🍦 Keras + CNN + MNIST

import tensorflow.keras as keras
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense, Dropout, Flatten, Input
from tensorflow.keras.layers import Conv2D, MaxPooling2D

num_classes = 10
input_shape = (28, 28, 1)  # MNIST channels first format

# Build Sequential CNN model
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(128, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(num_classes, activation='softmax'))

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

# Display model architecture
model.summary()

from keras.datasets import mnist
import numpy as np

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

# Reshape: (60000, 28, 28) -> (60000, 28, 28, 1)
x_train = x_train.astype('float32') / 255.
x_test = x_test.astype('float32') / 255.
x_train = np.reshape(x_train, (len(x_train), 28, 28, 1))
x_test = np.reshape(x_test, (len(x_test), 28, 28, 1))

# Convert class vectors to binary class matrices (one-hot encoding)
y_train = keras.utils.to_categorical(y_train, num_classes)
y_test = keras.utils.to_categorical(y_test, num_classes)

import matplotlib.pyplot as plt

row = 10
col = 10
n = row * col

plt.figure(figsize=(4, 4))
for i in range(n):
    # Create subplot
    ax = plt.subplot(row, col, i + 1)
    plt.imshow(x_test[i].reshape(28, 28))
    plt.gray()
    ax.get_xaxis().set_visible(False)
    ax.get_yaxis().set_visible(False)

plt.show()

# Install and load TensorBoard
!pip install tensorboard
%load_ext tensorboard

import datetime, os

# Create logs directory
logs_base_dir = "./logs"
os.makedirs(logs_base_dir, exist_ok=True)

# Launch TensorBoard
%tensorboard --logdir {logs_base_dir}

from tensorflow.keras.callbacks import TensorBoard

batch_size = 128
epochs = 12

# Train model with TensorBoard callback
model.fit(
    x_train, y_train,
    epochs=epochs,
    batch_size=batch_size,
    shuffle=True,
    validation_data=(x_test, y_test),
    callbacks=[TensorBoard(log_dir=logs_base_dir)]
)

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

# Get single test image
x_test[0].shape
one_image = x_test[0].reshape(1, 28, 28, 1)

# Predict
y_pred_all = model.predict(one_image)
y_pred_it = model.predict_classes(one_image)
print(y_pred_all, y_pred_it)

# Display image
plt.imshow(x_test[0].reshape(28, 28))
plt.show()

model.save('/content/drive/My Drive/Colab Notebooks/my_cnn_mnist_model.h5')

from tensorflow.keras.models import load_model

new_model = load_model('/content/drive/My Drive/Colab Notebooks/my_cnn_mnist_model.h5')

from google.colab import drive
from PIL import Image
import numpy as np

# Mount Google Drive
drive.mount('/content/drive')

# Load custom image
img_path = '/content/drive/My Drive/Colab Notebooks/mnist_0_31.jpg'
img = Image.open(img_path)
img = np.resize(img, (28, 28, 1))
im2arr = np.array(img)
im2arr = im2arr.astype('float32') / 255.
im2arr = im2arr.reshape(1, 28, 28, 1)

# Predict
y_pred = new_model.predict_classes(im2arr)
print("Predicted digit:", y_pred)