DirectML returning empty result with ObjectDetection (Mobilinet V2 FPN Keras) about tensorflow-onnx HOT 3 OPEN

Update: i did force the num_detections to 10 just to see what values I would get and surprising got good detection_boxes but bad detection_scores (-1 for all):

So investigating a little further i found out that the outputs detection_anchor_indices, detection_boxes, detection_classes, detection_multiclass_scores, raw_detection_boxes and even raw_detection_scores are returning correct values (DirectML outputs same as CPU), only the detection_scores and num_detections that are messed up.

from tensorflow-onnx.

Do you mean the model could be converted to ONNX model successfully and it works well on CPU but failed in other scenarios?

If so, this issue probably should be opened in onnxruntime repo because it looks like an inference issue.

from tensorflow-onnx.

Yes it does works well on CPU but fails in DirectML.
Thanks for the info, i did post it there.

from tensorflow-onnx.