# Increasing fps on Jetson TX2 for a Tensorflow algorithm **URL:** \ **Category:** Jetson TX2\ **Created:** [January 29, 2018, 5:45am UTC](https://forums.developer.nvidia.com/t/increasing-fps-on-jetson-tx2-for-a-tensorflow-algorithm/57562 "2018-01-29T05:45:54Z")\ **Posts on this page:** 8\ **Page:** 1
**Author:** ![Pratosha](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@Pratosha](https://forums.developer.nvidia.com/u/Pratosha)\ **Post date:** [January 29, 2018, 5:45am UTC](https://forums.developer.nvidia.com/t/increasing-fps-on-jetson-tx2-for-a-tensorflow-algorithm/57562/1 "2018-01-29T05:45:54Z")
Hi , I am working on a Real time Object detection algorithm using Tensorflow with GPU support v1.0.1 on Jetson TX2. After using the below commands: $ sudo nvpmodel -m 0 $ sudo ./jetson\_clocks.sh The algorithm is taking 0.8 to 0.9 seconds to detect one frame. How can I increase the fps to 17-19? Kindly help. ---
**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:** [January 29, 2018, 9:12am UTC](https://forums.developer.nvidia.com/t/increasing-fps-on-jetson-tx2-for-a-tensorflow-algorithm/57562/2 "2018-01-29T09:12:24Z")
Hi, We have an object detection sample with DetectNet and TensorRT: > **[GitHub - dusty-nv/jetson-inference: Hello AI World guide to deploying deep-learning...](https://github.com/dusty-nv/jetson-inference)** > > Hello AI World guide to deploying deep-learning inference networks and deep vision primitives with TensorRT and NVIDIA Jetson. It can reach around 11-fps with TX2 maximized frequency. Thanks. ---
**Author:** ![Pratosha](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@Pratosha](https://forums.developer.nvidia.com/u/Pratosha)\ **Post date:** [January 29, 2018, 9:19am UTC](https://forums.developer.nvidia.com/t/increasing-fps-on-jetson-tx2-for-a-tensorflow-algorithm/57562/3 "2018-01-29T09:19:13Z")
Hi AastaLLL, Thanks for your response. I am concentrating on increasing the fps of my current working algorithm as it is fine tuned for automotive on-road object detection. Is there any other way I can increase the fps? Kindly help ---
**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:** [January 30, 2018, 9:26am UTC](https://forums.developer.nvidia.com/t/increasing-fps-on-jetson-tx2-for-a-tensorflow-algorithm/57562/4 "2018-01-30T09:26:14Z")
Hi, Suppose you want to use a TensorFlow model on Jetson. Here are some advices for you: 1. Try TensorRT: > **[NVIDIA TensorRT](https://developer.nvidia.com/tensorrt)** > > An SDK with an optimizer for high-performance deep learning inference. 2. Profile your model first. If an op run slowly on GPU(ex. tf.where), try to place it on CPU. Thanks. ---
**Author:** ![Pratosha](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@Pratosha](https://forums.developer.nvidia.com/u/Pratosha)\ **Post date:** [January 30, 2018, 9:50am UTC](https://forums.developer.nvidia.com/t/increasing-fps-on-jetson-tx2-for-a-tensorflow-algorithm/57562/5 "2018-01-30T09:50:04Z")
Hi AastaLLL, It take 17 seconds per frame while placed on the CPU whereas 0.8 seconds/frame when run on the GPU. The code is written in python. I have tensorRT v3.0 installed on Jetson TX2. How do I use UFF format to make it compatible with tensorRT? I did run the detectnet code from the link shared - [GitHub - dusty-nv/jetson-inference: Hello AI World guide to deploying deep-learning inference networks and deep vision primitives with TensorRT and NVIDIA Jetson.](https://github.com/dusty-nv/jetson-inference) Is there anyway to train the model using our own dataset and checkpoint file ? For instance -(VGGnet\_fast\_rcnn\_iter\_70000.ckpt) Thanks, Pratosha ---
**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 8, 2018, 9:32am UTC](https://forums.developer.nvidia.com/t/increasing-fps-on-jetson-tx2-for-a-tensorflow-algorithm/57562/6 "2018-02-08T09:32:06Z")
Hi, To launch TensorRT with a TensorFlow model on Jetson, it requires following steps: **1.** Convert TensorFlow model to UFF format - Require x86 Linux platform - Python interface - Sample is located at '/usr/local/lib/python2.7/dist-packages/tensorrt/examples/tf\_to\_trt/' **2.** Create an TensorRT engine with UFF file - Can be applied on Jetson - C++ - Sample is located at '/usr/src/tensorrt/samples/sampleUffMNIST/' You can re-train the detectNet model with DIGITs and tutorial can be found here: [https://github.com/dusty-nv/jetson-inference#digits-workflow](https://github.com/dusty-nv/jetson-inference#digits-workflow) Please noticed that detectNet is a caffe-based model and use nvcaffe\_parser rather than uff\_parser. Thanks. ---
**Author:** ![Pratosha](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@Pratosha](https://forums.developer.nvidia.com/u/Pratosha)\ **Post date:** [February 8, 2018, 12:34pm UTC](https://forums.developer.nvidia.com/t/increasing-fps-on-jetson-tx2-for-a-tensorflow-algorithm/57562/7 "2018-02-08T12:34:00Z")
Hi AastaLLL, Thanks :) will surely try ---
**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/increasing-fps-on-jetson-tx2-for-a-tensorflow-algorithm/57562/8 "2021-10-18T18:28:06Z")
Closed on October 18, 2021, 6:28pm UTC