Getting-Things-Done-with-PyTorch 项目教程

Getting-Things-Done-with-PyTorch 项目教程

Getting-Things-Done-with-PytorchJupyter Notebook tutorials on solving real-world problems with Machine Learning & Deep Learning using PyTorch. Topics: Face detection with Detectron 2, Time Series anomaly detection with LSTM Autoencoders, Object Detection with YOLO v5, Build your first Neural Network, Time Series forecasting for Coronavirus daily cases, Sentiment Analysis with BERT.项目地址:https://gitcode.com/gh_mirrors/ge/Getting-Things-Done-with-Pytorch

1. 项目的目录结构及介绍

Getting-Things-Done-with-Pytorch/
├── LICENSE
├── README.md
├── book-cover.png
├── object-detection-with-YOLO-v5.ipynb
├── multi-label-text-classification-with-bert.ipynb
├── 3D_photo_inpainting.ipynb
└── ...

• LICENSE: 项目许可证文件。
• README.md: 项目介绍和使用说明。
• book-cover.png: 书籍封面图片。
• object-detection-with-YOLO-v5.ipynb: YOLO v5 目标检测教程。
• multi-label-text-classification-with-bert.ipynb: BERT 多标签文本分类教程。
• 3D_photo_inpainting.ipynb: 3D 照片修复教程。

2. 项目的启动文件介绍

项目的启动文件主要是 Jupyter Notebook 文件，每个文件对应一个具体的教程。以下是一些关键的启动文件：

• object-detection-with-YOLO-v5.ipynb: 该文件包含了使用 YOLO v5 进行目标检测的详细步骤和代码示例。
• multi-label-text-classification-with-bert.ipynb: 该文件包含了使用 BERT 进行多标签文本分类的详细步骤和代码示例。
• 3D_photo_inpainting.ipynb: 该文件包含了使用深度学习技术进行 3D 照片修复的详细步骤和代码示例。

3. 项目的配置文件介绍

项目中没有明确的配置文件，所有的配置和参数设置都在 Jupyter Notebook 文件中进行。每个 Notebook 文件都包含了所需的依赖库、模型参数和训练设置。

例如，在 object-detection-with-YOLO-v5.ipynb 中，你可以找到如下配置代码：

# 导入必要的库
import torch
import cv2
from models.experimental import attempt_load
from utils.general import non_max_suppression

# 加载模型
model = attempt_load('yolov5s.pt', map_location=torch.device('cpu'))

# 设置参数
conf_thres = 0.25
iou_thres = 0.45

这些代码片段展示了如何导入库、加载模型以及设置检测阈值。

Getting-Things-Done-with-PytorchJupyter Notebook tutorials on solving real-world problems with Machine Learning & Deep Learning using PyTorch. Topics: Face detection with Detectron 2, Time Series anomaly detection with LSTM Autoencoders, Object Detection with YOLO v5, Build your first Neural Network, Time Series forecasting for Coronavirus daily cases, Sentiment Analysis with BERT.项目地址:https://gitcode.com/gh_mirrors/ge/Getting-Things-Done-with-Pytorch