Collective Knowledge repository for collaboratively benchmarking and optimising embedded deep vision runtime library for Jetson TX1
CK-TensorRT is an open framework for collaborative and reproducible optimisation of convolutional neural networks for Jetson TX1. It's based on the Deep Inference framework from Dustin Franklin (a Jetson developer @ NVIDIA) and the Collective Knowledge framework for customizable cross-platform experimental workflows from the cTuning Foundation. In essence, CK-TensorRT is simply a suite of convenient wrappers with unified JSON API for customizable building, evaluating and multi-objective optimisation of Jetson Inference runtime library for Jetson TX1.
See project page for more details.
Quick installation on Ubuntu
Installing general dependencies
$ sudo apt install coreutils \ build-essential \ make \ cmake \ wget \ git \ python \ python-pip
Installing CK-TensorRT dependencies
$ sudo apt install libqt4-dev \ libglew-dev \ libgstreamer1.0-dev
$ sudo pip install ck $ ck version
Installing CK-TensorRT repository
$ ck pull repo:ck-tensorrt --url=https://github.com/dividiti/ck-tensorrt
Building CK-TensorRT and all dependencies via CK
The first time you run a TensorRT program (e.g.
tensorrt-test), CK will
build and install all missing dependencies on your machine,
download the required data sets and start the benchmark:
$ ck run program:tensorrt-test
Related projects and initiatives
We are working with the community to unify and crowdsource performance analysis and tuning of various DNN frameworks (or any realistic workload) using Collective Knowledge Technology:
- Reusable AI artifacts
- Android app for DNN crowd-benchmarking and crowd-tuning
- CK-powered ARM workload automation
Open R&D challenges
We use crowd-benchmarking and crowd-tuning of such realistic workloads across diverse hardware for open academic and industrial R&D challenges - join this community effort!