Deep Learning Project – Handwritten Digit Recognition using Python

Python Deep Learning Project

To make machines more intelligent, the developers are diving into machine learning and deep learning techniques. A human learns to perform a task by practicing and repeating it again and again so that it memorizes how to perform the tasks. Then the neurons in his brain automatically trigger and they can quickly perform the task they have learned. Deep learning is also very similar to this. It uses different types of neural network architectures for different types of problems. For example – object recognition, image and sound classification, object detection, image segmentation, etc.

This is the 11th project in the DataFlair’s series of 20 Python projects. I suggest you to bookmark the previous projects:

  1. Fake News Detection Python Project 
  2. Parkinson’s Disease Detection Python Project 
  3. Color Detection Python Project
  4. Speech Emotion Recognition Python Project 
  5. Breast Cancer Classification Python Project
  6. Age and Gender Detection Python Project 
  7. Handwritten Digit Recognition Python Project
  8. Chatbot Python Project
  9. Driver Drowsiness Detection Python Project
  10. Traffic Signs Recognition Python Project
  11. Image Caption Generator Python Project

Keeping you updated with latest technology trends, Join DataFlair on Telegram

What is Handwritten Digit Recognition?

The handwritten digit recognition is the ability of computers to recognize human handwritten digits. It is a hard task for the machine because handwritten digits are not perfect and can be made with many different flavors. The handwritten digit recognition is the solution to this problem which uses the image of a digit and recognizes the digit present in the image.

About the Python Deep Learning Project

python deep learning project - handwritten digit recognition

In this article, we are going to implement a handwritten digit recognition app using the MNIST dataset. We will be using a special type of deep neural network that is Convolutional Neural Networks. In the end, we are going to build a GUI in which you can draw the digit and recognize it straight away.

Prerequisites

The interesting Python project requires you to have basic knowledge of Python programming, deep learning with Keras library and the Tkinter library for building GUI.

Install the necessary libraries for this project using this command:

pip install numpy, tensorflow, keras, pillow,

The MNIST dataset

This is probably one of the most popular datasets among machine learning and deep learning enthusiasts. The MNIST dataset contains 60,000 training images of handwritten digits from zero to nine and 10,000 images for testing. So, the MNIST dataset has 10 different classes. The handwritten digits images are represented as a 28×28 matrix where each cell contains grayscale pixel value.

Download the full source code for the project

Building Python Deep Learning Project on Handwritten Digit Recognition

Below are the steps to implement the handwritten digit recognition project:

1. Import the libraries and load the dataset

First, we are going to import all the modules that we are going to need for training our model. The Keras library already contains some datasets and MNIST is one of them. So we can easily import the dataset and start working with it. The mnist.load_data() method returns us the training data, its labels and also the testing data and its labels.

import keras
from keras.datasets import mnist
from keras.models import Sequential
from keras.layers import Dense, Dropout, Flatten
from keras.layers import Conv2D, MaxPooling2D
from keras import backend as K

# the data, split between train and test sets
(x_train, y_train), (x_test, y_test) = mnist.load_data()

print(x_train.shape, y_train.shape)

2. Preprocess the data

The image data cannot be fed directly into the model so we need to perform some operations and process the data to make it ready for our neural network. The dimension of the training data is (60000,28,28). The CNN model will require one more dimension so we reshape the matrix to shape (60000,28,28,1).

x_train = x_train.reshape(x_train.shape[0], 28, 28, 1)
x_test = x_test.reshape(x_test.shape[0], 28, 28, 1)
input_shape = (28, 28, 1)

# convert class vectors to binary class matrices
y_train = keras.utils.to_categorical(y_train, num_classes)
y_test = keras.utils.to_categorical(y_test, num_classes)

x_train = x_train.astype('float32')
x_test = x_test.astype('float32')
x_train /= 255
x_test /= 255
print('x_train shape:', x_train.shape)
print(x_train.shape[0], 'train samples')
print(x_test.shape[0], 'test samples')

