You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I have trained MobileNet-V3-large-1x classifier for 2 classes using openvino training extensions. While inferring the trained onnx model, I get the result as something similar to this vector [[-1.5802931e-10 1.1259661e-10]].
Can you please tell me what these 2 values represent?
How to post-process these values to get meaningful information i.e, class label and confidence score?
The text was updated successfully, but these errors were encountered:
The values might be the logits for each class, which could be transformed to class probability via softmax operation. Currently, direct inference of ONNX format is not supported on OTX.
You can try to parse label_schema.json along with the ONNX file to map output index to the label name. @sovrasov Could you help?
Hi! Indeed, OTX generates models that produce logits. I recommend ModelAPI as a default tool for inference: https://pypi.org/project/openvino-model-api/
It supports inference of ONNX models via OpenVINO or ONNXRuntime
Hi,
I have trained MobileNet-V3-large-1x classifier for 2 classes using openvino training extensions. While inferring the trained onnx model, I get the result as something similar to this vector [[-1.5802931e-10 1.1259661e-10]].
Can you please tell me what these 2 values represent?
How to post-process these values to get meaningful information i.e, class label and confidence score?
The text was updated successfully, but these errors were encountered: