# Tensorrt tensorflow **URL:** \ **Category:** Jetson TX2\ **Created:** [February 9, 2018, 12:39pm UTC](https://forums.developer.nvidia.com/t/tensorrt-tensorflow/58056 "2018-02-09T12:39:00Z")\ **Posts on this page:** 3\ **Page:** 1
**Author:** ![JOO12](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@JOO12](https://forums.developer.nvidia.com/u/JOO12)\ **Post date:** [February 9, 2018, 12:39pm UTC](https://forums.developer.nvidia.com/t/tensorrt-tensorflow/58056/1 "2018-02-09T12:39:00Z")
Hello, I am trying to apply tensorrt to our trained model. Our model was trained on Tensorflow and had custom layer. 1. As I refer to tutorial and search this topic on internet, there is no example for applying tensorrt to tensorflow custom layer. Is it impossible for me to apply tensorrt to our model based on tensorflow? 2. Is the plugin layer only supported on caffe framework? If so, Can you guide me to apply tensorrt our trained model based on tensorflow even if it has custom layer? ---
**Author:** ![AastaLLL](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/aastalll/32/14043_2.png) [@AastaLLL](https://forums.developer.nvidia.com/u/AastaLLL)\ **Post date:** [February 12, 2018, 3:18am UTC](https://forums.developer.nvidia.com/t/tensorrt-tensorflow/58056/2 "2018-02-12T03:18:54Z")
Hi, To create TensorRT engine, it’s required to convert TensorFlow model into UFF format first. Currently, our plugin API only support caffe parser, not available for UFF parser. Thanks. ---
**Author:** ![nadeemm](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/nadeemm/32/367020_2.png) [@nadeemm](https://forums.developer.nvidia.com/u/nadeemm)\ **Post date:** [October 18, 2021, 6:28pm UTC](https://forums.developer.nvidia.com/t/tensorrt-tensorflow/58056/3 "2021-10-18T18:28:09Z")