Free Course Image Deep Learning With PyTorch

Free online courseDeep Learning With PyTorch

Duration of the online course: 3 hours and 39 minutes

5

StarStarStarStarStar

(4)

Build deep learning skills fast with a free PyTorch course: tensors, training, evaluation, and CNNs for image classification—plus practical Colab workflows.

In this free course, learn about

  • Set up PyTorch deep learning in Google Colab with GPU acceleration
  • Create, type, and manipulate tensors (default dtype, reshape, slice, views)
  • Apply tensor math, including in-place ops, and understand their effects
  • Build a basic feedforward neural network with linear layers and activations
  • Load datasets, choose correct feature/label dtypes for multi-class classification
  • Train models with loss, optimizer, epochs, and track performance
  • Evaluate models using torch.no_grad to disable gradients and speed inference
  • Run inference on new tabular samples (e.g., Iris) and interpret predictions
  • Save and load PyTorch models correctly (state_dict workflow)
  • Understand CNN basics: kernels/filters, RGB channels, and why CNNs suit images
  • Use pooling layers and know their role in downsampling and feature robustness
  • Prepare MNIST data: dataset sizes, transforms, and 4D tensor batch format
  • Compute CNN output shapes through conv/pool stacks and flatten for FC layers
  • Test, graph results, compute accuracy, and classify single MNIST images

Course Description

Mastering deep learning becomes much easier when you can see every step, run the code yourself, and understand what is happening under the hood. This free online course helps you build that foundation with PyTorch, one of the most widely used frameworks in AI research and production. You will move from core concepts to practical model building, gaining the confidence to turn datasets into working neural networks.

You start by getting comfortable with PyTorch tensors, the building blocks of everything you will train. Instead of treating them like a black box, you learn how data types behave, how reshaping and slicing affect memory, and how tensor math maps to model computations. Along the way, you practice writing clean operations and recognizing patterns such as in-place updates, which can be powerful but also lead to subtle bugs if misunderstood.

With the essentials in place, you will create and train a basic neural network end to end: loading data, defining a forward pass, selecting appropriate tensor types for features and labels, and improving your workflow for faster experimentation using cloud notebooks. You also learn how to properly evaluate models using the right tools to prevent unnecessary gradient tracking, so test metrics reflect real performance rather than training behavior.

The course then expands into convolutional neural networks, the standard approach for image tasks. You build intuition for kernels and filters, understand why convolutional layers are well-suited to vision, and see how pooling reduces spatial dimensions while preserving useful patterns. Using MNIST as a practical benchmark, you will prepare image tensors correctly, train and test a CNN, interpret results, and send brand-new images through the network to obtain predictions.

Finally, you will learn essential production-ready habits: saving and loading models correctly, running inference safely, and structuring a workflow you can reuse for future projects. By the end, you will have a clear path from raw data to trained models, and a practical set of PyTorch skills you can apply to classification problems in machine learning and computer vision.

Course content

  • Video class: Intro To Deep Learning With PyTorch - Deep Learning with Pytorch 1

    17m

  • Exercise: In Google Colab, which setting should you enable to speed up PyTorch model training?

  • Video class: Tensors With PyTorch - Deep Learning with PyTorch 2

    10m

  • Exercise: What is the default data type for a new PyTorch tensor?

  • Video class: Tensor Operations - Reshape and Slice - Deep Learning with PyTorch 3

    11m

  • Exercise: What happens when you modify the original tensor after creating a reshaped tensor from it in PyTorch?

  • Video class: Tensor Math Operations - Deep Learning with PyTorch 4

    12m

  • Exercise: Identify the in-place tensor addition in PyTorch

  • Video class: Create a Basic Neural Network Model - Deep Learning with PyTorch 5

    15m

  • Exercise: Which activation function is applied between the linear layers in the models forward pass?

  • Video class: Load Data and Train Neural Network Model - Deep Learning with PyTorch 6

    22m

  • Exercise: Choosing tensor dtypes for features and labels in a PyTorch multi-class classifier

  • Video class: Evaluate Test Data Set On Network - Deep Learning with PyTorch 7

    11m

  • Exercise: What is the primary purpose of torch.no_grad during model evaluation on a test set in PyTorch?

