TensorFlow 2.x [Deprecated]

This section outlines all computer-vision training and finetuning pipelines that are implemented with TensorFlow 2.x. As of TAO 6.25.09, support for these models has been deprecated and will be removed in a future release. For continued support, please fall back to TAO 6.0.0 or build the Docker container from source.

The source code for these networks are hosted on GitHub.

• Image Classification (TF2)
  • Preparing the Input Data Structure
  • Creating an Experiment Specification File - Specification File for Classification
  • Training the model
  • Evaluating the Model
  • Pruning the Model
  • Re-training the Pruned Model
  • Exporting the model
  • Deploying to DeepStream
• EfficientDet (TF2)
  • Data Input for EfficientDet
  • Pre-processing the Dataset
  • Creating a Configuration File
  • Pruning the Model
  • Re-training the Pruned Model
  • Exporting the Model
  • Deploying to DeepStream