3. Create the model

Now we will create our CNN model in Python data science project. A CNN model generally consists of convolutional and pooling layers. It works better for data that are represented as grid structures, this is the reason why CNN works well for image classification problems. The dropout layer is used to deactivate some of the neurons and while training, it reduces offer fitting of the model. We will then compile the model with the Adadelta optimizer.

batch_size = 128
num_classes = 10
epochs = 10

model = Sequential()
model.add(Conv2D(32, kernel_size=(3, 3),activation='relu',input_shape=input_shape))
model.add(Conv2D(64, (3, 3), activation='relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.25))
model.add(Flatten())
model.add(Dense(256, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(num_classes, activation='softmax'))

model.compile(loss=keras.losses.categorical_crossentropy,optimizer=keras.optimizers.Adadelta(),metrics=['accuracy'])

4. Train the model

The model.fit() function of Keras will start the training of the model. It takes the training data, validation data, epochs, and batch size.

It takes some time to train the model. After training, we save the weights and model definition in the ‘mnist.h5’ file.

hist = model.fit(x_train, y_train,batch_size=batch_size,epochs=epochs,verbose=1,validation_data=(x_test, y_test))
print("The model has successfully trained")

model.save('mnist.h5')
print("Saving the model as mnist.h5")

5. Evaluate the model

We have 10,000 images in our dataset which will be used to evaluate how good our model works. The testing data was not involved in the training of the data therefore, it is new data for our model. The MNIST dataset is well balanced so we can get around 99% accuracy.

score = model.evaluate(x_test, y_test, verbose=0)
print('Test loss:', score[0])
print('Test accuracy:', score[1])

6. Create GUI to predict digits

Now for the GUI, we have created a new file in which we build an interactive window to draw digits on canvas and with a button, we can recognize the digit. The Tkinter library comes in the Python standard library. We have created a function predict_digit() that takes the image as input and then uses the trained model to predict the digit.

Then we create the App class which is responsible for building the GUI for our app. We create a canvas where we can draw by capturing the mouse event and with a button, we trigger the predict_digit() function and display the results.

Here’s the full code for our gui_digit_recognizer.py file:

from keras.models import load_model
from tkinter import *
import tkinter as tk
import win32gui
from PIL import ImageGrab, Image
import numpy as np

model = load_model('mnist.h5')

def predict_digit(img):
    #resize image to 28x28 pixels
    img = img.resize((28,28))
    #convert rgb to grayscale
    img = img.convert('L')
    img = np.array(img)
    #reshaping to support our model input and normalizing
    img = img.reshape(1,28,28,1)
    img = img/255.0
    #predicting the class
    res = model.predict([img])[0]
    return np.argmax(res), max(res)

class App(tk.Tk):
    def __init__(self):
        tk.Tk.__init__(self)

        self.x = self.y = 0

        # Creating elements
        self.canvas = tk.Canvas(self, width=300, height=300, bg = "white", cursor="cross")
        self.label = tk.Label(self, text="Thinking..", font=("Helvetica", 48))
        self.classify_btn = tk.Button(self, text = "Recognise", command =         self.classify_handwriting) 
        self.button_clear = tk.Button(self, text = "Clear", command = self.clear_all)

        # Grid structure
        self.canvas.grid(row=0, column=0, pady=2, sticky=W, )
        self.label.grid(row=0, column=1,pady=2, padx=2)
        self.classify_btn.grid(row=1, column=1, pady=2, padx=2)
        self.button_clear.grid(row=1, column=0, pady=2)

        #self.canvas.bind("<Motion>", self.start_pos)
        self.canvas.bind("<B1-Motion>", self.draw_lines)

    def clear_all(self):
        self.canvas.delete("all")

    def classify_handwriting(self):
        HWND = self.canvas.winfo_id() # get the handle of the canvas
        rect = win32gui.GetWindowRect(HWND) # get the coordinate of the canvas
        im = ImageGrab.grab(rect)

        digit, acc = predict_digit(im)
        self.label.configure(text= str(digit)+', '+ str(int(acc*100))+'%')

    def draw_lines(self, event):
        self.x = event.x
        self.y = event.y
        r=8
        self.canvas.create_oval(self.x-r, self.y-r, self.x + r, self.y + r, fill='black')

app = App()
mainloop()

Screenshots:

python machine learning project output as number 2

python machine learning project output as number 5

Python Interview Questions

python project output as number 6

Summary

In this article, we have successfully built a Python deep learning project on handwritten digit recognition app. We have built and trained the Convolutional neural network which is very effective for image classification purposes. Later on, we build the GUI where we draw a digit on the canvas then we classify the digit and show the results.

Want to get hired as a Python expert? Practice the 150+ Python Interview Questions by DataFlair

Do share your views regarding the intermediate Python project in the comment section.

20 Responses

  1. Srikanth Pusa says:

    Hi

    I have tried working.
    But prediction values is not working as expected. None of the result is as expected.

    • DataFlair Team says:

      Hey Srikanth Pusa,

      It is hard to interpret the cause of this issue as there can be any number of factors. You can try changing the hyperparameters and train the model yourself. Look at the testing and validation accuracy graph to see how your model works.

  2. Kingo says:

    Hi,
    I am getting the error that ModuleNotFoundError: No module named ‘win32gui’
    even after installing win32gui in my PC any help.?

    • DataFlair Team says:

      Hey Kingo,

      We are here to help!!

      Make sure the module is installed at the proper place. You should use python3 and install the package using pip install win32gui command.

  3. Mukund says:

    i am getting an error num_classes is not defined

  4. BHARAT SINGH says:

    Hey,
    i have tried on spyder, but the thing is,
    few imports are as useused throws error.
    Help if possible

  5. Srijan says:

    Hey Can you please tell me how do i train the model.
    Running just the gui_digit_recognizer.py is not giving a good result.
    I need to train it first I guess but i am not sure how to do that

  6. Rahul says:

    How can i run this project in Linux

  7. Rishabh Jain says:

    I tried this but I am getting some errors:

    Traceback (most recent call last):
    File “C:\Python36\gui_digit_recognizer.py”, line 1, in
    from keras.models import load_model
    File “C:\Python36\lib\site-packages\keras\__init__.py”, line 3, in
    from . import activations
    File “C:\Python36\lib\site-packages\keras\activations.py”, line 3, in
    from . import backend as K
    File “C:\Python36\lib\site-packages\keras\backend\__init__.py”, line 64, in
    from .tensorflow_backend import *
    File “C:\Python36\lib\site-packages\keras\backend\tensorflow_backend.py”, line 1, in
    import tensorflow as tf
    File “C:\Python36\lib\site-packages\tensorflow\__init__.py”, line 24, in
    from tensorflow.python import pywrap_tensorflow # pylint: disable=unused-import
    File “C:\Python36\lib\site-packages\tensorflow\python\__init__.py”, line 52, in
    from tensorflow.core.framework.graph_pb2 import *
    File “C:\Python36\lib\site-packages\tensorflow\core\framework\graph_pb2.py”, line 6, in
    from google.protobuf import descriptor as _descriptor
    File “C:\Python36\lib\site-packages\google\protobuf\descriptor.py”, line 47, in
    from google.protobuf.pyext import _message
    ImportError: DLL load failed: The specified procedure could not be found.

    Please help me

  8. Julian Darley says:

    the training code runs correctly (on a win10 box with GTX1080) until line 47, at which point i get:

    Traceback (most recent call last):
    File “train_digit_recognizer.py”, line 47, in
    hist = model.fit(x_train, y_train,batch_size=batch_size,epochs=epochs,verbose=1,validation_data=(x_test, y_test))
    File “A:\TRAINING COURSES IN USE\PYTHON\Handwritten-Digit-Recognition\lib\site-packages\keras\engine\training.py”, line 1239, in fit
    validation_freq=validation_freq)
    File “A:\TRAINING COURSES IN USE\PYTHON\Handwritten-Digit-Recognition\lib\site-packages\keras\engine\training_arrays.py”, line 196, in fit_loop
    outs = fit_function(ins_batch)
    File “A:\TRAINING COURSES IN USE\PYTHON\Handwritten-Digit-Recognition\lib\site-packages\tensorflow_core\python\keras\backend.py”, line 3727, in __call__
    outputs = self._graph_fn(*converted_inputs)
    File “A:\TRAINING COURSES IN USE\PYTHON\Handwritten-Digit-Recognition\lib\site-packages\tensorflow_core\python\eager\function.py”, line 1551, in __call__
    return self._call_impl(args, kwargs)
    File “A:\TRAINING COURSES IN USE\PYTHON\Handwritten-Digit-Recognition\lib\site-packages\tensorflow_core\python\eager\function.py”, line 1591, in _call_impl
    return self._call_flat(args, self.captured_inputs, cancellation_manager)
    File “A:\TRAINING COURSES IN USE\PYTHON\Handwritten-Digit-Recognition\lib\site-packages\tensorflow_core\python\eager\function.py”, line 1692, in _call_flat
    ctx, args, cancellation_manager=cancellation_manager))
    File “A:\TRAINING COURSES IN USE\PYTHON\Handwritten-Digit-Recognition\lib\site-packages\tensorflow_core\python\eager\function.py”, line 545, in call
    ctx=ctx)
    File “A:\TRAINING COURSES IN USE\PYTHON\Handwritten-Digit-Recognition\lib\site-packages\tensorflow_core\python\eager\execute.py”, line 67, in quick_execute
    six.raise_from(core._status_to_exception(e.code, message), None)
    File “”, line 3, in raise_from
    tensorflow.python.framework.errors_impl.UnknownError: Failed to get convolution algorithm. This is probably because cuDNN failed to initialize, so try looking to see if a warning log message was printed above.
    [[node conv2d_1/convolution (defined at A:\TRAINING COURSES IN USE\PYTHON\Handwritten-Digit-Recognition\lib\site-packages\keras\backend\tensorflow_backend.py:3009) ]] [Op:__inference_keras_scratch_graph_1536]

    i have searched the web for solutions, nothing i have seen really addresses the issue. any help gratefully received.

  9. Julian Darley says:

    using pycharm and carefully installing and updating all the appropriate libraries, i have now got everything working. the only problem is that actual recognition success rate is much less than 10%. it is more or less hopeless – a random guessing machine would give better results! i have tried it both with the given mnist.h5 file and my own training and the results are equally bad. of course i can try changing the hyperparameters, but so far the results are very disappointing.
    i will try to create my own data library to train it on so that it recognises my handwriting, which is for me and all other private users surely the most useful thing.

  10. Praphull says:

    Can you tell me how to solve avx avx2 problem

  11. sachin says:

    can you tell me the python and tensorflow version that you used in this project because i am getting error after many tries.

  12. Anonymous says:

    hey when i run this,and draw any digit ,it predict wrong digit.

  13. Mohammad Yahiya Khan says:

    Can I have a mentor or an advisor please for this project
    I am a beginner in coding world

  14. Sri says:

    I am trying to run this code on a Mac. I Understand that win32 is a windows thing and that does not work for Mac. I would greatly appreciate it. if you could explain or provide an alternative.

    From what I can tell only these lines are affected:

    HWND = self.canvas.winfo_id() # get the handle of the canvas
    rect = win32gui.GetWindowRect(HWND) # get the coordinate of the canvas || Does not work as win32 gui module not available for Mac
    im = ImageGrab.grab(rect)

  15. Akash Dhiman says:

    Error when checking target: expected dense_8 to have 2 dimensions, but got array with shape (60000, 10, 10)

  16. kailash somani says:

    how and where save mnist.h5 file

  17. kailash somani says:

    first install python 3.5 64 bit then run pip install tensorflow it will get appropriate version automatically
    tensorflow runs only on 64 bit python

Leave a Reply

Your email address will not be published. Required fields are marked *

This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.