  • Video class: Evaluate NEW Data On The Network - Deep Learning with PyTorch 8

    05m

  • Exercise: How do you perform inference on a new Iris sample with a trained PyTorch model?

  • Video class: Save and Load our Neural Network Model - Deep Learning with PyTorch 9

    04m

  • Exercise: Saving and loading a PyTorch model correctly

  • Video class: Convolutional Neural Network Intro - Deep Learning with PyTorch 10

    07m

  • Exercise: For classifying digits with a CNN in PyTorch using the MNIST dataset, how many images are in the training and test sets respectively?

  • Video class: Image Filter / Image Kernel Overview - Deep Learning with PyTorch 11

    10m

  • Exercise: How does a 3x3 kernel compute an output during CNN convolution?

  • Video class: Convolutional Layer and RGB - Deep Learning with PyTorch 12

    10m

  • Exercise: Why prefer a convolutional neural network over a fully connected neural network for image tasks in PyTorch

  • Video class: Pooling Layer in Convolutional Neural Network - Deep Learning with PyTorch 13

    06m

  • Exercise: What is the main role of a pooling layer in a CNN built with PyTorch

  • Video class: Import MNIST Images - Deep Learning with PyTorch 14

    11m

  • Exercise: Why convert MNIST images to a 4D tensor before training a CNN in PyTorch?

  • Video class: Convolutional and Pooling Layers - Deep Learning with PyTorch 15

    18m

  • Exercise: After two 3x3 stride 1 conv layers without padding and two 2x2 max pools, what is the final tensor shape from a single 28x28 image formatted as 1x1x28x28?

  • Video class: Convolutional Neural Network Model - Deep Learning with PyTorch 16

    12m

  • Exercise: In the CNN defined with PyTorch, what tensor size is flattened before the first fully connected layer?

  • Video class: Train and Test CNN Model - Deep Learning with PyTorch 17

    16m

  • Exercise: Preventing gradient computation during testing in PyTorch

  • Video class: Graph CNN Results - Deep Learning with PyTorch 18

    08m

  • Exercise: Evaluate CNN test accuracy in PyTorch

  • Video class: Send New Image Thru The Model - Deep Learning with PyTorch 19

    05m

  • Exercise: How do you run a single MNIST image through a trained PyTorch CNN to get the predicted class?

This free course includes:

3 hours and 39 minutes of online video course

Digital certificate of course completion (Free)

Exercises to train your knowledge

100% free, from content to certificate

Ready to get started?Download the app and get started today.

Install the app now

to access the course
Icon representing technology and business courses

Over 5,000 free courses

Programming, English, Digital Marketing and much more! Learn whatever you want, for free.

Calendar icon with target representing study planning

Study plan with AI

Our app's Artificial Intelligence can create a study schedule for the course you choose.

Professional icon representing career and business

From zero to professional success

Improve your resume with our free Certificate and then use our Artificial Intelligence to find your dream job.

You can also use the QR Code or the links below.

QR Code - Download Cursa - Online Courses

Course comments: Deep Learning With PyTorch

SA

Sulaiman Ahmed

StarStarStarStarStar

very nice teaching

MY

Muhammad Yasir

StarStarStarStarStar

The PyTorch course was clear, practical, and well paced, helping me gain real skills in deep learning. However, I still haven’t received the certifica

More free courses at Artificial Intelligence and Machine Learning

Free Ebook + Audiobooks! Learn by listening or reading!

Download the App now to have access to + 5000 free courses, exercises, certificates and lots of content without paying anything!

  • 100% free online courses from start to finish

    Thousands of online courses in video, ebooks and audiobooks.

  • More than 60 thousand free exercises

    To test your knowledge during online courses

  • Valid free Digital Certificate with QR Code

    Generated directly from your cell phone's photo gallery and sent to your email

Cursa app on the ebook screen, the video course screen and the course exercises screen, plus the course completion certificate