Course 4 week 3 Assignment 1

Course Q&A Deep Learning Specialization Convolutional Neural Networks
1

I have a type error in my mask code that I can’t understand.
Some to guide me please !

ipython-input-15-14a23f211c10> in yolo_filter_boxes(boxes, box_confidence, box_class_probs, threshold)
35 # same dimension as box_class_scores, and be True for the boxes you want to keep (with probability >= threshold)
36 ## (≈ 1 line)
—> 37 filtering_mask = box_class_scores < threshold
38
39 # Step 4: Apply the mask to box_class_scores, boxes and box_classes

/opt/conda/lib/python3.7/site-packages/tensorflow/python/ops/gen_math_ops.py in less(x, y, name)
4909 _result = pywrap_tfe.TFE_Py_FastPathExecute(
4910 _ctx._context_handle, tld.device_name, “Less”, name, tld.op_callbacks,
→ 4911 x, y)
4912 return _result
4913 except _core._NotOkStatusException as e:

TypeError: Cannot convert 0.5 to EagerTensor of dtype int64

ID labo: spkvnyiwnnox

2

It sounds like your code must be confusing the box scores with the box classes. The scores should be floating point values, so how did they turn out to be integers?

I added a bunch of print statements to my code in that section and here’s the output I get when I run that test cell:

boxes.shape (19, 19, 5, 4)
boxes.dtype <dtype: 'float32'>
box_scores.shape (19, 19, 5, 80)
box_scores.dtype <dtype: 'float32'>
box_classes.shape (19, 19, 5)
box_classes.dtype <dtype: 'int64'>
box_class_scores.shape (19, 19, 5)
box_class_scores.dtype <dtype: 'float32'>
filtering_mask.shape (19, 19, 5)
filtering_mask.dtype <dtype: 'bool'>
sum(filtering_mask) = 1789
scores[2] = 9.270486
boxes[2] = [ 4.6399336  3.2303846  4.431282  -2.202031 ]
classes[2] = 8
scores.shape = (1789,)
boxes.shape = (1789, 4)
classes.shape = (1789,)
 All tests passed!
3

Yes yes thank you, I used box classes like arg in reduce_max.

Now, I passed the test