Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Benchmarking script #14

Closed
robmarkcole opened this issue Jun 13, 2020 · 5 comments
Closed

Benchmarking script #14

robmarkcole opened this issue Jun 13, 2020 · 5 comments

Comments

@robmarkcole
Copy link
Collaborator

I will happily create a benchmarking script, to evaluate speed of deepstack on different platforms. It would do a batch job of say 30 detections and present the runtime. I don’t want to reinvent the wheel, perhaps you have a script already?

@johnolafenwa
Copy link
Owner

johnolafenwa commented Jun 13, 2020

We don't have a standard script yet for that. Please create it and make a PR to include it in benchmark directory.

@robmarkcole
Copy link
Collaborator Author

OK this will be a script which just posts every photo in a directory for processing. Wont include the photos, although we could have a standard set of photos in a seperate repo perhaps

@robmarkcole
Copy link
Collaborator Author

robmarkcole commented Jun 19, 2020

Created a notebook here (will breakout into script) and the results are in, with tflite being lightning fast, processing 15 images (obj detection):

Platform Speed (sec) Predictions
Mac Pro with deepstack (add version tag) 51.9 91
RPi4 with tflite-server 9.33 159

ps which is the 'benchmark directory'?

@johnolafenwa
Copy link
Owner

Interesting. Thanks for these @robmarkcole , i will push a nightly tag pending the setup of the cicd pipeline so you can benchmark against the new detection pipeline.

BTW, as i have not setup the benchmark directory, can you make a PR for these to include the benchmark scripts and we can review and make neccessary updates.

I am also curios, what are the specs for the MacBook Pro?

@robmarkcole
Copy link
Collaborator Author

Hardware Overview:

Model Name: MacBook Pro
Model Identifier: MacBookPro14,1
Processor Name: Dual-Core Intel Core i5
Processor Speed: 2.3 GHz
Number of Processors: 1
Total Number of Cores: 2
L2 Cache (per Core): 256 KB
L3 Cache: 4 MB
Hyper-Threading Technology: Enabled
Memory: 8 GB

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants