C4 W3 A1 yolo_eval

Course Q&A Deep Learning Specialization Convolutional Neural Networks
1

Hi,
I’m getting the following error when running the yolo_eval function. Does someone know how to solve this?

---------------------------------------------------------------------------
TypeError                                 Traceback (most recent call last)
<ipython-input-26-14e5cd22cb79> in <module>
      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()))

<ipython-input-25-a0575d2c92bd> in yolo_eval(yolo_outputs, image_shape, max_boxes, score_threshold, iou_threshold)
     31 
     32     # Use one of the functions you've implemented to perform Score-filtering with a threshold of score_threshold (≈1 line)
---> 33     scores, boxes, classes = yolo_non_max_suppression(boxes, box_confidence, box_class_probs, score_threshold)
     34 
     35     # Scale boxes back to original image shape.

<ipython-input-18-8f7110a2511a> in yolo_non_max_suppression(scores, boxes, classes, max_boxes, iou_threshold)
     22     """
     23 
---> 24     max_boxes_tensor = tf.Variable(max_boxes, dtype='int32')     # tensor to be used in tf.image.non_max_suppression()
     25 
     26     ### START CODE HERE

/opt/conda/lib/python3.7/site-packages/tensorflow/python/ops/variables.py in __call__(cls, *args, **kwargs)
    260       return cls._variable_v1_call(*args, **kwargs)
    261     elif cls is Variable:
--> 262       return cls._variable_v2_call(*args, **kwargs)
    263     else:
    264       return super(VariableMetaclass, cls).__call__(*args, **kwargs)

/opt/conda/lib/python3.7/site-packages/tensorflow/python/ops/variables.py in _variable_v2_call(cls, initial_value, trainable, validate_shape, caching_device, name, variable_def, dtype, import_scope, constraint, synchronization, aggregation, shape)
    254         synchronization=synchronization,
    255         aggregation=aggregation,
--> 256         shape=shape)
    257 
    258   def __call__(cls, *args, **kwargs):

/opt/conda/lib/python3.7/site-packages/tensorflow/python/ops/variables.py in <lambda>(**kws)
    235                         shape=None):
    236     """Call on Variable class. Useful to force the signature."""
--> 237     previous_getter = lambda **kws: default_variable_creator_v2(None, **kws)
    238     for _, getter in ops.get_default_graph()._variable_creator_stack:  # pylint: disable=protected-access
    239       previous_getter = _make_getter(getter, previous_getter)

/opt/conda/lib/python3.7/site-packages/tensorflow/python/ops/variable_scope.py in default_variable_creator_v2(next_creator, **kwargs)
   2644       synchronization=synchronization,
   2645       aggregation=aggregation,
-> 2646       shape=shape)
   2647 
   2648 

/opt/conda/lib/python3.7/site-packages/tensorflow/python/ops/variables.py in __call__(cls, *args, **kwargs)
    262       return cls._variable_v2_call(*args, **kwargs)
    263     else:
--> 264       return super(VariableMetaclass, cls).__call__(*args, **kwargs)
    265 
    266 

/opt/conda/lib/python3.7/site-packages/tensorflow/python/ops/resource_variable_ops.py in __init__(self, initial_value, trainable, collections, validate_shape, caching_device, name, dtype, variable_def, import_scope, constraint, distribute_strategy, synchronization, aggregation, shape)
   1516           aggregation=aggregation,
   1517           shape=shape,
-> 1518           distribute_strategy=distribute_strategy)
   1519 
   1520   def _init_from_args(self,

/opt/conda/lib/python3.7/site-packages/tensorflow/python/ops/resource_variable_ops.py in _init_from_args(self, initial_value, trainable, collections, caching_device, name, dtype, constraint, synchronization, aggregation, distribute_strategy, shape)
   1650             initial_value = ops.convert_to_tensor(
   1651                 initial_value() if init_from_fn else initial_value,
-> 1652                 name="initial_value", dtype=dtype)
   1653           if shape is not None:
   1654             if not initial_value.shape.is_compatible_with(shape):

/opt/conda/lib/python3.7/site-packages/tensorflow/python/framework/ops.py in convert_to_tensor(value, dtype, name, as_ref, preferred_dtype, dtype_hint, ctx, accepted_result_types)
   1497 
   1498     if ret is None:
-> 1499       ret = conversion_func(value, dtype=dtype, name=name, as_ref=as_ref)
   1500 
   1501     if ret is NotImplemented:

