# Data Science Tensorflow Handbook

> Use when working with TensorFlow — deep learning, Keras, neural networks, ML models

- Skill: `liaosw97/data-science-tensorflow-handbook` (Agent Skill, multi-file: 2 files)
- Install (CLI): `npx skillmds@latest add liaosw97/data-science-tensorflow-handbook`
- Raw SKILL.md: https://api.skillmd.com/api/skills/liaosw97/data-science-tensorflow-handbook/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Coding & Dev Tools
- Author: liaosw97 (https://skillmd.com/u/liaosw97)
- Updated: 2026-09-22
- Page: https://skillmd.com/skills/liaosw97/data-science-tensorflow-handbook

---


# TensorFlow 实践手册

## Keras API

### 序列模型定义
```python
from tensorflow.keras import Sequential
from tensorflow.keras.layers import Dense

model = Sequential([
    Dense(64, activation='relu', input_shape=(784,)),
    Dense(64, activation='relu'),
    Dense(10, activation='softmax')
])

model.compile(
    optimizer='adam',
    loss='sparse_categorical_crossentropy',
    metrics=['accuracy']
)
```

## 分布式训练

### 多GPU训练配置
```python
strategy = tf.distribute.MirroredStrategy()

with strategy.scope():
    model = create_model()
    model.compile(loss='sparse_categorical_crossentropy',
                 optimizer='adam',
                 metrics=['accuracy'])

model.fit(train_dataset, epochs=10)
```