How do i create Confusion matrix of predicted and ground truth labels with Tensorflow?

Question

I have implemented a Nueral Network model for a classification with the help of using TensorFlow. But, i don\'t know how can i able to draw confusion matrix by using predic

Answer 1

If you want to produce a confusion matrix, and then later precision and recall, you first need to get your counts of true positives, true negatives, false positives and false negatives. Here is how:

For better readibility, I wrote the code very verbose.

def evaluation(logits,labels):
"Returns correct predictions, and 4 values needed for precision, recall and F1 score"


    # Step 1:
    # Let's create 2 vectors that will contain boolean values, and will describe our labels

    is_label_one = tf.cast(labels, dtype=tf.bool)
    is_label_zero = tf.logical_not(is_label_one)
    # Imagine that labels = [0,1]
    # Then
    # is_label_one = [False,True]
    # is_label_zero = [True,False]

    # Step 2:
    # get the prediction and false prediction vectors. correct_prediction is something that you choose within your model.
    correct_prediction = tf.nn.in_top_k(logits, labels, 1, name="correct_answers")
    false_prediction = tf.logical_not(correct_prediction)

    # Step 3:
    # get the 4 metrics by comparing boolean vectors
    # TRUE POSITIVES
    true_positives = tf.reduce_sum(tf.to_int32(tf.logical_and(correct_prediction,is_label_one)))

    # FALSE POSITIVES
    false_positives = tf.reduce_sum(tf.to_int32(tf.logical_and(false_prediction, is_label_zero)))

    # TRUE NEGATIVES
    true_negatives = tf.reduce_sum(tf.to_int32(tf.logical_and(correct_prediction, is_label_zero)))

    # FALSE NEGATIVES
    false_negatives = tf.reduce_sum(tf.to_int32(tf.logical_and(false_prediction, is_label_one)))


return true_positives, false_positives, true_negatives, false_negatives

# Now you can do something like this in your session:

true_positives, \
false_positives, \
true_negatives, \
false_negatives = sess.run(evaluation(logits,labels), feed_dict=feed_dict)

# you can print the confusion matrix using the 4 values from above, or get precision and recall:
precision = float(true_positives) / float(true_positives+false_positives)
recall = float(true_positives) / float(true_positives+false_negatives)

# or F1 score:
F1_score = 2 * ( precision * recall ) / ( precision+recall )