problem about the bbox format

[LeeBC2298]

I need to feed my own data and I feed the data as the note under 'calculate_actual_outputs':

And my data is like this:
the prior boxes:

the ground truth boxes:

I think my data format is correct, but I got this error:

It seems that the 'pos_cond' should be shape [batch, num_of_anchers, 4], is this caused by my data format?

[LeeBC2298]

I tried to fix my problem like this:
_pos = tf.expand_dims(pos_cond, -1)
_pos = tf.concat([_pos, _pos, _pos, _pos], axis=-1)
expanded_gt_boxes = tf.where(_pos, gt_boxes_map, tf.zeros_like(gt_boxes_map))

This worked, but met another error at bbox_utils.get_deltas_from_bboxes, so I think it may be caused by my bbox format.

[FurkanOM]

Hi, which version of tensorflow are you using?

[LeeBC2298]

Hi, which version of tensorflow are you using?

I used tensorflow 1.15.0 and this error is probably caused by the version mismatch.
I found this warning:

and changed tf.where to np.where, it fixed the error.