/opt/conda/lib/python3.7/site-packages/tensorflow/python/framework/tensor_conversion_registry.py in _default_conversion_function(***failed resolving arguments***)
     50 def _default_conversion_function(value, dtype, name, as_ref):
     51   del as_ref  # Unused.
---> 52   return constant_op.constant(value, dtype, name=name)
     53 
     54 

/opt/conda/lib/python3.7/site-packages/tensorflow/python/framework/constant_op.py in constant(value, dtype, shape, name)
    262   """
    263   return _constant_impl(value, dtype, shape, name, verify_shape=False,
--> 264                         allow_broadcast=True)
    265 
    266 

/opt/conda/lib/python3.7/site-packages/tensorflow/python/framework/constant_op.py in _constant_impl(value, dtype, shape, name, verify_shape, allow_broadcast)
    273       with trace.Trace("tf.constant"):
    274         return _constant_eager_impl(ctx, value, dtype, shape, verify_shape)
--> 275     return _constant_eager_impl(ctx, value, dtype, shape, verify_shape)
    276 
    277   g = ops.get_default_graph()

/opt/conda/lib/python3.7/site-packages/tensorflow/python/framework/constant_op.py in _constant_eager_impl(ctx, value, dtype, shape, verify_shape)
    298 def _constant_eager_impl(ctx, value, dtype, shape, verify_shape):
    299   """Implementation of eager constant."""
--> 300   t = convert_to_eager_tensor(value, ctx, dtype)
    301   if shape is None:
    302     return t

/opt/conda/lib/python3.7/site-packages/tensorflow/python/framework/constant_op.py in convert_to_eager_tensor(value, ctx, dtype)
     96       dtype = dtypes.as_dtype(dtype).as_datatype_enum
     97   ctx.ensure_initialized()
---> 98   return ops.EagerTensor(value, ctx.device_name, dtype)
     99 
    100 

TypeError: Cannot convert 0.6 to EagerTensor of dtype int32
2

It looks like the arguments you are passing to yolo_non_max_suppression do not match the definition of that function. Also note that in my implementation of yolo_non_max_suppression, I do not have a line like the one that “throws” in your exception case. The core of the logic in that function in my case just invokes the TF function tf.image.non_max_suppression, which was discussed in the instructions for that section.

3

In yolo_eval(), you are using the wrong arguments when you call yolo_non_max_suppression(). It looks like you copied the arguments you’re using for yolo_filter_boxes(). That’s incorrect.

4

Hi everyone.
I am facing an ‘unmatching shape’ error with the yolo_eval() function. The error basically says :
“InvalidArgumentError: Incompatible shapes: [1786,3] vs. [1,4] [Op:Mul]”,
and the traceback at some point refers back to the line of code that rescales the boxes to fit the test set image shape. It seems like the problem is that the shape of the variable ‘boxes’ doesn’t match that of ‘image_dims’ used in the implementation of the ‘scale_boxes()’ function. I have checked the code multiple times but I don’t really see where this could come from.
I am also trying to get a fresh copy of the notebook (in case I might accidentally have modified some of the code I shouldn’t). I tried clicking on the ‘instructions’ link at the top in the notebook but this simply leads to the week 3 course overview page.
Thank you very much for any help or directions.

yolo_eval_error_capture
yolo_eval_error_capture1322×391 44.3 KB

5

Here’s a thread about how to get a fresh copy of any course notebook.

I added lots of print statements to my code. Here’s what I get when I run the test cell for yolo_eval:

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
boxes.shape (1786, 4) before scale_boxes
image_shape (720, 1280)
boxes.shape (1786, 4) after scale_boxes
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!

Your outputs must be different based on the error message. It looks like perhaps the second dimension of boxes is 3 instead of 4 in your case, if I’m interpreting your output correctly. That would be a problem if I’m reading that right. :scream_cat:

6

Hello @paulinpaloalto. I was able to get a fresh copy of the notebook by following the link you provided. I confirm that your interpretation is correct!! I accidentally erased a line and the 2nd dimension of boxes got changed to 3.
Thank you very much ! :pray:t5

2 Likes