Hello,
I’m getting this error: InvalidArgumentError: Incompatible shapes: [19,19,5,2] vs. [19,19,5,80] [Op:Mul] That is diffferent from the other cases. I appreciate your help
In Exercise 1 - yolo_filter_boxes, I added some print functions to help me solve . See below
boxes.shape = (19, 19, 5, 4)
box_scores.shape = (19, 19, 5, 80)
box_classses.shape = (19, 19, 5)
box_class_scores.shape = (19, 19, 5)
filtering_mask.shape = (19, 19, 5)
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,)
Here are the shapes that I see when I run the test cell for yolo_filter_boxes:
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!
Everything you show looks the same. But then where does that exception message come from? There is nothing we see that has shape [19,19,5,2]. So what variable is it that is triggering that exception?
Thanks Paul
Can I send you a direct message with a screen shot ?
Thanks,
Manny
Sure, that is a way to share code privately.
Paul,
I’m including a screen shot of the error
InvalidArgumentError Traceback (most recent call last)
in
5 tf.random.normal([19, 19, 5, 1], mean=1, stddev=4, seed = 1),
6 tf.random.normal([19, 19, 5, 80], mean=1, stddev=4, seed = 1))
----> 7 scores, boxes, classes = yolo_eval(yolo_outputs)
8 print("scores[2] = " + str(scores[2].numpy()))
9 print("boxes[2] = " + str(boxes[2].numpy()))
in yolo_eval(yolo_outputs, image_shape, max_boxes, score_threshold, iou_threshold)
33 # Use one of the functions you’ve implemented to perform Score-filtering with a threshold of score_threshold (≈1 line)
34
—> 35 scores, boxes, classes = yolo_filter_boxes(boxes, box_confidence, box_class_probs, score_threshold)
36
37 # Scale boxes back to original image shape.
in yolo_filter_boxes(boxes, box_confidence, box_class_probs, threshold)
25 ##(≈ 1 line)
26
—> 27 box_scores = box_confidence * box_class_probs
28
29 print("boxes.shape = " + str(boxes.shape))
/opt/conda/lib/python3.7/site-packages/tensorflow/python/ops/math_ops.py in binary_op_wrapper(x, y)
1123 with ops.name_scope(None, op_name, [x, y]) as name:
1124 try:
→ 1125 return func(x, y, name=name)
1126 except (TypeError, ValueError) as e:
1127 # Even if dispatching the op failed, the RHS may be a tensor aware
/opt/conda/lib/python3.7/site-packages/tensorflow/python/ops/math_ops.py in _mul_dispatch(x, y, name)
1455 return sparse_tensor.SparseTensor(y.indices, new_vals, y.dense_shape)
1456 else:
→ 1457 return multiply(x, y, name=name)
1458
1459
/opt/conda/lib/python3.7/site-packages/tensorflow/python/util/dispatch.py in wrapper(*args, **kwargs)
199 “”“Call target, and fall back on dispatchers if there is a TypeError.”“”
200 try:
→ 201 return target(*args, **kwargs)
202 except (TypeError, ValueError):
203 # Note: convert_to_eager_tensor currently raises a ValueError, not a
/opt/conda/lib/python3.7/site-packages/tensorflow/python/ops/math_ops.py in multiply(x, y, name)
507 “”"
508
→ 509 return gen_math_ops.mul(x, y, name)
510
511
/opt/conda/lib/python3.7/site-packages/tensorflow/python/ops/gen_math_ops.py in mul(x, y, name)
6164 return _result
6165 except _core._NotOkStatusException as e:
→ 6166 _ops.raise_from_not_ok_status(e, name)
6167 except _core._FallbackException:
6168 pass
/opt/conda/lib/python3.7/site-packages/tensorflow/python/framework/ops.py in raise_from_not_ok_status(e, name)
6841 message = e.message + (" name: " + name if name is not None else “”)
6842 # pylint: disable=protected-access
→ 6843 six.raise_from(core._status_to_exception(e.code, message), None)
6844 # pylint: enable=protected-access
6845
/opt/conda/lib/python3.7/site-packages/six.py in raise_from(value, from_value)
InvalidArgumentError: Incompatible shapes: [19,19,5,2] vs. [19,19,5,80] [Op:Mul]
Ok, well that answers my first question: which variable is wrong. It’s box_confidence. So how is that computed and why is it the wrong shape?
I added print statements in my yolo_eval code right before the call to yolo_filter_boxes and here’s what I see:
box_confidence.shape (19, 19, 5, 1)
box_class_probs.shape (19, 19, 5, 80)
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) = 1786
scores[2] = 171.60194
boxes[2] = [-1240.3483 -3212.5881 -645.78 2024.3052]
classes[2] = 16
scores.shape = (10,)
boxes.shape = (10, 4)
classes.shape = (10,)
All tests passed!
So why is your box_confidence the wrong shape? It’s just part of the input data to yolo_eval, right? Oh, wait, did you copy a solution off GitHub? If you did, you have to be super careful: they changed the definition of some of the APIs here in April 2021. If you copy a solution from before that, it doesn’t work. Of course it’s also cheating, so if that’s happened, then maybe you get what you deserved. 
Sorry if I’m jumping to the wrong conclusion here.
Thanks Paul,
My box_confidence.shape = (19, 19, 5, 1) same that yours (See print).
Same as yours box_confidence.shape (19, 19, 5, 1). Appreciate your help
Ok, well then why does that line above throw this exception:
You tell me. Maybe it’s time to just look at your code, but I’ll bet it’s that you copied a solution from the internet which is old and defines the data differently.
Please check your DMs for a message from me.