课程

PyTorch 深度学习进阶

中级技能水平

更新时间 2025年6月

了解用于建模图像和序列数据的基础深度学习架构，如 CNN、RNN、LSTM 和 GRU。

免费开始课程

PyTorchArtificial Intelligence

4小时

15 视频

51 道练习

4,050 XP

27,530

成就证明

深受数千家公司学习者的喜爱

需要团队培训？

企业版试用

课程描述

学习深度学习

深度学习是人工智能领域中一个快速发展的方向，它彻底改变了机器学习领域，推动了计算机视觉、自然语言处理和语音识别等领域的突破。生成式人工智能的最新进展，包括图像生成器和对话式聊天机器人，已将深度机器学习模型推到了公众视野的中心。立即开始了解深度学习的工作原理，并亲自训练深度模型。

使用 PyTorch，以最 Pythonic 的方式进行深度学习

PyTorch 是一个强大且灵活的深度学习框架，使研究人员和从业者能够轻松构建和训练神经网络。深受全球 Python 爱好者喜爱的 PyTorch，提供了极大的灵活性和直观的方式来实现深度学习概念。

训练稳健的深度学习模型

这门 PyTorch 深度学习课程旨在帮助你全面理解深度学习的基本概念和技术，并让你掌握实现各种神经网络概念的实用技能。你将掌握多输入和多输出架构。你将学习如何使用非饱和激活函数、批量归一化和合适的权重初始化来防止梯度消失和梯度爆炸问题。您将能够使用正则化和 dropout 来缓解过拟合。最后，你将了解如何通过学习率调度来加速训练过程。

构建图像和序列模型

您将了解两种专门的神经网络架构：用于图像数据的卷积神经网络（CNN）以及用于时间序列或文本等序列数据的循环神经网络（RNN）。您将了解它们的优势，并能够将其应用于图像分类和时间序列预测任务。

在课程结束时，您将具备扎实的知识和信心，能够为各种应用稳健地训练和评估您自己的深度学习模型。

先决条件

Introduction to Deep Learning with PyTorch

1

Training Robust Neural Networks

Learn how to train neural networks in a robust way. In this chapter, you will use object-oriented programming to define PyTorch datasets and models and refresh your knowledge of training and evaluating neural networks. You will also get familiar with different optimizers and, finally, get to grips with various techniques that help mitigate the problems of unstable gradients so ubiquitous in neural nets training.

PyTorch and object-oriented programming

PyTorch Dataset

PyTorch DataLoader

PyTorch Model

Optimizers, training, and evaluation

Training loop

Model evaluation

Vanishing and exploding gradients

Initialization and activation

Activations: ReLU vs. ELU

Batch Normalization

2

Images & Convolutional Neural Networks

Train neural networks to solve image classification tasks. In this chapter, you will learn how to handle image data in PyTorch and get to grips with convolutional neural networks (CNNs). You will practice training and evaluating an image classifier while learning about how to improve the model performance with data augmentation.

Handling images with PyTorch

Image dataset

Data augmentation

Data augmentation in PyTorch

Convolutional Neural Networks

The convolutional layer

Building convolutional networks

Training image classifiers

Choosing augmentations

Dataset with augmentations

Image classifier training loop

Evaluating image classifiers

Multi-class model evaluation

Analyzing metrics per class

3

Sequences & Recurrent Neural Networks

Build and train recurrent neural networks (RNNs) for processing sequential data such as time series, text, or audio. You will learn about the two most popular recurrent architectures, Long-Short Term Memory (LSTM) and Gated Recurrent Unit (GRU) networks, as well as how to prepare sequential data for model training. You will practice your skills by training and evaluating a recurrent model for predicting electricity consumption.

Handling sequences with PyTorch

Generating sequences

Sequential Dataset

Recurrent Neural Networks

Sequential architectures

Building a forecasting RNN

LSTM and GRU cells

RNN vs. LSTM vs. GRU

LSTM network

GRU network

Training and evaluating RNNs

RNN training loop

Evaluating forecasting models

4

Multi-Input & Multi-Output Architectures

Build multi-input and multi-output models, demonstrating how they can handle tasks requiring more than one input or generating multiple outputs. You will explore how to design and train these models using PyTorch and delve into the crucial topic of loss weighting in multi-output models. This involves understanding how to balance the importance of different tasks when training a model to perform multiple tasks simultaneously.

Multi-input models

Two-input dataset

Two-input model

Training two-input model

Multi-output models

Two-output Dataset and DataLoader

Two-output model architecture

Training multi-output models

Evaluation of multi-output models and loss weighting

Multi-output model evaluation

Loss weighting

PyTorch 深度学习进阶

课程完成

获得成就证明

将此证书添加到您的 LinkedIn 档案、简历或履历中
在社交媒体和绩效评估中分享立即注册

加入超过19百万学习者，今天就开始PyTorch 深度学习进阶！

通过 DataCamp for Mobile 提升您的数据技能

随时随地通过我们的移动课程和每日 5 分钟编程挑战提升技能。