课程

Deep Learning for Images with PyTorch

高级技能水平

更新时间 2025年6月

Apply PyTorch to images and use deep learning models for object detection with bounding boxes and image segmentation generation.

免费开始课程

PyTorchArtificial Intelligence4 小时16 视频58 练习4,700 经验值11,752成就声明

创建您的免费帐户

或

继续操作即表示您接受我们的《使用条款》和《隐私政策》，并同意您的数据存储在美国。

深受数千家公司学习者的喜爱

培训2人或更多？

试用DataCamp for Business

课程描述

This course on deep learning for images using PyTorch will equip you with the practical skills and knowledge to excel in image classification, object detection, segmentation, and generation.

Classify images with convolutional neural networks (CNNs)

You'll apply CNNs for binary and multi-class image classification and understand how to leverage pre-trained models in PyTorch. With bounding boxes, you'll also be able to detect objects within an image and evaluate the performance of object recognition models.

Segment images by applying masks

Explore image segmentation, including semantic, instance, and panoptic segmentation, by applying masks to images and learn about the different model architectures needed for each type of segmentation.

Generate images with GANs

Finally, you'll learn how to generate your own images using Generative Adversarial Networks (GANs). You'll learn the skills to build and train Deep Convolutional GANs (DCGANs) and how to assess the quality and diversity of generated images.By the end of this course, you'll have gained the skills and experience to work with various image tasks using PyTorch models.

先决条件

Intermediate Deep Learning with PyTorch

1

Image Classification with CNNs

Learn about image classification with CNNs, the difference between the binary and multi-class image classification models, and how to use transfer learning for image classification in PyTorch.

Binary and multi-class image classification

50 经验值

The number of classes

50 经验值

Binary classification model

100 经验值

Multi-class classification model

100 经验值

Convolutional layers for images

50 经验值

RGB, grayscale, or alpha?

50 经验值

Adding a new convolutional layer

100 经验值

Creating a sequential block

100 经验值

Working with pre-trained models

50 经验值

Save and load a model

100 经验值

Loading a pre-trained model

100 经验值

Image classification with ResNet

100 经验值

2

Object Recognition

Detect objects in images by predicting bounding boxes around them and evaluate the performance of object recognition models.

Bounding boxes

50 经验值

Object recognition

50 经验值

Image tensors

100 经验值

Drawing a bounding box

100 经验值

Evaluating object recognition models

50 经验值

Calculate IoU

50 经验值

Bounding boxes prediction

100 经验值

Calculate NMS

100 经验值

Object detection using R-CNN

50 经验值

Pre-trained model backbone

100 经验值

Classifier block

100 经验值

Box regressor block

100 经验值

Region network proposals with Faster R-CNN

50 经验值

Anchor generator

100 经验值

Faster R-CNN model

100 经验值

Define losses for RPN and R-CNN

100 经验值

3

Image Segmentation

Learn about the three types of image segmentation (semantic, instance, and panoptic), their applications, and the appropriate machine learning model architectures to perform each of them.

Introduction to image segmentation

50 经验值

Segmentation types

100 经验值

Creating binary masks

100 经验值

Segmenting image with a mask

100 经验值

Instance segmentation with Mask R-CNN

50 经验值

Segmenting with pre-trained Mask R-CNN

100 经验值

Analyzing model output

50 经验值

Displaying soft masks

100 经验值

Semantic segmentation with U-Net

50 经验值

Building a U-Net: layers definitions

100 经验值

Building a U-Net: forward method

100 经验值

Running semantic segmentation

100 经验值

Panoptic segmentation

50 经验值

Setup up semantic masks

100 经验值

Overlay instance masks

100 经验值

4

Image Generation with GANs

Generate completely new images with Generative Adversarial Networks (GANs). Learn to build and train a Deep Convolutional GAN, and how to evaluate the quality and variety of its outputs.

Introduction to GANs

50 经验值

GANs intuition

50 经验值

100 经验值

Discriminator

100 经验值

Deep Convolutional GAN

50 经验值

Convolutional Generator

100 经验值

Convolutional Discriminator

100 经验值

Training GANs

50 经验值

Generator loss

100 经验值

Discriminator loss

100 经验值

Training loop

100 经验值

Evaluating GANs

50 经验值

Generating images

100 经验值

Fréchet Inception Distance

100 经验值

50 经验值

Deep Learning for Images with PyTorch

课程完成

获得成就证明

将此证书添加到你的 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Deep Learning for Images with PyTorch！

创建您的免费帐户

或

继续操作即表示您接受我们的《使用条款》和《隐私政策》，并同意您的数据存储在美国。

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。