- This tutorial is to organize and summarize the research content of my postgraduate period. At the same time, I hope to help more friends. If there is any new knowledge learned later, I will share it with you.。
- This tutorial will be shared in the form of video, the teaching process is as follows:
1)Introduce the structure and innovation of the network
2)Use Pytorch for network construction and training
3)3) Use Tensorflow (internal keras module) to build and train the network
- All PPTs in the course are placed in the
course_ppt
folder, and you need to download them yourself。
Tutorial directory, click to jump to the corresponding video (it will be added later according to the learning content)
-
Image Classification
-
LeNet(COMPLETED)
-
AlexNet(已完成)
-
VggNet(已完成)
-
GoogLeNet(已完成)
-
ResNet(已完成)
-
ResNeXt (已完成)
-
MobileNet_v1_v2(已完成)
-
MobileNet_v3(已完成)
-
ShuffleNet_v1_v2 (已完成)
-
EfficientNet_v1(已完成)
-
EfficientNet_v2 (已完成)
-
Vision Transformer(已完成)
-
Swin Transformer(已完成)
-
ConvNeXt(准备中)
- ConvNeXt网络讲解
- 使用Pytorch搭建ConvNeXt
-
-
目标检测
-
Faster-RCNN/FPN(已完成)
-
SSD/RetinaNet (已完成)
-
YOLOv3 SPP (已完成)
-
-
语义分割
-
FCN (已完成)
-
DeepLabV3 (已完成)
-
LR-ASPP (已完成)
-
U-Net (已完成)
-
- Anaconda3(建议使用)
- python3.6/3.7/3.8
- pycharm (IDE)
- pytorch 1.7.1 (pip package)
- torchvision 0.8.1 (pip package)
- tensorflow 2.4.1 (pip package)
欢迎大家关注下我的微信公众号(阿喆学习小记),平时会总结些相关学习博文。
如果有什么问题,也可以到我的CSDN中一起讨论。 https://blog.csdn.net/qq_37541097/article/details/103482003
我的bilibili频道: https://space.bilibili.com/18161609/channel/index