Deep Learning for Images with PyTorch
Apply PyTorch to images and use deep learning models for object detection with bounding boxes and image segmentation generation.
Start Course for Free4 hours16 videos58 exercises4,262 learnersStatement of Accomplishment
Create Your Free Account
or
By continuing, you accept our Terms of Use, our Privacy Policy and that your data is stored in the USA.Training 2 or more people?
Try DataCamp for BusinessLoved by learners at thousands of companies
Course Description
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.Training 2 or more people?
Get your team access to the full DataCamp platform, including all the features.In the following Tracks
Deep Learning in Python
Go To Track- 1
Image classification with CNNs
FreeLearn 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 classification50 xpThe number of classes50 xpBinary classification model100 xpMulti-class classification model100 xpConvolutional layers for images50 xpRGB, grayscale, or alpha?50 xpAdding a new convolutional layer100 xpCreating a sequential block100 xpWorking with pre-trained models50 xpSave and load a model100 xpLoading a pre-trained model100 xpImage classification with ResNet100 xp - 2
Object recognition
Detect objects in images by predicting bounding boxes around them and evaluate the performance of object recognition models.
Bounding boxes50 xpObject recognition50 xpImage tensors100 xpDrawing a bounding box100 xpEvaluating object recognition models50 xpCalculate IoU50 xpBounding boxes prediction100 xpCalculate NMS100 xpObject detection using R-CNN50 xpPre-trained model backbone100 xpClassifier block100 xpBox regressor block100 xpRegion network proposals with Faster R-CNN50 xpAnchor generator100 xpFaster R-CNN model100 xpDefine losses for RPN and R-CNN100 xp - 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 segmentation50 xpSegmentation types100 xpCreating binary masks100 xpSegmenting image with a mask100 xpInstance segmentation with Mask R-CNN50 xpSegmenting with pre-trained Mask R-CNN100 xpAnalyzing model output50 xpDisplaying soft masks100 xpSemantic segmentation with U-Net50 xpBuilding a U-Net: layers definitions100 xpBuilding a U-Net: forward method100 xpRunning semantic segmentation100 xpPanoptic segmentation50 xpSetup up semantic masks100 xpOverlay instance masks100 xp - 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 GANs50 xpGANs intuition50 xpGenerator100 xpDiscriminator100 xpDeep Convolutional GAN50 xpConvolutional Generator100 xpConvolutional Discriminator100 xpTraining GANs50 xpGenerator loss100 xpDiscriminator loss100 xpTraining loop100 xpEvaluating GANs50 xpGenerating images100 xpFréchet Inception Distance100 xpWrap-up50 xp
Training 2 or more people?
Get your team access to the full DataCamp platform, including all the features.In the following Tracks
Deep Learning in Python
Go To Trackcollaborators
audio recorded by
prerequisites
Intermediate Deep Learning with PyTorch
Michał OleszakMachine Learning Engineer
Michał is a Machine Learning Engineering Manager based in Zurich, Switzerland. He has a background in statistics and econometrics, holding an MSc degree from Erasmus University Rotterdam, The Netherlands. He has worn many hats, having worked at a consultancy, a start-up, a software house, and a large corporation. He blogs about anything machine learning. Visit his website to find out more.
What do other learners have to say?
Join over 15 million learners and start Deep Learning for Images with PyTorch today!
Create Your Free Account
or
By continuing, you accept our Terms of Use, our Privacy Policy and that your data is stored in the USA.