This portal has been archived. Explore the next generation of this technology.
Image classification • MLPerf inference • TFLite CPU • Mobilenets • Raspberry Pi 4 • webcam
solution:demo-image-classification-tflite-cpu-mobilenets-rpi4 (v1.5.0)Portable solution description
- What is the portable CK solution: docs
- Reproduced paper: MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
- Reproduced SOTA results (crowd-benchmarking): crowd-benchmarking-mlperf-inference-classification-mobilenets
Auto-tuning results: (Pareto-efficient ML/SW/HW co-design)
- Reproducibility checklist: ACM/cTuning
- Automation framework: CK
- CK repository: A collection of all AI and ML workflows and packages in the CK format
- Benchmarking pipeline (build, run, validate): program:image-classification-tflite-codereef
- Workflow CLI and Python API (compile, run, benchmark, validate): module:program
- Workflow dependencies (model, dataset, framework): View
- Workflow params: --env.CK_IMAGE_DIR=input
- Benchmarking pipeline (build, run, validate): program:image-classification-tflite-codereef
Check the prerequisites for your system
Install manually from the command line (to be automated in the future):
Sources: * https://github.com/mlperf/inference/tree/master/v0.5/classification_and_detection/optional_harness_ck/classification This CK solution demo was prepared by Grigori Fursin and Hervé Guillou. Requred Ubuntu packages: sudo apt update sudo apt install git wget libz-dev curl cmake sudo apt install gcc g++ autoconf autogen libtool For OpenCV: sudo apt install python-opencv sudo apt install libatlas-base-dev sudo apt install libjasper-dev sudo apt install libhdf5-dev sudo apt install libhdf5-serial-dev sudo apt install libqtgui4 sudo apt install libqt4-test
Install cBench (docs)
Install cBench from the command line (a small Python library to manage CK solutions):
Note that you may need to add the --user flag if you install in your user space, i.e. "python3 -m pip install cbench --user"
pip3 install cbench or python3 -m pip install cbench or pip install cbench
Init this solution with the portable workflow on your machine
Run manually from your command line
(cBench will attempt to automatically adapt this workflow to your system -
you may need to press Enter several times to select default answers for some questions):
cb init demo-image-classification-tflite-cpu-mobilenets-rpi4
Run this workflow locally
or start local run manually from the command line:
cb run demo-image-classification-tflite-cpu-mobilenets-rpi4 # Note that the following CK program pipeline will be executed: ck compile program:image-classification-tflite-codereef --cmd_key=default --speed ck run program:image-classification-tflite-codereef --cmd_key=default
Successfully tested configuration
Host OS: linux-32 (Raspbian GNU/Linux 10 (buster))
Target OS: linux-32 (Raspbian GNU/Linux 10 (buster))
Target machine: Raspberry (Raspberry Pi 4 Model B Rev 1.1 )
Target CPU: BCM2835
Target CPUs:
Python version for virtual env: 3.7.3
Target OS: linux-32 (Raspbian GNU/Linux 10 (buster))
Target machine: Raspberry (Raspberry Pi 4 Model B Rev 1.1 )
Target CPU: BCM2835
Target CPUs:
Python version for virtual env: 3.7.3
Reused CK components
pip install numpy pip install opencv-python ck pull repo:ck-mlperf ck install package --tags=lib,python-package,numpy ck install package --tags=lib,python-package,cv2 ck install package:imagenet-2012-val-min ck install package:imagenet-2012-aux ck install package:lib-rtl-xopenme ck install package:dataset-imagenet-preprocessed-using-opencv ck install package --tags=lib,tflite,v1.13.1,vsrc ck install package:model-tf-mlperf-mobilenet-quantized ck compile program:image-classification-tflite-codereef --speed