Model Online / On-Site
Duration
Modules 5 modules

Course Objective & Scope

The TensorFlow and Keras ecosystem offers an integrated deep learning stack spanning rapid prototyping with Keras, high-throughput input pipelines with tf.data and enterprise deployment via SavedModel. This course teaches participants how to build, train and export deep learning models from scratch while understanding TensorFlow 2's eager execution and @tf.function graph compilation.

Participants build non-blocking data pipelines with tf.data, design models using the Keras Sequential, Functional and Subclassing APIs, write custom training steps with GradientTape and monitor experiments in TensorBoard. They leave with a reusable project template that outputs production-ready SavedModel artefacts.

Who Should Attend?

  • Data scientists building deep learning models with TensorFlow and Keras
  • ML engineers maintaining and extending existing TensorFlow models in production
  • Software developers looking for a structured framework to start building neural networks
  • Prerequisite: basic Python skills and familiarity with core machine learning concepts

Key Takeaways

  • Work fluently with tf.Tensor, tf.Variable, GradientTape and @tf.function graph compilation
  • Build high-speed input pipelines with tf.data.Dataset using prefetching, caching and parallel mapping
  • Choose and implement Keras Sequential, Functional and Model Subclassing architectures
  • Use built-in preprocessing layers (Normalization, TextVectorization) and Keras Callbacks
  • Analyse training runs in TensorBoard and export models in .keras and SavedModel formats

Curriculum

TensorFlow 2 Architecture: Tensors, GradientTape and tf.function
  • Constant tensors (tf.constant), trainable variables (tf.Variable) and device placement
  • Automatic differentiation with tf.GradientTape and AutoGraph compilation via @tf.function
High-Performance Input Pipelines with tf.data
  • Building tf.data.Dataset objects from in-memory arrays, CSV/Parquet files and TFRecords
  • Eliminating GPU starvation with map, batch, cache and prefetch(tf.data.AUTOTUNE)
Model Building in Keras: Sequential, Functional and Subclassing
  • The Keras Functional API for multi-input, multi-output and branched architectures
  • Writing custom layers (keras.layers.Layer) and subclassing keras.Model
Preprocessing Layers, Training, Callbacks and TensorBoard
  • In-graph preprocessing layers (Normalization, CategoryEncoding, TextVectorization)
  • compile/fit, EarlyStopping, ModelCheckpoint, overriding train_step and TensorBoard
Saving Models, Transfer Learning and Deployment Readiness
  • Fine-tuning workflows with pretrained backbone models
  • Comparing the .keras format and tf.saved_model.save, and verifying exports with saved_model_cli

Other Courses in This Category

  • R Programming for Data Science and Statistical Modelling

    R programming for data science, statistical analysis and machine learning: tidyverse (dplyr, tidyr, ggplot2), hypothesis testing and regression, ML workflows with tidymodels, Quarto reporting and Plumber APIs.

    Programming for AI Corporate
    Live Course
    5 modules
    View
  • Python for Data Science Python for Data Science

    Hands-on Python training covering data manipulation with Pandas and Polars, visualization with Matplotlib, Seaborn, and Plotly, exploratory data analysis (EDA), and machine learning modeling with Scikit-learn.

    Programming for AI Corporate, Individual
    Live Course
    4 modules
    View
  • Modern C++ Fundamentals and High-Performance AI Applications

    Modern C++ (C++17/20) for AI and high-performance systems: RAII and smart pointers, STL, move semantics, multithreading, SIMD, building Python extensions with pybind11 and the LibTorch/ONNX Runtime C++ APIs.

    Programming for AI Corporate
    Live Course
    5 modules
    View
  • Python Programming Python Programming

    Master Python from scratch: data structures, control flow, functional programming, Object-Oriented Programming (OOP), error handling, file I/O, virtual environments, and Pandas.

    Programming for AI Corporate, Individual
    Live Course
    9 modules
    View
  • Advanced Python for AI and Data Engineering

    Advanced Python for AI and data engineering: type hinting, decorators, memory-efficient generators, asyncio, multiprocessing and the GIL, Cython/Numba acceleration, profiling and packaging. For developers and data scientists.

    Programming for AI Corporate
    Live Course
    5 modules
    View
  • API Integration and Development with Python for AI Projects

    Consuming and building APIs in Python for AI and data projects: HTTP/REST principles, requests and async httpx clients, authentication, retry/rate-limit handling, LLM APIs and foundational service design.

    Programming for AI Corporate
    Live Course
    5 modules
    View

Get in touch