Notes from learning about Keras Classification models.
pip install tensorflow_cpu==2.18.0
pip install matplotlib==3.9.2
import os
import keras
import matplotlib.pyplot as plt
from keras.models import Sequential
from keras.layers import Dense
from keras.layers import Input
from keras.utils import to_categorical
from keras.datasets import mnist
os.environ['TF_ENABLE_ONEDNN_OPTS'] = '0'
os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2'
# load the data
(X_train, y_train), (X_test, y_test) = mnist.load_data()
# see the shape - (60000, 28, 28)
X_train.shape
# this is what one image looks like
plt.imshow(X_train[0])
# flatten images into one-dimensional vector
num_pixels = X_train.shape[1] * X_train.shape[2] # find size of one-dimensional vector
X_train = X_train.reshape(X_train.shape[0], num_pixels).astype('float32') # flatten training images
X_test = X_test.reshape(X_test.shape[0], num_pixels).astype('float32') # flatten test images
# normalize inputs from 0-255 to 0-1
X_train = X_train / 255
X_test = X_test / 255
# one hot encode outputs
y_train = to_categorical(y_train)
y_test = to_categorical(y_test)
num_classes = y_test.shape[1]
print(num_classes)
# create the model
def classification_model():
model = Sequential()
model.add(Input(shape=(num_pixels,)))
model.add(Dense(num_pixels, activation='relu'))
model.add(Dense(100, activation='relu'))
model.add(Dense(num_classes, activation='softmax'))
model.compile(optimizer='adam', loss='categorical_crossentropy', metrics=['accuracy'])
return model
# create, fit, and run the model
model = classification_model()
model.fit(X_train, y_train, validation_data=(X_test, y_test), epochs=10, verbose=2)
scores = model.evaluate(X_test, y_test, verbose=0)
print('Accuracy: {}% \n Error: {}'.format(scores[1], 1 - scores[1]))
# save the model
model.save('classification_model.keras')
# load the model
pretrained_model = keras.saving.load_model('classification_model.keras')
