TensorFlow

An end-to-end machine learning platform.

TensorFlow is taught here in 12 lessons, running from Tensors and eager execution through to Debugging, profiling and export formats. Each lesson takes one topic, shows the working code, and links onward to the next, so the course can be read straight through in order.

Lessons

1. Tensors and eager executionImmutable constants, trainable variables, shape and dtype rules, and how tf.function turns Python into a traced graph.
2. Building a Keras modelSequential and functional APIs, matching the output layer and loss to the task, and the from_logits setting that silently costs you accuracy.
3. Training, saving and servingmodel.fit with callbacks, a custom GradientTape loop, the tf.data pipeline, and exporting a model whose preprocessing travels with it.
4. Layers, activations and custom modelsDense, convolution, embedding and recurrent layers, choosing activations deliberately, and writing your own layer and model by subclassing.
5. The tf.data pipeline in depthBuild input pipelines that keep the GPU fed: map, batch, shuffle, cache, prefetch, and how to prove the bottleneck is the input rather than the model.
6. Regularisation and normalisationDropout, weight penalties, batch versus layer normalisation, augmentation, and early stopping — what each one actually does to the training signal.
7. Hyperparameter tuning with KerasTunerDefine a search space, run RandomSearch or Hyperband, persist results, and compare trials honestly instead of chasing the best-looking number.
8. Transfer learning and fine-tuningLoad a pretrained backbone, freeze and unfreeze it in the right order, match the preprocessing exactly, and know when fine-tuning is worth the cost.
9. Text and image preprocessing layersKeras preprocessing layers, TextVectorization and StringLookup, and building resizing and augmentation into the model so training and serving agree.
10. TensorBoard and experiment trackingScalars, graphs, histograms, image summaries and the embedding projector, plus comparing runs so that a change you made is the change that mattered.
11. Mixed precision and multi-device trainingMixed precision policy and loss scaling, distribution strategies, how batch size scales across devices, and checkpointing a run that can be resumed.
12. Debugging, profiling and export formatsShape and dtype errors, NaN losses, the tf.debugging toolkit, the profiler, and exporting to TF Lite, TF.js and TF Serving from one model.

More in AI & Intelligent Development

AI Basics AI Agents Math for AI Machine Learning scikit-learn PyTorch Natural Language Processing LangChain Ollama OpenCV Codex Claude Code OpenCode Vibe Coding Selenium Playwright

FAQ