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

[Kaiju]

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.
Specifically,

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.

[ai_curious]

YOLO assignment exercise 1 shape question

Hello, For exercise 1 in the YOLO assignment, the tensor box_class_scores is of the shape (19,19,5) and the boolean mask filtering_mask is also of the shape (19,19,5). However, after doing scores = tf.boolean_mask(box_class_scores, filtering_mask), the output shape is (1789, ) and I’m not sure where this 1789 came from. I was expecting the shape to be (1805,) where 1805 = 19*19*5. I must missed something here and thank you in advance for helping out !

take a look and let us know what you think

[Kaiju]

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