// the find
ageron/tf2_course
Notebooks for my "Deep Learning with TensorFlow 2 and Keras" course
Six Jupyter notebooks covering TensorFlow 2 and Keras from basic neural nets through CNNs and RNNs, written by Aurélien Géron (author of Hands-on ML). It's a companion to a paid training course, not a standalone textbook — so expect gaps if you weren't in the room.
Géron knows this material cold; the notebooks reflect the same clarity and practical focus as his O'Reilly book. Colab links work out of the box, so there's zero setup friction for someone who just wants to run code. The low-level TF2 API notebook is genuinely useful — most tutorials skip straight to Keras and leave you helpless when you need to step outside it. The data loading and preprocessing notebook covers tf.data properly, which most tutorials treat as an afterthought.
Last commit was May 2023 and the FAQ recommends Python 3.7, which is end-of-life — the environment.yml is stale and you'll likely hit dependency conflicts. Only six notebooks means significant topics (transformers, custom training loops at scale, TFX) are either missing or thin. It's a course companion, not a self-contained resource, so some notebooks assume context from lectures that aren't here. No tests or CI, so there's no guarantee anything still runs against current TF versions.