TensorRT 4.0 Python API Documentation¶
TensorRT 4.0 includes support for Python, allowing developers to integrate a TensorRT inference engine into a python development environment or to experiment with TensorRT in an accessible fashion.
TensorRT 4.0 includes the Universial Framework Format (UFF): a way to convert models trained in TensorFlow and soon other frameworks like Caffe2 to a single model format. TensorRT is also now able to generate engines from UFF models.
Installing TensorRT and the UFF Toolkit¶
Workflows and Use Cases¶
There are a few use cases for which the Python API for TensorRT excels.
We have included a few sample applications with the TensorRT Python package which cover many of these use cases.
- There is an existing TensorFlow (or other UFF compatable framework) model that a developer wants to try out with TensorRT.
- There is a Caffe1 model that a developer want to try out with TensorRT
- A developer wants to deploy a TensorRT engine as a part of a larger application such as a web backend