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

How to get the output from the readme #18

Open
alfonsocv12 opened this issue Oct 24, 2023 · 1 comment
Open

How to get the output from the readme #18

alfonsocv12 opened this issue Oct 24, 2023 · 1 comment

Comments

@alfonsocv12
Copy link

alfonsocv12 commented Oct 24, 2023

Hello Lukas I have test out the bench mark with the example code that you wrote on the readme.

The output is really different from the examples that you have on the same file.

I don't know if you use a script or wrote them by hand or with some output of another program.

I'll like to have it on the same format to compare with other devices.

Here is the curren't output of my rx 6800 xt

Warming up with batch_size=1: 100%|██████████████████████████████████████████████████████████████████████████████████████████████████████████| 1/1 [00:04<00:00,  4.91s/it]
Warning! No positional inputs found for a module, assuming batch size is 1.
Warming up with batch_size=1: 100%|███████████████████████████████████████████████████████████████████████████████████████████████████████| 10/10 [00:00<00:00, 182.40it/s]
Measuring inference for batch_size=1: 100%|█████████████████████████████████████████████████████████████████████████████████████████████| 100/100 [00:00<00:00, 181.97it/s]
Unable to measure energy consumption. Device must be a NVIDIA Jetson.
Warming up with batch_size=8: 100%|███████████████████████████████████████████████████████████████████████████████████████████████████████| 10/10 [00:00<00:00, 152.08it/s]
Measuring inference for batch_size=8: 100%|█████████████████████████████████████████████████████████████████████████████████████████████| 100/100 [00:00<00:00, 151.14it/s]
Unable to measure energy consumption. Device must be a NVIDIA Jetson.

And from the CPU 3800x

Warming up with batch_size=1: 100%|██████████████████████████████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00, 27.85it/s]
Warning! No positional inputs found for a module, assuming batch size is 1.
Measurement of allocated memory is only available on CUDA devices
Warming up with batch_size=1: 100%|████████████████████████████████████████████████████████████████████████████████████████████████████████| 10/10 [00:00<00:00, 71.95it/s]
Measuring inference for batch_size=1: 100%|██████████████████████████████████████████████████████████████████████████████████████████████| 100/100 [00:01<00:00, 71.72it/s]
Unable to measure energy consumption. Device must be a NVIDIA Jetson.
Measurement of allocated memory is only available on CUDA devices
Warming up with batch_size=8: 100%|████████████████████████████████████████████████████████████████████████████████████████████████████████| 10/10 [00:00<00:00, 13.81it/s]
Measuring inference for batch_size=8: 100%|██████████████████████████████████████████████████████████████████████████████████████████████| 100/100 [00:07<00:00, 14.13it/s]
Unable to measure energy consumption. Device must be a NVIDIA Jetson.
@JiyongShi
Copy link

see test example
or print all result info:

print(results)

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