for row in open(dataset_path):
        <iterate over each row code here>

        # convert the data and labels to NumPy arrays
        data = np.array(data, dtype="float32")
        labels = np.array(labels, dtype="int")

        # return a 2-tuple of the A-Z data and labels
        return (data, labels)

    for row in open(dataset_path):
        <iterate over each row code here>


    # convert the data and labels to NumPy arrays
    data = np.array(data, dtype="float32")
    labels = np.array(labels, dtype="int")

    # return a 2-tuple of the A-Z data and labels
    return (data, labels)

python train_model.py --az A_Z_Handwritten_Data.csv --model trained_ocr.model

[INFO] evaluating network...
Traceback (most recent call last):
  File "C:\Users\achmiel\Downloads\How-did-I-write-an-own-OCR-program-using-Keras-and-TensorFlow-in-Python-master\How-did-I-write-an-own-OCR-program-using-Keras-and-TensorFlow-in-Python-master\train_model.py", line 113, in <module>
    print(classification_report(testY.argmax(axis=1),
  File "C:\Users\achmiel\Anaconda3\lib\site-packages\sklearn\utils\validation.py", line 63, in inner_f
    return f(*args, **kwargs)
  File "C:\Users\achmiel\Anaconda3\lib\site-packages\sklearn\metrics\_classification.py", line 1991, in classification_report
    raise ValueError(
ValueError: Number of classes, 11, does not match size of target_names, 36. Try specifying the labels parameter

# randomly select a few testing characters
for i in np.random.choice(np.arange(0, len(testY)), size=(49,)):
    # classify the character
    probs = model.predict(testX[np.newaxis, i])
prediction = probs.argmax(axis=1)
label = labelNames[prediction[0]]

# extract the image from the test data and initialize the text
# label color as green (correct)
image = (testX[i] * 255).astype("uint8")
color = (0, 255, 0)

# otherwise, the class label prediction is incorrect
if prediction[0] != np.argmax(testY[i]):
    color = (0, 0, 255)

# merge the channels into one image, resize the image from 32x32
# to 96x96 so we can better see it and then draw the predicted
# label on the image
image = cv2.merge([image] * 3)
image = cv2.resize(image, (96, 96), interpolation=cv2.INTER_LINEAR)
cv2.putText(image, label, (5, 20), cv2.FONT_HERSHEY_SIMPLEX, 0.75,
color, 2)

# add the image to our list of output images
images.append(image)

# randomly select a few testing characters
for i in np.random.choice(np.arange(0, len(testY)), size=(49,)):
    # classify the character
    probs = model.predict(testX[np.newaxis, i])
    prediction = probs.argmax(axis=1)
    label = labelNames[prediction[0]]
    
    # extract the image from the test data and initialize the text
    # label color as green (correct)
    image = (testX[i] * 255).astype("uint8")
    color = (0, 255, 0)
    
    # otherwise, the class label prediction is incorrect
    if prediction[0] != np.argmax(testY[i]):
        color = (0, 0, 255)
    
    # merge the channels into one image, resize the image from 32x32
    # to 96x96 so we can better see it and then draw the predicted
    # label on the image
    image = cv2.merge([image] * 3)
    image = cv2.resize(image, (96, 96), interpolation=cv2.INTER_LINEAR)
    cv2.putText(image, label, (5, 20), cv2.FONT_HERSHEY_SIMPLEX, 0.75,
    color, 2)
    
    # add the image to our list of output images
    images.append(image)