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.
Object detection • TensorFlow CUDA • KITTI min • Windows • self-driving car • webcam
solution:demo-obj-detection-kitti-min-tf-cuda-win-webcam (v1.5.0)Portable solution description
- What is the portable CK solution: docs
- 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:squeezedet
- Workflow CLI and Python API (compile, run, benchmark, validate): module:program
- Workflow dependencies (model, dataset, framework): View
- Benchmarking pipeline (build, run, validate): program:squeezedet
Check the prerequisites for your system
Install manually from the command line (to be automated in the future):
You need to install VS Studio and CUDA 9.0! CK will automatically detect them.
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-obj-detection-kitti-min-tf-cuda-win-webcam
Run this workflow locally
or start local run manually from the command line:
cb run demo-obj-detection-kitti-min-tf-cuda-win-webcam # Note that the following CK program pipeline will be executed: ck compile program:squeezedet --cmd_key=use_codereef --speed ck run program:squeezedet --cmd_key=use_codereef
Successfully tested configuration
Host OS: windows-64 (Windows 10)
Target OS: windows-64 (Windows 10)
Target machine: LENOVO ThinkPad T470p (20J6CTO1WW)
Target CPU: Intel(R) Core(TM) i5-7300HQ CPU @ 2.50GHz
Python version for virtual env: 3.6.8
Target OS: windows-64 (Windows 10)
Target machine: LENOVO ThinkPad T470p (20J6CTO1WW)
Target CPU: Intel(R) Core(TM) i5-7300HQ CPU @ 2.50GHz
Python version for virtual env: 3.6.8
Reused CK components
pip install opencv-python call ck install package --tags=dataset,object-detection,kitti-min call ck install package --tags=tensorflow,demo,squeezedet call ck install package --tags=model,squeezedet call ck install package:lib-tensorflow-1.10.0-cuda