Course Outline
Foundations of Machine Learning and Recursive Neural Networks (RNN)
- Neural Networks (NN) and RNNs
- Backpropagation
- Long Short-Term Memory (LSTM)
TensorFlow Fundamentals
- Creating, initializing, saving, and restoring TensorFlow variables.
- Feeding, reading, and preloading data into TensorFlow.
- Leveraging TensorFlow's infrastructure to train models at scale.
- Visualizing and evaluating models using TensorBoard.
Core TensorFlow Mechanics
- Preparing the Data
- Downloading datasets
- Understanding Inputs and Placeholders
- Constructing the Graph
- Inference
- Loss calculation
- Training processes
- Training the Model
- Managing the Graph
- Utilizing Sessions
- Implementing the Training Loop
- Evaluating the Model
- Building the Evaluation Graph
- Analyzing Evaluation Output
Advanced Usage
- Threading and Queues
- Distributed TensorFlow
- Documentation and Model Sharing
- Customizing Data Readers
- Utilizing GPUs¹
- Manipulating TensorFlow Model Files
TensorFlow Serving
- Introduction to Serving
- Basic Serving Tutorial
- Advanced Serving Tutorial
- Serving the Inception Model
¹ The "Using GPUs" topic within Advanced Usage is not available for remote courses. This module can be included in classroom-based sessions only by prior agreement and provided all trainers and participants have laptops with supported NVIDIA GPUs and 64-bit Linux installed (hardware not supplied by NobleProg). NobleProg cannot guarantee trainer availability for this specific hardware setup.
Requirements
- Understanding of Statistics
- Proficiency in Python
- (Optional) A laptop equipped with an NVIDIA GPU supporting CUDA 8.0 and cuDNN 5.1, running a 64-bit Linux operating system.
Testimonials (2)
The training was organized and well-planned out, and I come out of it with systematized knowledge and a good look at topics we looked at
Magdalena - Samsung Electronics Polska Sp. z o.o.
Course - Deep Learning with TensorFlow 2
Tomasz really know the information well and the course was well paced.
