Skip to content

Added the ability to benchmark on a directory and output to a chart #314

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

Merged
merged 1 commit into from
Oct 28, 2024

Conversation

ahmadsharif1
Copy link
Contributor

@ahmadsharif1 ahmadsharif1 commented Oct 28, 2024

Example run:

python benchmarks/decoders/benchmark_decoders.py --decoders=tcoptions:device=cuda,tcoptions: --bm_video_speed_min_run_seconds=0.1 --bm_video_dir=/tmp/videos1 --plot_path=chart.png

video=/tmp/videos1/853.mp4, decoder=TorchcodecNonCompiled:
[--------------- video=/tmp/videos1/853.mp4 h264 3840x2160, 4.988317s 59.94005593469701fps ---------------]
                                         |  10 seek()+next()  |  1 next()  |  10 next()  |  create()+next()
1 threads: ------------------------------------------------------------------------------------------------
      TorchcodecNonCompiled:device=cuda  |       3236.4       |   380.1    |    442.3    |                 
      TorchcodecNonCompiled              |                    |            |             |       274.6     
      TorchcodecNonCompiled:             |       2017.1       |   259.9    |    344.5    |                 

Times are in milliseconds (ms).

Produces this chart:

image

@facebook-github-bot facebook-github-bot added the CLA Signed This label is managed by the Meta Open Source bot. label Oct 28, 2024
@ahmadsharif1 ahmadsharif1 merged commit 6ecf3a8 into pytorch:main Oct 28, 2024
40 checks passed
@ahmadsharif1 ahmadsharif1 deleted the bench5 branch October 28, 2024 20:02
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
CLA Signed This label is managed by the Meta Open Source bot.
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants