Original by Margaret Maynard-Reid, 4/24/2018
Oringal Notebook: https://github.com/margaretmz/deep-learning/blob/master/fashion_mnist_keras.ipynb
In [1]:
import tensorflow as tf
import numpy as np
import matplotlib.pyplot as plt
# Load the fashion-mnist pre-shuffled train data and test data
(x_train, y_train), (x_test, y_test) = tf.keras.datasets.fashion_mnist.load_data()
print("x_train shape:", x_train.shape, "y_train shape:", y_train.shape)
In [2]:
# Print training set shape - note there are 60,000 training data of image size of 28x28, 60,000 train labels)
print("x_train shape:", x_train.shape, "y_train shape:", y_train.shape)
# Print the number of training and test datasets
print(x_train.shape[0], 'train set')
print(x_test.shape[0], 'test set')
# Define the text labels
fashion_mnist_labels = ["T-shirt/top", # index 0
"Trouser", # index 1
"Pullover", # index 2
"Dress", # index 3
"Coat", # index 4
"Sandal", # index 5
"Shirt", # index 6
"Sneaker", # index 7
"Bag", # index 8
"Ankle boot"] # index 9
# Image index, you can pick any number between 0 and 59,999
img_index = 5
# y_train contains the lables, ranging from 0 to 9
label_index = y_train[img_index]
# Print the label, for example 2 Pullover
print ("y = " + str(label_index) + " " +(fashion_mnist_labels[label_index]))
# # Show one of the images from the training dataset
plt.imshow(x_train[img_index])
Out[2]:
In [3]:
w, h = 28, 28
x_train = x_train.reshape(x_train.shape[0], w, h, 1)
x_test = x_test.reshape(x_test.shape[0], w, h, 1)
x_train.shape
Out[3]:
In [4]:
from tensorflow.keras.layers import Dense, Conv2D, MaxPooling2D, Dropout, Flatten
model = tf.keras.Sequential()
model.add(Conv2D(filters=64, kernel_size=2, padding='same', activation='relu', input_shape=(28,28,1)))
model.add(MaxPooling2D(pool_size=2))
model.add(Dropout(0.3))
model.add(Conv2D(filters=32, kernel_size=2, padding='same', activation='relu'))
model.add(MaxPooling2D(pool_size=2))
model.add(Dropout(0.3))
model.add(Flatten())
model.add(Dense(256, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(10, activation='softmax'))
model.summary()
In [5]:
BATCH_SIZE=1000
EPOCHS = 20
model.compile(loss='sparse_categorical_crossentropy',
optimizer='adam',
metrics=['accuracy'])
%time history = model.fit(x_train, y_train, epochs=EPOCHS, batch_size=BATCH_SIZE, validation_split=0.2, verbose=1)
In [6]:
train_loss, train_accuracy = model.evaluate(x_train, y_train, batch_size=BATCH_SIZE)
train_accuracy
Out[6]:
In [7]:
test_loss, test_accuracy = model.evaluate(x_test, y_test, batch_size=BATCH_SIZE)
test_accuracy
Out[7]:
In [8]:
import pandas as pd
def plot_history(history, samples=10, init_phase_samples=None):
epochs = history.params['epochs']
acc = history.history['acc']
val_acc = history.history['val_acc']
every_sample = int(epochs / samples)
acc = pd.DataFrame(acc).iloc[::every_sample, :]
val_acc = pd.DataFrame(val_acc).iloc[::every_sample, :]
fig, ax = plt.subplots(figsize=(20,5))
ax.plot(acc, 'bo', label='Training acc')
ax.plot(val_acc, 'b', label='Validation acc')
ax.set_title('Training and validation accuracy')
ax.legend()
plot_history(history)
In [12]:
y_hat = model.predict(x_test)
# Plot a random sample of 10 test images, their predicted labels and ground truth
figure = plt.figure(figsize=(20, 8))
for i, index in enumerate(np.random.choice(x_test.shape[0], size=15, replace=False)):
ax = figure.add_subplot(3, 5, i + 1, xticks=[], yticks=[])
# Display each image
ax.imshow(np.squeeze(x_test[index]))
predict_index = np.argmax(y_hat[index])
true_index = y_test[index]
# Set the title for each image
ax.set_title("{} ({})".format(fashion_mnist_labels[predict_index],
fashion_mnist_labels[true_index]),
color=("green" if predict_index == true_index else "red"))
In [ ]: