Unrecognized sequence type in KNearestNeighbors

## 🐞Describe the bug
I am trying to test a KNearestNeighbors classifier. The classifier is made using `KNearestNeighborsClassifierBuilder`. When I load and test the `mlmodel` file, I encounter the error "RuntimeError: Error: Unrecognized sequence type."

## Trace

```
---------------------------------------------------------------------------
RuntimeError Traceback (most recent call last)
in
1 test_input = np.random.rand(20)
----> 2 model.predict({'my_in': test_input})

~/opt/anaconda3/lib/python3.7/site-packages/coremltools/models/model.py in predict(self, data, useCPUOnly, **kwargs)
326
327 if self.__proxy__:
--> 328 return self.__proxy__.predict(data, useCPUOnly)
329 else:
330 if _macos_version() < (10, 13):

RuntimeError: Error: Unrecognized sequence type.
```

## To Reproduce

Here is a minimal example: first create the classifier:
```
from coremltools.models.nearest_neighbors import KNearestNeighborsClassifierBuilder
from coremltools.models.utils import save_spec

my_inputs = np.random.rand(10,20)
my_outputs = (5* np.random.rand(10)).astype(int)

builder = KNearestNeighborsClassifierBuilder(
input_name='my_in',
output_name='my_out',
number_of_dimensions=my_inputs.shape[1],
default_class_label=0,
number_of_neighbors=20
)

save_spec(builder.spec, "test.mlmodel")
```

Then load and test it:
```
model = coremltools.models.MLModel('test.mlmodel')
test_input = np.random.rand(20)
model.predict({'my_in': test_input}) # Here the error is thrown
```

## System environment (please complete the following information):
- coremltools version 4.1
- MacOS 11.4
- python anaconda 3.7.4
- Run over `jupyter-lab` v. 1.1.4

## Related

[Related #898](https://github.com/apple/coremltools/issues/898) was closed but no explanation.

Start with KNearestNeighborsClassifierBuilder and the MLModel.predict path shown in the reproduction, focusing on how the 20-element NumPy input is interpreted. Re-run the minimal example from the issue and trace the sequence-type handling. Done means the generated test.mlmodel loads and predicts with the provided input without raising "Unrecognized sequence type."

Written by the indexing model from the issue text.