Project-Based Deep Learning Resources

Question

Hey all,I found Replit's 100 Days of Code for Python, Andrej Karpathy's Zero to Hero, and Umar Jamil's coding transformers from scratch to be engaging resources because they were hands-on projects.I am looking for a resource that can provide a practical basis to the theoretical Deep Learning by Goodfellow et al. I stress that the resource should be project-based, as I learn best by creating.Do you have any recommendations?Thank you!

strangecasts · Accepted Answer

Keras' code examples - https://keras.io/examples/ - tend to be structured divided into dataset-preprocessing-training, and tend to start with a somewhat underparameterized model to show off the method quickly, rather than attaining the best performance. Keras 3 is also set up to be backend-independent, so you should be able to borrow the examples' preprocessing regardless of whether you're using PyTorch, TensorFlow or Jax.In particular, the monocular depth estimation example seems like a good start: https://keras.io/examples/vision/depth_estimation/