HomeImplementationNeural NetworksBuilding a CNN model for Fashion MNIST dataset
Neural Networks

Building a CNN model for Fashion MNIST dataset

CEO 458 views 
import numpy as np
import tensorflow as tf
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense, Flatten, Conv2D, MaxPooling2D

import random
random.seed(1)
np.random.seed(1)
tf.random.set_seed(1)

(X_train, y_train), (X_test, y_test) = tf.keras.datasets.fashion_mnist.load_data()

# checking unique labels
np.unique(y_train)

# reshaping to one channel color
X_train = X_train.reshape(X_train.shape[0], 28, 28, 1)
X_test = X_test.reshape(X_test.shape[0], 28, 28, 1)

# normalizing 
X_train_normalized = X_train.astype('float32')/255.0
X_test_normalized = X_test.astype('float32')/255.0

#encoding label classes
y_train_encoded = tf.keras.utils.to_categorical(y_train)
y_test_encoded = tf.keras.utils.to_categorical(y_test)

#building CNN model
model = Sequential(
    [
        Conv2D(64, kernel_size=(3,3), input_shape=(28, 28, 1), activation='relu', padding='same'),
        MaxPooling2D(pool_size=(2, 2), padding='same'),
        Flatten(),
        Dense(100, activation='relu'),
        Dense(10, activation='softmax')
    ]
)

# checking trainable parameters
model.summary()

#compiling model
model.compile(optimizer='adam', loss='categorical_crossentropy', metrics=['accuracy'])

# fitting with 5 epochs
model.fit(X_train_normalized, y_train_encoded, epochs=5)

# checking training set accuracy
model.evaluate(X_train_normalized, y_train_encoded)

# checking test set accuracy
model.evaluate(X_test_normalized, y_test_encoded)

You Might Also Like