-
Notifications
You must be signed in to change notification settings - Fork 561
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
Integration of Libtorch in DeepDetect for image classification #611
Conversation
|
||
_device = gpu ? torch::Device("cuda") : torch::Device("cpu"); | ||
|
||
_traced = torch::jit::load(this->_mlmodel._model_file); |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
This code only works for traced model, right ?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Yes, only traced models are currently supported.
FYI, a build on a CPU only machine with
However, the build works with I believe that if there's no CUDA automatically detected, USE_CPU_ONLY should be forced ON automatically. |
I get this error when starting dede:
|
Fixed everything mentioned above, except the libiomp loading error. |
Script to trace resnet and other models. Requirements:
|
<!> A segfault may occur when running a model with CUDA |
@BynaryCobweb Confirmed that the final linking is fixed on CPU builds! |
Example: Image classification
|
|
Building instructions: