Building a Vision Transformer Model from Scratch with PyTorch

Building a Vision Transformer Model from Scratch with PyTorch

freeCodeCamp.org via freeCodeCamp Direct link

⌨️ 2:27:08 Visualizing Fine-Tuned Accuracy

15 of 16

15 of 16

⌨️ 2:27:08 Visualizing Fine-Tuned Accuracy

Class Central Classrooms beta

YouTube videos curated by Class Central.

Classroom Contents

Building a Vision Transformer Model from Scratch with PyTorch

Automatically move to the next video in the Classroom when playback concludes

  1. 1 ⌨️ 0:00:00 Intro
  2. 2 ⌨️ 0:28:23 Theoretical Explanation of Vision Transformers
  3. 3 ⌨️ 0:47:40 Environment Setup and Library Imports
  4. 4 ⌨️ 0:55:14 Configurations and Hyperparameter Setup
  5. 5 ⌨️ 0:58:28 Image Transformation Operations
  6. 6 ⌨️ 1:00:28 Downloading the CIFAR-10 Dataset
  7. 7 ⌨️ 1:04:22 Creating DataLoaders
  8. 8 ⌨️ 1:11:32 Building the Vision Transformer ViT Model
  9. 9 ⌨️ 1:43:41 Defining Loss Function and Optimizer
  10. 10 ⌨️ 1:45:37 Training Loop and Model Training
  11. 11 ⌨️ 2:03:18 Visualizing Accuracy Training vs Testing
  12. 12 ⌨️ 2:06:08 Making and Visualizing Predictions
  13. 13 ⌨️ 2:18:48 Fine-Tuning with Data Augmentation
  14. 14 ⌨️ 2:25:08 Training the Fine-Tuned Model
  15. 15 ⌨️ 2:27:08 Visualizing Fine-Tuned Accuracy
  16. 16 ⌨️ 2:28:38 Predictions After Fine-Tuning

Never Stop Learning.

Get personalized course recommendations, track subjects and courses with reminders, and more.

Someone learning on their laptop while sitting on the floor.