Completed
0:20:25 Design Principles: Uniformity & Depth
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
VGG From Scratch - Deep Learning Theory and PyTorch Implementation
Automatically move to the next video in the Classroom when playback concludes
- 1 0:00:00 Welcome & Overview of the VGG Atlas
- 2 0:09:38 Philosophy Behind VGG: Depth with Simplicity
- 3 0:10:29 Historical Origins & Architectural Motivation
- 4 0:17:10 Mathematics of Convolution in VGG
- 5 0:20:25 Design Principles: Uniformity & Depth
- 6 0:23:22 Peer Comparison: VGG vs Contemporary Architectures
- 7 0:28:25 Training Strategy: Optimizing the VGG Model
- 8 0:42:33 Exploring Data Augmentation Techniques
- 9 0:49:56 VGG in Transfer Learning Applications
- 10 1:03:57 Visualization & Interpretability Techniques
- 11 1:14:10 VGG Variants: A Family of Deep Nets
- 12 1:16:46 Hands-on Walkthrough: Practical Applications
- 13 1:18:02 VGG Ecosystem & Research Resources
- 14 1:19:45 Kicking Off Practical Labs in Google Colab
- 15 1:21:07 Setting Up Your Coding Environment
- 16 1:23:36 Tiny VGG: Building the Model from Scratch
- 17 1:25:34 Importing Essential Libraries
- 18 1:29:54 Loading and Preparing Data in Google Colab
- 19 1:41:16 Familiarizing with Data Folders and Files
- 20 1:47:26 Setting Up the Directory Path for Data
- 21 1:47:56 Becoming One with the Data
- 22 2:02:04 Visualizing Sample Images with Metadata
- 23 2:02:44 Visualizing Images in Python Using NumPy and Matplotlib
- 24 2:09:04 Transforming the Data
- 25 2:12:54 Visualizing Transformed Data with PyTorch
- 26 2:16:34 Transforming Data with `torchvision.transforms`
- 27 2:23:40 Loading Data Using `ImageFolder`
- 28 2:53:40 Turning Loaded Images into a DataLoader
- 29 3:08:20 Visualizing Some Sample Images
- 30 3:09:42 Starting VGG Model Construction & Explaining Structure Using CNN Explainer Tool
- 31 3:20:15 Replicating the CNN Explainer Tool VGG Model in Google Colab Using Code
- 32 3:51:45 Instantiating an Instance from the VGG Model
- 33 3:56:21 Displaying and Summarizing the VGG Model
- 34 3:57:01 Dummy Forward Pass Using a Single Image
- 35 4:08:00 Using `torchinfo` to Understand Input/Output Shapes in the Model
- 36 4:10:13 Model Summary
- 37 4:20:13 Creating the Training and Testing Loop
- 38 4:41:33 Creating a Function to Combine Training and Testing Steps
- 39 4:51:29 Calling the Training Function
- 40 5:04:05 Training the Model: Running the Training Step
- 41 5:04:15 Reading the Results, Fine-Tuning, and Improving Hyperparameters
- 42 5:12:05 Plotting the Loss Curve and Fine-Tuning with Different Settings
