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
TensorRT Can't identify the cuda device #21487
Comments
@qinyao-he are you using tensorrt 4? The 1.9rc and 1.10 was built agains trt 3.0, so if you run with trt 4.0 there could be problem like this. |
It should print the loaded trt version before the first log message |
@aaroey I actually use TensorRT 4, and I indeed build from master myself. |
Well I just managed to reproduce the problem using your script. It turns out the error was caused by another problem: the device is not set in the engine and the converter will use default cuda malloc for memory allocation during the conversion. I'll fix it. As a work around, it should work if you add |
I use tensorrt 3.0.4, and came out with the error:
I have try to add
hopelessness ... |
I think this is because the device is not initialized when you call Actually I think this should be fixed in master by #20318. Could you also help to tried with master? Thanks. |
maybe you should upgrade your cuda driver version. |
System information
Ubuntu 16.04
source
('v1.9.0-rc2-1924-g054b046', '1.10.0-rc1'). Current master branch
First train the example small model use mnist.py.
Then use tensorflow built-in tools to freeze the graph:
Finally use tensorrt.py to optimize the graph use TensorRT engine.
Describe the problem
The log shows TensorRT could not find cuda devices. And the graph remains unchanged after the conversion.
Source code / logs
The text was updated successfully, but these errors were encountered: