TensorFlow for Image Recognition Training Course

Machine Learning and Recursive Neural Networks (RNN) Basics for Government

• Neural Networks (NN) and Recurrent Neural Networks (RNN)
• Backpropagation Techniques
• Long Short-Term Memory (LSTM) Models

TensorFlow Basics for Government

• Creation, Initialization, Saving, and Restoring TensorFlow Variables
• Feeding, Reading, and Preloading TensorFlow Data
• Using TensorFlow Infrastructure to Train Models at Scale for Government
• Visualizing and Evaluating Models with TensorBoard for Government

TensorFlow Mechanics 101 for Government

• Tutorial Files for Government
• Prepare the Data
  • Data Download for Government
  • Inputs and Placeholders for Government
• Build the Graph
  • Inference for Government
  • Loss Calculation for Government
  • Training for Government
• Train the Model
  • The Graph Structure for Government
  • The Session Management for Government
  • The Training Loop for Government
• Evaluate the Model
  • Building the Evaluation Graph for Government
  • Generating Evaluation Output for Government

Advanced Usage for Government

• Threading and Queues for Government
• Distributed TensorFlow for Government
• Writing Documentation and Sharing Models for Government
• Customizing Data Readers for Government
• Using GPUs¹ for Government (topics related to the use of GPUs are not available as part of a remote course)
• Manipulating TensorFlow Model Files for Government

TensorFlow Serving for Government

• Introduction to TensorFlow Serving for Government
• Basic Serving Tutorial for Government
• Advanced Serving Tutorial for Government
• Serving Inception Model Tutorial for Government

Convolutional Neural Networks (CNN) for Government

• Overview of CNNs for Government
  • Goals for Government
  • Highlights of the Tutorial for Government
  • Model Architecture for Government
• Code Organization for Government
• CIFAR-10 Model for Government
  • Model Inputs for Government
  • Model Prediction for Government
  • Model Training for Government
• Launching and Training the Model for Government
• Evaluating a Model for Government
• Training a Model Using Multiple GPU Cards¹ for Government
  • Placing Variables and Operations on Devices for Government
  • Launching and Training the Model on Multiple GPU Cards for Government

Deep Learning for MNIST for Government

• Setup for Government
• Loading MNIST Data for Government
• Starting a TensorFlow InteractiveSession for Government
• Building a Softmax Regression Model for Government
• Placeholders for Government
• Variables for Government
• Predicted Class and Cost Function for Government
• Training the Model for Government
• Evaluating the Model for Government
• Building a Multilayer Convolutional Network for Government
• Weight Initialization for Government
• Convolution and Pooling for Government
• First Convolutional Layer for Government
• Second Convolutional Layer for Government
• Densely Connected Layer for Government
• Readout Layer for Government
• Training and Evaluating the Model for Government

Image Recognition for Government

• Inception-v3 for Government
  • C++ Implementation for Government
  • Java Implementation for Government

¹ Topics related to the use of GPUs are not available as part of a remote course. They can be delivered during classroom-based courses, but only by prior agreement, and only if both the trainer and all participants have laptops with supported NVIDIA GPUs, with 64-bit Linux installed (not provided by NobleProg). NobleProg cannot guarantee the availability of trainers with the required hardware.