Module 1: PyTorch Basics and Linear Regression
- Introduction to Jupyter notebooks & Data Science in Python
- Creating vectors, matrices & Tensors in PyTorch
- Tensor operations and gradient computations
- Interoperability of PyTorch with Numpy
- Linear Regression from scratch using Tensor operations
- Weights, biases and the mean squared error loss function
- Gradient descent and model training with PyTorch Autograd
- Linear Regression using PyTorch built-ins (nn.Linear, nn.functional etc.)
PART 1 (A): PyTorch Basics: Tensors & Gradients
PART 1 (B): Linear Regression & Gradient Descent
**Extras: Pytorch Tensor 101
Mini Project:
Insurance cost prediction using linear regression
Housing price prediction using linear regression
Module 2: Working with Images and Logistic Regression
- Working with images from the MNIST dataset
- Training and validation dataset creation
- Softmax function and categorical cross entropy loss
- Model training, evaluation and sample predictions
PART 2: Image Classfication using Logistic Regression
Mini Project: MNIST Classification using linear regression
Module 3: Training Deep Neural Networks on a GPU
- Working with cloud GPU platforms like Kaggle & Colab
- Creating a multilayer neural network using nn.Module
- Activation function, non-linearity and universal approximation theorem
- Moving with datasets and models to the GPU for faster training
PART 3: Training Deep Neural Networks on a GPU
Module 4: Image Classification with Convolutional Neural Networks
- Working with the 3-channel RGB images from the CIFAR10 dataset
- Introduction to Convolutions, kernels & features maps
- Underfitting, overfitting and techniques to improve model performance
PART 4: Image Classification using Convolutional Neural Networks
Module 5: Data Augmentation, Regularization and ResNets
- Improving the dataset using data normalization and data augmentation
- Improving the model using residual connections and batch normalization
- Improving the training loop using learning rate annealing, weight decay and gradient clip
- Training a state of the art image classifier from scratch in 10 minutes
PART 5: Data Augmentation, Regularization and ResNets
Module 6: Image Generation using Generative Adversarial Networks (GANs)
- Introduction to generative modeling and application of GANs
- Creating generator and discriminator neural networks
- Generating and evaluating fake images of handwritten digits
- Training the generator and discriminator in tandem and visualizing results
PART 6: Generating Images using Generative Adverserial Networks
Final Kaggle Project Human Protein Multi-label Classification