Skip to content

快速开始

本指南将帮助你快速上手 AI-Practices 项目。

前置要求

组件最低要求推荐配置
Python3.103.10 ~ 3.11
CPU4 核心8+ 核心
RAM8 GB32 GB
GPUGTX 1060RTX 3080+
存储50 GB200 GB SSD

安装步骤

1. 克隆仓库

bash
git clone https://github.com/zimingttkx/AI-Practices.git
cd AI-Practices

2. 创建环境

bash
conda create -n ai-practices python=3.10 -y
conda activate ai-practices

3. 安装依赖

bash
pip install -r requirements.txt

4. 验证安装

bash
python -c "import tensorflow as tf; print(f'TensorFlow: {tf.__version__}')"
python -c "import torch; print(f'PyTorch: {torch.__version__}')"

5. 启动 Jupyter

bash
jupyter lab

运行第一个实验

bash
cd 09-practical-projects/02-computer-vision/01-mnist-cnn
python src/train.py --epochs 20 --batch_size 64

预期输出:

Epoch 20/20 - loss: 0.0234 - accuracy: 0.9921
Test Accuracy: 99.12%

学习路径

初学者 (8-12 周)

Week 1-2:  01-foundations (Part 1)
Week 3-4:  01-foundations (Part 2)
Week 5-6:  02-neural-networks
Week 7-8:  03-computer-vision
Week 9-10: 04-sequence-models
Week 11-12: 09-practical-projects

进阶 (4-6 周)

Week 1-2: 05-advanced-topics
Week 3-4: 06-generative-models
Week 5-6: 07-reinforcement-learning

下一步

Released under the MIT License.