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

Benchmark for image-based neural networks for inference framework #8671

Closed
1 of 4 tasks
sidgoyal78 opened this issue Mar 1, 2018 · 2 comments
Closed
1 of 4 tasks
Assignees
Labels
预测 原名Inference,包含Capi预测问题等

Comments

@sidgoyal78
Copy link
Contributor

sidgoyal78 commented Mar 1, 2018

TODO:

The main task is to benchmark inference API for image recognition models, using different batch sizes and run on either GPU and CPU. We want to do both a overall time and operator level timing benchmark.

@sidgoyal78 sidgoyal78 self-assigned this Mar 1, 2018
@sidgoyal78 sidgoyal78 added the 预测 原名Inference,包含Capi预测问题等 label Mar 1, 2018
@Xreki
Copy link
Contributor

Xreki commented Mar 5, 2018

We need to compare the performance with TensorRT. Do you test the inference time of TensorRT for the same model?

@sidgoyal78
Copy link
Contributor Author

It is still work in progress. I got a machine setup for running TensorRT today. I will have some results in the next 2 days.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
预测 原名Inference,包含Capi预测问题等
Projects
None yet
Development

No branches or pull requests

2 participants