Not able to detect faces using predict.py

[akj2784]

I have used 124 images of a kid with wide varieties of photo covering the age group of 1-5 years), did encoding and then trained it and then ran the predict.py file.

�[6;30;42m=====Predicting faces in './test-images\DSC_0010.JPG'=====�[0m
X_faces_loc []
faces_encodings []
Found 0 faces in the image
Traceback (most recent call last):
File "predict.py", line 50, in
closest_distances = clf.kneighbors(faces_encodings, n_neighbors=1)
File "C:\Users\Akash Jain\AppData\Roaming\Python\Python36\site-packages\sklearn\neighbors\base.py", line 403, in kneighbors
X = check_array(X, accept_sparse='csr')
File "C:\Users\Akash Jain\AppData\Roaming\Python\Python36\site-packages\sklearn\utils\validation.py", line 552, in check_array
"if it contains a single sample.".format(array))
ValueError: Expected 2D array, got 1D array instead:
array=[].
Reshape your data either using array.reshape(-1, 1) if your data has a single feature or array.reshape(1, -1) if it contains a single sample.

What could be the reason ? I have tried with 5-6 sample images with very clear face but still it doesn't detect. Am I missing something ? Does it need more data to train ? ALso even if it doesnt detect face ideally it should not throw up error.