Check the preview of 2nd version of this platform being developed by the open MLCommons taskforce on automation and reproducibility as a free, open-source and technology-agnostic on-prem platform.
docker:object-detection-tf-py.debian-9 (v3.0.0)
Share
Copyright: See copyright in the source repository
License: See license in the source repository
Creation date: 2019-06-17
Source: GitHub
cID: 88eef0cd8c43b68a:23cdc43ca7446b0b

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 - Object Detection - TF-Python (Debian 9)

  1. Default image (based on Debian 9 latest)

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

Default image

Download

$ docker pull ctuning/object-detection-tf-py.debian-9

Build

$ ck build docker:object-detection-tf-py.debian-9

NB: Equivalent to:

$ cd `ck find docker:object-detection-tf-py.debian-9`
$ docker build -f Dockerfile -t ctuning/object-detection-tf-py.debian-9 .

Run

Object Detection (default command)

Non-quantized, 50 images
$ ck run docker:object-detection-tf-py.debian-9

NB: Equivalent to:

$ docker run --rm ctuning/object-detection-tf-py.debian-9 \
    "ck run program:object-detection-tf-py \
        --dep_add_tags.weights=ssd-mobilenet,non-quantized \
        --dep_add_tags.dataset=coco.2017,full --env.CK_BATCH_COUNT=50 \
    "
...
Summary:
-------------------------------
Graph loaded in 0.923238s
All images loaded in 17.265170s
All images detected in 1.988970s
Average detection time: 0.040591s
mAP: 0.3148934914889957
Recall: 0.3225293342489256
--------------------------------

Object Detection (custom command)

Non-quantized, 5000 images
$ docker run --rm ctuning/object-detection-tf-py.debian-9 \
    "ck run program:object-detection-tf-py \
        --dep_add_tags.weights=ssd-mobilenet,non-quantized \
        --dep_add_tags.dataset=coco.2017,full --env.CK_BATCH_COUNT=5000 \
    "
...
Summary:
-------------------------------
Graph loaded in 0.937587s
All images loaded in 2006.936262s
All images detected in 272.221948s
Average detection time: 0.054455s
mAP: 0.23111107753357035
Recall: 0.26304841188725403
--------------------------------
Quantized, 50 images
$ docker run --rm ctuning/object-detection-tf-py.debian-9 \
    "ck run program:object-detection-tf-py \
        --dep_add_tags.weights=ssd-mobilenet,quantized \
        --dep_add_tags.dataset=coco.2017,full --env.CK_BATCH_COUNT=50 \
    "
...
Summary:
-------------------------------
Graph loaded in 1.092699s
All images loaded in 12.919672s
All images detected in 2.137745s
Average detection time: 0.043627s
mAP: 0.32625778039773207
Recall: 0.33433530428110675
--------------------------------
Quantized, 5000 images
$ docker run --rm ctuning/object-detection-tf-py.debian-9 \
    "ck run program:object-detection-tf-py \
        --dep_add_tags.weights=ssd-mobilenet,quantized \
        --dep_add_tags.dataset=coco.2017,full --env.CK_BATCH_COUNT=5000 \
    "
...
Summary:
-------------------------------
Graph loaded in 1.589762s
All images loaded in 1273.597364s
All images detected in 213.662603s
Average detection time: 0.042741s
mAP: 0.23594222525632427
Recall: 0.26864982712779556
--------------------------------

Bash

$ docker run -it --rm ctuning/object-detection-tf-py.debian-9 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!