-
Notifications
You must be signed in to change notification settings - Fork 6
animl 3.2.0 #224
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
base: main
Are you sure you want to change the base?
animl 3.2.0 #224
Conversation
222 miew onnx
add user_set for get_onnx_device, change get_device to get_torch_device
…ngle_classification convert none empty to empty df
matobler
left a comment
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.
Only two small commets realted to CPU ad ONNX
| providers = ['CUDAExecutionProvider', 'CPUExecutionProvider'] | ||
|
|
||
| # cuda not available | ||
| else: |
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.
For ONNX there is also a 'TensorrtExecutionProvider'.
https://github.com/ankane/onnxruntime-1/blob/master/docs/execution_providers/TensorRT-ExecutionProvider.md
I am not sure if that always goes with 'CUDAExecutionProvider'. If there is no 'CUDAExecutionProvider' and there is anything else besides 'CPUExecutionProvider' and the user specifices "cpu" the provider will return a list.
| providers = ort.get_available_providers() | ||
| print(providers) | ||
|
|
||
| providers = animl.get_onnx_device(user_set='cuda:0', quiet=True) |
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.
might want to do two tests, one on GPU and one on CPU.
232 onnx providers
…ation fix single_clasification to handle predictions_raw indexing correctly
No description provided.