Deep Learning
A 22-part video course by Patrick Loeber that takes you from installing PyTorch to building, training, and deploying neural networks.
Learn from: the original creator. Original content published on YouTube. DigitalSkillX organizes these public resources into a structured learning path. DigitalSkillX does not claim ownership or partnership.
Now playing: PyTorch Tutorial 01 - Installation
This learning path follows Patrick Loeber's PyTorch tutorial series in order. It starts with installation and tensor basics, moves through autograd, backpropagation, and training pipelines, then covers regression, datasets, activation functions, and neural network architectures including CNNs and RNNs. Later lessons cover practical tools like TensorBoard, model saving, and deployment, plus extras on PyTorch Lightning and learning rate schedulers. The videos are hands-on and code-focused, so it helps to follow along in your own environment. Some lessons are long, so plan for a few sessions rather than one sitting.
Beginners who want a structured free introduction before deeper practice.
Lesson 1: PyTorch Tutorial 01 - Installation
Patrick Loeber shows how he installs PyTorch. The lesson covers the installation process so you can get a working setup before writing any code.
Open on YouTubeLesson 2: PyTorch Tutorial 02 - Tensor Basics
This lesson introduces tensors, the core data structure in PyTorch. It covers basic tensor creation and common tensor operations.
Open on YouTubeLesson 3: PyTorch Tutorial 03 - Gradient Calculation With Autograd
The lesson explains how to calculate gradients using PyTorch's autograd system. It shows how automatic differentiation works in practice.
Open on YouTubeLesson 4: PyTorch Tutorial 04 - Backpropagation - Theory With Example
A theory-focused lesson on backpropagation with a worked example. It explains the idea behind the algorithm before you implement it in code.
Open on YouTubeLesson 5: PyTorch Tutorial 05 - Gradient Descent with Autograd and Backpropagation
This lesson combines autograd and backpropagation to implement gradient descent. It shows how the pieces fit together in a training loop.
Open on YouTubeLesson 6: PyTorch Tutorial 06 - Training Pipeline: Model, Loss, and Optimizer
The lesson builds a general training pipeline with a model, loss function, and optimizer. It improves on the code from the previous lesson.
Open on YouTubeLesson 7: PyTorch Tutorial 07 - Linear Regression
This lesson implements linear regression in PyTorch. It applies the training pipeline to a simple regression problem.
Open on YouTubeLesson 8: PyTorch Tutorial 08 - Logistic Regression
The lesson implements logistic regression for classification. It covers the changes needed to move from regression to classification.
Open on YouTubeLesson 9: PyTorch Tutorial 09 - Dataset and DataLoader - Batch Training
This lesson introduces the built-in Dataset and DataLoader classes. It shows how to use them for batch training.
Open on YouTubeLesson 10: PyTorch Tutorial 10 - Dataset Transforms
The lesson covers dataset transforms in PyTorch. It shows how to apply transformations to data before it reaches the model.
Open on YouTubeLesson 11: PyTorch Tutorial 11 - Softmax and Cross Entropy
This lesson explains the softmax function and cross entropy loss. It covers why they are used together for classification tasks.
Open on YouTubeLesson 12: PyTorch Tutorial 12 - Activation Functions
The lesson covers activation functions used in neural networks. It explains common choices and where they are applied.
Open on YouTubeLesson 13: PyTorch Tutorial 13 - Feed-Forward Neural Network
This lesson implements a first multilayer neural network. It brings together the earlier building blocks into a feed-forward model.
Open on YouTubeLesson 14: PyTorch Tutorial 14 - Convolutional Neural Network (CNN)
The lesson implements a convolutional neural network. It covers the layers and structure used for image data.
Open on YouTubeLesson 15: PyTorch Tutorial 15 - Transfer Learning
This lesson introduces transfer learning. It shows how to reuse a pretrained model for a new task.
Open on YouTubeLesson 16: PyTorch RNN Tutorial - Name Classification Using A Recurrent Neural Net
This lesson implements a recurrent neural network from scratch. It briefly covers RNN theory and then builds a name classification model.
Open on YouTubeLesson 17: PyTorch Tutorial - RNN & LSTM & GRU - Recurrent Neural Nets
The lesson covers the nn.RNN module and how to work with input sequences. It also shows how to switch to GRU or LSTM layers.
Open on YouTubeLesson 18: PyTorch Tutorial 16 - How To Use The TensorBoard
The lesson shows how to use TensorBoard with PyTorch. It covers logging training runs and viewing them in the TensorBoard interface.
Open on YouTubeLesson 19: PyTorch Tutorial 17 - Saving and Loading Models
This lesson covers saving and loading models in PyTorch. It explains the options and when to use each one.
Open on YouTubeLesson 20: Create & Deploy A Deep Learning App - PyTorch Model Deployment With Flask & Heroku
A longer project lesson on deploying a PyTorch model. It builds a Flask app with a REST API and deploys it to Heroku.
Open on YouTubeLesson 21: PyTorch Lightning Tutorial - Lightweight PyTorch Wrapper For ML Researchers
This lesson introduces PyTorch Lightning, a wrapper that reduces boilerplate code. It shows how to convert existing PyTorch code to Lightning.
Open on YouTubeLesson 22: PyTorch LR Scheduler - Adjust The Learning Rate For Better Results
The lesson covers learning rate schedulers in PyTorch. It shows how adjusting the learning rate during training can improve results.
Open on YouTube0 of 22 lessons completed (0%).
Complete this learning path to become eligible for your DigitalSkillX certificate.