Confusion Matrix in transfer learning with keras

I was going to draw confusion matrix in my model and I used Transfer learning concept based on Deep Learning model.

Confusion Matrix’s code

def plot_confusion_matrix(cm, classes, normalize=False,title='Confusion Matrix', cmap=plt.cm.Blues):
  plt.imshow(cm, interpolation='nearest', cmap=cmap)
  plt.title(title)
  plt.colorbar()
  tick_marks = np.arange(len(classes))
  plt.xticks(tick_marks, classes, rotation=45)
  plt.yticks(tick_marks, classes)

  if normalize:
    cm=cm.astype('float') / cm.sum(axis=1)[:, np.newaxis]
    print("Normalized Confusion Matrix")
  else:
    print("Confusion matrix, without normalization")
  print(cm)

  thresh = cm.max() / 2
  for i, j in itertools.product(range(cm.shape[0]),range(cm.shape[1])):
    plt.text(j, i, cm[i, j],
             horizontalalignment="center",
             color="white" if cm[i,j] > thresh else "black")
  plt.tight_layout()
  plt.ylabel('True Label')
  plt.xlabel('Predicted Label')

Now below the shape of test_labels and Predictions are given,

test_labels.shape
(12,)
predictions.shape
(10,2)

The above code is perfectly working but I saw error in below. So please concern below code,

cm = confusion_matrix(test_labels, predictions.argmax(axis=1))

and here is the error,

ValueError                                Traceback (most recent call last)
<ipython-input-40-79fd4e2e074c> in <module>()
----> 1 cm = confusion_matrix(test_labels, predictions.argmax(axis=1))

2 frames
/usr/local/lib/python3.6/dist-packages/sklearn/utils/validation.py in check_consistent_length(*arrays)
    210     if len(uniques) > 1:
    211         raise ValueError("Found input variables with inconsistent numbers of"
--> 212                          " samples: %r" % [int(l) for l in lengths])
    213 
    214 

ValueError: Found input variables with inconsistent numbers of samples: [12, 10]
  

Note: This is value error and I am confused about it I try more and more but I failed. So I need help to solve this error.

Answer

As the error suggests, you have different sample sizes for test_labels and predictions. This may happen when you use batches for prediction which may result in dropping of the last few samples.

One possibility is, you can use:

cm = confusion_matrix(test_labels[:-2], predictions.argmax(axis=1))

This may solve the shape mismatch problem (But it is based on the assumption that the last two samples are missing in prediction).

I may be able to provide a more useful answer if you can share the code used for prediction.