迁移学习笔记——Adapting Component Analysis
【TensorRT】将 PyTorch 转化为可部署的 TensorRT
三、如何读取视频?
一、迁移学习与fine-tuning有什么区别?
ML9自学笔记