EVA (Extensive Vision AI Program) - Phase I

Probably the most exhaustive and updated Deep Vision Program in the world! It is spread over three semester-style phases, each restricted by a qualifying exam from https://theschoolof.ai/

Course Topics (Updated in 2021):

1. Background & Basics: Machine Learning Intuition
2. Python: Python 101 for Machine Learning
3. DNN Concepts: Convolutions, Pooling Operations & Channels
4. PyTorch: PyTorch 101 for Vision Machine Learning
5. First Neural Network: Kernels, Activations, and Layers
6. Architectural Basics: We go through 9 model iterations together, step-by-step to find the final architecture
7. BN, Kernels & Regularization: Mathematics behind Batch Normalization, Kernel Initialization, and Regularization
8. Advance Convolutions, Attention and Image Augmentation: Depthwise, Pixel Shuffle, Dilated, Transpose, Channel Attention and Albumentations Library
9. Advanced Training Concepts: Class Activation Maps, Optimizers, LR Schedules, LR Finder & One Cycle Policy
10. ResNets: Training ResNet for TinyImageNet from scratch
11. Object Detection YoloV2/V3/V4: Understanding YOLO Loss Function & Training Yolo
12. The Dawn Of Transformers: Convolutions, Transformers and Types of Attention (Soft, Spatial, Channel, Self and Multi-head)
13. Hands-On: Transformers and Attention Mechanism
14. Hands-On: Vision Transformers (ViT)
15. Modern Object Detection: End-To-End Object Detection with Transformers
16. CapStone: Qualifying Project for Phase 2