Join the public MLCommons taskforce to participate in the collaborative development of the next generation of this open-source technology!
docker:image-classification-tflite.dashboard.ubuntu-18.04 (v1.0.0)
Creation date: 2019-06-05
Source: GitHub
cID: 88eef0cd8c43b68a:34b17b135b623246

Don't hesitate to get in touch if you encounter any issues or would like to discuss this community project!
Please report if this CK component works: 1  or fails: 0 
Sign up to be notified when artifacts are shared or updated!

Description  

This CK-powered container is our attempt to provide a common API to customize, build and run AI and ML applications with different models, frameworks, libraries, datasets, compilers, formats, backends and platforms. Our on-going project is to make the onboarding process as simple as possible via this platform. Please check this CK white paper and don't hesitate to contact us if you have suggestions or feedback!

ReadMe  

MLPerf Inference - Image Classification - TFLite (Ubuntu 18.04): Dashboard

  1. Dashboard image (based on Ubuntu 18.04 latest)

NB: You may need to run commands below with sudo, unless you manage Docker as a non-root user.

Dashboard image

Download

$ docker pull ctuning/image-classification-tflite.dashboard.ubuntu-18.04

Build

$ ck build docker:image-classification-tflite.dashboard.ubuntu-18.04

NB: Equivalent to:

$ cd `ck find docker:image-classification-tflite.dashboard.ubuntu-18.04`
$ docker build -f Dockerfile -t ctuning/image-classification-tflite.dashboard.ubuntu-18.04 .

Run

Dashboard

  1. Run a dashboard container with an interactive shell:
$ ck run docker:image-classification-tflite.dashboard.ubuntu-18.04

NB: Equivalent to:

$ docker run -it --publish 3355:3344 --rm ctuning/image-classification-tflite.dashboard.ubuntu-18.04
  1. Point your browser to http://localhost:3355/?template=dashboard&scenario=mlperf.mobilenets to listen to the server.

Bash

$ docker run -it --rm ctuning/image-classification-tflite.dashboard.ubuntu-18.04 bash

Versions  

Files  

Comments  

Please log in to add your comments!
If you notice any inapropriate content that should not be here, please report us as soon as possible and we will try to remove it within 48 hours!