How aymericdamien/tensorflow-examples works
TensorFlow Examples is a learning repository, not an application runtime: its main workflow is for a learner to choose a topic, study runnable examples or notebooks, and apply TensorFlow APIs to model-building and data tasks. The README documents parallel TensorFlow v1 and v2 materials, supervised and unsupervised models, data handling, model utilities, and multi-GPU training. Relationships below reflect those documented capabilities; only input_data.py was sampled, so implementation-level links between tutorial topics are not inferred.
Main entry points: examples Python examples · 0_Prerequisite ML prerequisites · 1_Introduction TensorFlow basics · 2_BasicModels Basic models
Components 14
Getting started
- ML prerequisites
tensorflow_v2/notebooks/0_Prerequisite - TensorFlow basics
tensorflow_v2/notebooks/1_Introduction
Model tutorials
- Basic models
tensorflow_v2/notebooks/2_BasicModels - Neural networks
tensorflow_v2/notebooks/3_NeuralNetworks
Data and hardware
- Data management
tensorflow_v2/notebooks/5_DataManagement - Multi-GPU training
tensorflow_v2/notebooks/6_Hardware - MNIST reader
input_data.py
Utilities and versions
- Model utilities
tensorflow_v2/notebooks/4_Utils - TF v1 examples
tensorflow_v1/examples - TF v1 notebooks
tensorflow_v1/notebooks - Python examples
examples
Other components
- Learner
- TensorFlow
- MNIST dataset
Connections 12
- Learner → ML prerequisites: studies first
README.md - Learner → TensorFlow basics: learns basics
README.md - Learner → Basic models: studies models
README.md - Learner → Neural networks: studies networks
README.md - Learner → Model utilities: learns utilities
README.md - Learner → Data management: learns pipelines
README.md - Learner → Multi-GPU training: learns scaling
README.md - Learner → TF v1 examples: chooses v1
README.md - Learner → TF v1 notebooks: chooses v1
README.md - Learner → Python examples: runs examples
README.md - Python examples → TensorFlow: requires
README.md - MNIST dataset → MNIST reader: downloaded and parsed
input_data.py