Deep Learning with PyTorch: Zero to GANs
"Deep Learning with PyTorch: Zero to GANs" is a beginner-friendly online course offering a practical and coding-focused introduction to deep learning using the PyTorch framework. Enroll now to start learning.
- Watch live hands-on tutorials on YouTube
- Train models on cloud Jupyter notebooks
- Build an end-to-end real-world course project
- Earn a verified certificate of accomplishment
The course is self-paced and there are no deadlines. There are no prerequisites for this course.
Subscribe to Jovian PRO to get dedicated support from the course team. Read the course FAQs or visit the community discussion forum to learn more.
Lesson 1 - PyTorch Basics and Gradient Descent
- PyTorch basics: tensors, gradients, and autograd
- Linear regression & gradient descent from scratch
- Using PyTorch modules: nn.Linear & nn.functional
Assignment 1 - All About torch.Tensor
- Explore the PyTorch documentation website
- Demonstrate usage of some tensor operations
- Publish your Jupyter notebook & share your work
Lesson 2 - Working with Images and Logistic Regression
- Training-validation split on the MNIST dataset
- Logistic regression, softmax & cross-entropy
- Model training, evaluation & sample predictions
Assignment 2 - Train Your First Model
- Download and explore a real-world dataset
- Create a linear regression model using PyTorch
- Train multiple models and make predictions
Lesson 3 - Training Deep Neural Networks on a GPU
- Multilayer neural networks using nn.Module
- Activation functions, non-linearity & backprop
- Training models faster using cloud GPUs
Assignment 3 - Feed Forward Neural Networks
- Explore the CIFAR10 image dataset
- Create a pipeline for training on GPUs
- Hyperparameter tuning & optimization
Lesson 4 - Image Classification with Convolutional Neural Networks
- Working with 3-channel RGB images
- Convolutions, kernels & features maps
- Training curve, underfitting & overfitting
Lesson 5 - Data Augmentation, Regularization & ResNets
- Adding residual layers with batchnorm to CNNs
- Learning rate annealing, weight decay & more
- Training a state-of-the-art model in 5 minutes
Lesson 6: Generative Adversarial Networks and Transfer Learning
- Generating fake digits & anime faces with GANs
- Training generator and discriminator networks
- Transfer learning for image classification
Course Project - Train a Deep Learning Model from Scratch
- Discover & explore a large real-world dataset
- Train a convolutional neural network from scratch
- Document, present, and publish your work online
Certificate of Accomplishment
Earn a verified certificate of accomplishment (sample) for FREE by completing all weekly assignments and the course project. The certificate can be added to your LinkedIn profile, linked from your Resume, and downloaded as a PDF.
Course Prerequisites
- Programming basics (functions & loops)
- Linear algebra basics (vectors & matrices)
- Calculus basics (derivatives & slopes)
- No prior knowledge of deep learning required
Instructor - Aakash N S
Aakash N S is the co-founder and CEO of Jovian. Previously, Aakash has worked as a software engineer (APIs & Data Platforms) at Twitter in Ireland & San Francisco and graduated from the Indian Institute of Technology, Bombay. He’s also an avid blogger, open-source contributor, and online educator.
Jovian PRO
Get access to a private Slack group with the course team, attend weekly office hours on Zoom, and get 1-on-1 guidance for your project by joining the Jovian PRO Program. This is a limited and paid program designed to help you get the most out of this course. Apply here: https://jovian.ai/pro.
