Car detection with YOLO: mask operation and dimensions in yolo_filter_boxes function

Hi I was able to complete teh yolo_filter_boxes function, but still not clear about the output dimensions after step 4 Step 4: Apply the mask to box_class_scores, boxes and box_classes

Having read the tf documentation, did not find information there.

  1. we take box_class_scores with a dimension (19, 19, 5) apply the mask with a shape (19, 19, 5) and get scores tensor with a shape (1789,). How did we get the number 1789
  2. similary for " classes" with a shape (1789,), we took box_classes shape (19, 19, 5) and applied the mask mask with a shape (19, 19, 5). How did we get a shape of 1789? how did we unroll the 3d tensor to a shape of 1789?
  3. for boxes of shape (1789, 4) we tool boxes with a shape (19,19,5,4) and applied the mask mask with a shape (19, 19, 5).

Grateful if somebody helps explain the mechanics of what we did in the last step.

take a look and let us know what you think

clearer now. posted a follow up question on the thread referenced above