关于GCU、沐曦GPGPU、MLU、0卡V100资源4月7日恢复上架的公告>>> 关于共建具身智能开源数据集的倡议>>> 关于云脑任务中统一路径访问方式的公告>>> 关于将启智集群GPU资源迁移至智算集群的公告>>>
tyx_neu
/
Learning_NOTES
Not watched
1
2
Fork 0
Code
Releases 0 Wiki Activity
Issues 5 Pull Requests 0 Datasets Model Cloudbrain
You can not select more than 25 topics Topics must start with a chinese character,a letter or number, can include dashes ('-') and can be up to 35 characters long.
26 Commits
1 Branch
34 MiB
26 Download
 
Branch: master
Branches Tags
${ item.name }
Create branch ${ searchTerm }
from 'master'
${ noResults }
tyx_neu d8fe6880a2 update mobilenets 1 year ago
Basic_Knowledge update basic knowledge in Q&A way 1 year ago
Classical_CNNs_for_classification Update RepLKNet notes 1 year ago
Feature_Pyramid(continued) update Feature Pyramid NOTES continued 1 year ago
Light_weight_Deep_Neural_Networks update mobilenets 1 year ago
Prohibited_Items_Detection/Few-Shot modified folder name 1 year ago
Transformers update swin-transformer 1 year ago
FORMER.docx update 1 year ago
README.md update README 1 year ago

README.md

❗版权归tyx个人所有​

☀️导航

📌Basic_Knowledge（基础知识篇）

  • Step_One
  • Step_Two
  • Step_Three

📌Classical_CNNs_for_classification（经典CNN模型总结）

📌Feature_Pyramid（特征金字塔方法总结，持续更新中）

📌Light_weight_Deep_Neural_Networks（轻量化模型总结，暂未更新）

📌Transformers（暂未更新）

📌Prohibited_Items_Detection（持续更新）

☀️目前已经更新的内容

📌基础知识篇

基础知识部分主要回答了有关以下内容：

  • 统计学习的一些基础内容（主要参考李航的统计学习方法）

  • 有关于深度学习的基础内容：

    • 卷积的基础内容，例如1×1卷积的作用，常见的卷积方法

    • 损失函数

    • 常用的激活函数及其特点

    • 正则化方法

    • 梯度相关内容，例如梯度消失/爆炸的原因，梯度下降原理

    • 池化的方法，池化前传和反传的不同

  • 有关模型训练的内容

    • 优化器有哪些

    • 权重初始化方法

    • Dataset操作流程

    • 模型训练和测试的不同

      以上内容根据本人学习进度分为了三个部分进行总结

📌经典CNN模型总结笔记

已经更新的内容有：

📃 AlexNet

📄 Dropout

📄 BatchNormalization

📄 Inception_V1

📄 Inception_V2V3

📄 ResNet

📄 DenseNet

📄 CSPNet

📄 RepVGG

📄 A ConvNet for the 2020s

📄 RepLKNet

📌Transformers模型总结笔记

已经更新的内容有：

📃 Transformer

📃 Vision Transformer

📃Inductive Biases

📃 Swin-Transformer

📌轻量化模型总结笔记

📌 危险品检测总结笔记

已经更新的内容有：

📃 Few-shot X-ray Prohibited Item Detection A Benchmark and Weak-feature Enhancement Network

Delete task

Are you sure you want to delete this task? Once this task is deleted, it cannot be recovered.

cancel
confirm

版权归tyx个人所有 用途：个人学习笔记仓库 研究方向：计算机视觉-目标检测

Markdown

Contributors (1)
All

Please read the following content carefully:

Dear OpenI User

Thank you for your continuous support to the Openl Qizhi Community AI Collaboration Platform. In order to protect your usage rights and ensure network security, we updated the Openl Qizhi Community AI Collaboration Platform Usage Agreement in January 2024. The updated agreement specifies that users are prohibited from using intranet penetration tools. After you click "Agree and continue", you can continue to use our services. Thank you for your cooperation and understanding.

For more agreement content, please refer to the《Openl Qizhi Community AI Collaboration Platform Usage Agreement》

Agree and continue
Disagree, exit