how do I know the shape of output and what meaning for each dimension for my trained model?

[Ji__Alex]

From vehicle-detection-adas-binary-0001  I can know below information:

The net outputs a blob with the shape: [1, 1, N, 7], where N is the number of detected bounding boxes. For each detection, the description has the format: [image_id, label, conf, x_min, y_min, x_max, y_max]

So that I can compute the bounding boxes.

However, if I train my model from darknet yolo-v3-tiny, convert to .pb file, and then convert to IR files, how do I know the shape of output and what meaning for each dimension?

[Iffa_Intel]

Greetings,

You may refer to this tutorial:

https://www.youtube.com/watch?v=-8_yRzN-fTY

Sincerely,

Iffa

[Iffa_Intel]

Greetings,

Intel will no longer monitor this thread since we have provided a solution. If you need any additional information from Intel, please submit a new question. 

Sincerely,

Iffa