NonMaxSuppression spatial_dimension should be num_boxes?

[Timmmm]

It says

boxes : tensor(float)
An input tensor with shape [num_batches, spatial_dimension, 4].

And an example is:

boxes = np.array([[[0.0, 0.0, 1.0, 1.0],
                   [0.0, 0.1, 1.0, 1.1],
                   [0.0, -0.1, 1.0, 0.9],
                   [0.0, 10.0, 1.0, 11.0],
                   [0.0, 10.1, 1.0, 11.1],
                   [0.0, 100.0, 1.0, 101.0]],
                  [[0.0, 0.0, 1.0, 1.0],
                   [0.0, 0.1, 1.0, 1.1],
                   [0.0, -0.1, 1.0, 0.9],
                   [0.0, 10.0, 1.0, 11.0],
                   [0.0, 10.1, 1.0, 11.1],
                   [0.0, 100.0, 1.0, 101.0]]]).astype(np.float32)

So spatial_dimension is 6? It's pretty clear to me that the spatial dimension is hardcoded to 2 (i.e. boxes are 2D), and spatial_dimension should be renamed num_boxes. Perhaps the original intention was to allow 1D, 2D, and 3D boxes with dimensions [num_batches, num_boxes, spatial_dimension, 2]?

[stale]

Is this still relevant? If so, what is blocking it? Is there anything you can do to help move it forward?

This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs.