Project - Train a Deep Learning Model from Scratch

Deep Learning with PyTorch: Zero to GANs

Lesson 1 - PyTorch Basics and Gradient Descent Assignment 1 - All About torch.Tensor Lesson 2 - Working with Images and Logistic Regression Assignment 2 - Train Your First Model Lesson 3 - Training Deep Neural Networks on a GPU Assignment 3 - Feed Forward Neural Networks Lesson 4 - Image Classification with Convolutional Neural Networks Lesson 5 - Data Augmentation, Regularization & ResNets Lesson 6: Generative Adversarial Networks and Transfer Learning

← Back

For the course project, you will pick a dataset of your choice and apply the concepts learned in this course to train deep learning models end-to-end with PyTorch, experimenting with different hyperparameters & metrics.

Find a large dataset (2000+ samples) online (see "Where to Find Datasets" below)
Understand and describe the modeling objective clearly
1. What type of data is it? (images, text, audio, etc.)
2. What type of problem is it? (regression, classification, generative modeling, etc.)
Clean the data if required and perform exploratory analysis (plot graphs, ask questions)
Modeling
1. Define a model (network architecture)
2. Pick some hyperparameters
3. Train the model
4. Make predictions on samples
5. Evaluate on the test dataset
6. Save the model weights
7. Try different hyperparameters & regularization
Conclusions - summarize your learning & identify opportunities for future work
Publish and submit your Jupyter notebook
(Optional) Write a blog post to describe your experiments and summarize your work. Use Medium or Github pages.

NOTE: There is no starter notebook for the course project. Please create a new notebook on Google Colab, make it public, and submit the link to it at the bottom of this page.

Use the following sources to find interesting datasets: