Objective: Learn how to implement state-of-the-art neural networks for object detection and other relevant tasks
Note: For all .ipynb files, open the notebook in Google Colaboratory instead of GitHub’s viewer.
Lesson 1: Machine Learning Fundamentals
- Implement and play with the code from an introduction to machine learning with scikit-learn and HackerEarth's practical tutorial on data manipulation with Numpy and Pandas in Python
Lesson 2: Neural Networks in PyTorch
- Read and complete the exercises in Lesson_Two.ipynb. A PDF version is also provided for convenience.
Lesson 3: Segmentation Models and Catalyst
- Study Lesson_Three.ipynb. Once again, there is also a PDF version.
Lesson 4: Further Studies (Optional)
- Courses on Deep Learning: Fast.ai; Google's ML Crash Course; Udacity
- Books: Grokking Deep Learning; Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow
- Useful Blogs: CodeBug88; Chris Albon
- Framework Tutorials: PyTorch; Catalyst; PyTorch Lightning
- Lectures and Papers: UCL x DeepMind: Deep Learning Lecture Series; Roadmap of Research Papers
- Other: Twitter Thread on Advanced Resources