-
Notifications
You must be signed in to change notification settings - Fork 5.5k
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
Recognize digits model (tensorflow version) on TensorRT #8790
Comments
Update: I managed to get the Tensorflow model corresponding the I modified the sample Python examples are provided in the TensorRT container: https://devblogs.nvidia.com/tensorrt-container/ , to do the following:
I will put up the code somewhere (after figuring out the license/acknowledgement aspect, since i have modified the code which is classified as "commercial" by Nvidia). Meanwhile, below are the results:
The GPU that was used for profiling is a GeForce GTX 1080 Ti. |
Thanks. The running time increases as the batch size. It is a little strange. |
I think the reason for that is in the current benchmarking code, I have included time for memory allocation in the device and also the time taken to transfer the input array (from Python runtime) to device. |
@Xreki : I have updated the timings. (I basically removed the cudaMalloc and memcopy parts, and just timed the execution part). Now I think the values make more sense. |
So, do you compare Fluid with TensorRT and what is the results? |
In order to compare performance of the C++ inference framework with that of TensorRT (#8671), we need to get the tensorflow model of recognize digits running with TensorRT. (As of now we need to use Tensorflow's model, as we don't have a Fluid to TensorRT converter yet.)
The text was updated successfully, but these errors were encountered: