This course is designed for beginners with little no experience in Deep learning or PyTorch.

What you will learn

Train Convolutional Neural Networks.

How to apply data transformations using the torchvision library.

How to efficiently store and load data samples on PyTorch.

How to leverage GPU acceleration to train neural networks efficiently

Overall the student will build a solid foundation in the fundamental concepts and techniques required to train neural networks effectively


Hands-On Deep Learning with PyTorch: A Beginner’s Course:

Whether you’re new to neural networks or looking to expand your skills, this course will provide you with a hands-on approach to training neural networks from scratch.

Our comprehensive curriculum covers all the essential components of deep learning, including Neural Networks, Loss Functions, Optimizers, Datasets, and DataLoaders. You’ll also learn how to leverage the GPU for accelerated training and gain practical insights into building and training basic neural networks using PyTorch.

What sets this course apart is it’s accessibility. You don’t need any previous knowledge of neural networks or PyTorch. All you need is a basic understanding of Python, and we’ll guide you through the rest.

Get Instant Notification of New Courses on our Telegram channel.

By the end of the course, you’ll have gained the skills to confidently train basic neural networks using PyTorch. Unlock your potential in deep learning and embark on this exciting journey today. Enroll now and start building your expertise in the world of artificial intelligence.

Content of the Course:

  • Datasets
  • Data Loaders.
  • Image Augmentation
  • Loss Functions
  • Optimizers.
  • Activation Functions.
  • Normalization Techniques.
  • Convolutional Neural Networks (CNN).
  • Training Neural Networks.
  • GPU Acceleration.


  • The only requirement is basic knowledge of Python.
  • No experience on Deep learning required.
  • No experience on PyTorch required.




Theory: Data Formats.

Float Tensor
Long Tensor
Bool Tensor
No_grad Context Manager
torchvision: Compose Object (Theory)
torchvision: Compose Object (Example)

Theory: Datasets and DataLoaders.

PyTorch Dataset (Theory)
PyTorch Dataset (Example)
PyTorch DataLoader (Theory)
PyTorch DataLoader (Example)

Theory: Model components.

Linear Layer
Convolutional Operation (Theory)
Convolutional Operation (Example)
Activation Functions
Softmax Normalization Function
Argmax Function
How to create a CNN.
Neural Network Evaluation Mode

Theory: CUDA

What’s CUDA
CUDA Example.

Theory: Optimization Components.

What’s a Loss Function
Cross Entropy Loss (Theory)
Cross Entropy Loss (Example)
What’s an Optimizer
What’s a Learning Rate
How to initiate Adam (Example)

Theory: How to Train a Neural Network.

How to Train a Neural Network (Example)

Practice: Training a CNN

Gather Data.
Build Dataset
Build the Neural Network
Training the Neural Network

Farewell and Assignment.