NVIDIA-AI-IOT/tf_to_trt_image_classification
NVIDIA repository for converting TensorFlow image classification models to TensorRT for optimized inference on Jetson TX2.
Not currently ranked — collecting fresh signals.
star history
This repository contains scripts and examples for converting pre-trained TensorFlow image classification models from the Slim model zoo to TensorRT format. The conversion enables significant inference speedups on NVIDIA edge devices like the Jetson TX2, benchmarking models such as Inception and ResNet architectures. It includes setup instructions, model download scripts, conversion utilities, and benchmark tools for evaluating TensorRT engine performance against raw TensorFlow execution.
Frequently asked
- What is NVIDIA-AI-IOT/tf_to_trt_image_classification?
- NVIDIA repository for converting TensorFlow image classification models to TensorRT for optimized inference on Jetson TX2.
- Is tf_to_trt_image_classification open source?
- Yes — NVIDIA-AI-IOT/tf_to_trt_image_classification is open source, released under the BSD-3-Clause license.
- What language is tf_to_trt_image_classification written in?
- NVIDIA-AI-IOT/tf_to_trt_image_classification is primarily written in Python.
- How popular is tf_to_trt_image_classification?
- NVIDIA-AI-IOT/tf_to_trt_image_classification has 460 stars on GitHub.
- Where can I find tf_to_trt_image_classification?
- NVIDIA-AI-IOT/tf_to_trt_image_classification is on GitHub at https://github.com/NVIDIA-AI-IOT/tf_to_trt_image_classification.