Applied Deep Learning with PyTorch

Go to main | Course Page

Section 1: Introduction to PyTorch

  1. Tensors
  2. Dataset Class and Dataloader
  3. Autograd
  4. Optimizer
  5. Model Class
  6. Saving Models

Section 2: Setup and Helper Functions for PyTorch (Code Demo)

  1. Setup Environment
  2. Data for Clasification and Regression
  3. Helper Class for DataLoader
  4. Helper Functions for Classification and Regression

Section 3: Logistic Regression in PyTorch (Code Demo)

  1. Initialize Dataloader
  2. Define Model architecture and Initialize
  3. Loss and Optimizer
  4. Model Training
  5. Model Evaluation
  6. Save Model

Section 4: 2-Layer Neural Network for Classification in PyTorch (Code Demo)

  1. Initialize Dataloader
  2. Define Model architecture and initialize
  3. Loss and Optimizer and model training

Section 5: 5-Layer Neural Network for Regression (Week 1 Assignment) in PyTorch (Code Demo)

  1. Initialize Dataloader
  2. Define Model architecture and initialize
  3. Loss and Optimizer
  4. Model Training
  5. Model Evaluation and save the model

Section 6: Regularization

  1. Introduction to Regularization
  2. L1 and L2 Regularization
  3. Why Regularization Works
  4. Dropout Regularization
  5. Inverted Dropout
  6. Early Stopping

Section 7: Regularization in PyTorch (Code Demo)

  1. Batch Normalization
  2. Regularization - Dropout
  3. L1 Regularization
  4. L2 Regularization
  5. ElasticNet Regularization
  6. Regularization - Early Stopping

Section 8: Optimization

  1. Stochastic Gradient Descent
  2. Stochastic Gradient Descent With Momentum
  3. Adaptive Gradient Algorithm (AdaGrad)
  4. Root Mean Squared Propagation (RMSProp)
  5. Adaptive Moment Estimation (Adam)
  6. How to Choose - Checklist

Section 9: Optimization in PyTorch (Code Demo)

  1. Code Implemendation of Optimization
Report abuse