In [1]:
import numpy as np
import matplotlib.pyplot as plt
import matplotlib.cm as cm
import pandas as pd
import keras
from keras.models import Sequential
from keras.layers import Dense, Flatten
from tensorflow import set_random_seed
import tensorflow as tf
from sklearn.model_selection import train_test_split
from keras.datasets import fashion_mnist
Load the Fashion MNIST Data¶
The MNIST dataset consists of 70,000, 28x28 grayscale images split into 10 fashion categories. The categories are:
- 0 - T-shirt/top
- 1 - Trouser
- 2 - Pullover
- 3 - Dress
- 4 - Coat
- 5 - Sandal
- 6 - Shirt
- 7 - Sneaker
- 8 - Bag
- 9 - Ankle boot
In [2]:
(X_train, y_train), (X_holdout, y_holdout) = fashion_mnist.load_data()
In [3]:
X_val, X_test, y_val, y_test = train_test_split(X_holdout, y_holdout, test_size = 0.5, random_state=1)
print(X_train.shape)
print(y_train.shape)
print(X_test.shape)
print(y_test.shape)
print(X_val.shape)
print(y_val.shape)
Visualizing Samples¶
In [4]:
np.set_printoptions(linewidth=120)
n = np.random.choice(range(60000))
img = X_train[n]
print(img)
np.set_printoptions(linewidth=75)
In [5]:
#n = np.random.choice(range(60000))
img = X_train[n]
plt.imshow(img, cmap=cm.binary)
plt.axis('off')
plt.show()
Scale and the Reshape Feature Arrays¶
In [6]:
Xs_train = X_train.reshape(-1,28,28,1) / 255
Xs_test = X_test.reshape(-1,28,28,1) / 255
Xs_val = X_val.reshape(-1,28,28,1) / 255
Convolutional Neural Network¶
In [7]:
from keras.layers import Conv2D, MaxPooling2D
In [8]:
%%time
np.random.seed(1)
tf.set_random_seed(1)
model = Sequential()
model.add(Conv2D(32, (3, 3), padding='same', input_shape=(28,28,1), activation='relu'))
model.add(MaxPooling2D((2,2)))
model.add(Conv2D(64, (3, 3), activation='relu'))
model.add(MaxPooling2D((2,2)))
model.add(Conv2D(64, (3, 3), activation='relu'))
model.add(MaxPooling2D((2,2)))
model.add(Flatten())
model.add(Dense(64, activation='relu'))
model.add(Dense(10, activation='softmax'))
opt = keras.optimizers.Adam(lr=0.001)
model.compile(loss='sparse_categorical_crossentropy', optimizer=opt, metrics=['accuracy'])
model.summary()
h = model.fit(Xs_train.reshape(-1,28,28,1), y_train,
batch_size=256, epochs=20, verbose=1,
validation_data = (Xs_val.reshape(-1,28,28,1), y_val))
Plot Loss and Accuracy Curves¶
In [9]:
plt.rcParams["figure.figsize"] = [8,4]
plt.subplot(1,2,1)
plt.plot(h.history['loss'], label='Training')
plt.plot(h.history['val_loss'], label='Validation')
plt.title('model loss')
plt.ylabel('loss')
plt.xlabel('epoch')
plt.legend()
plt.subplot(1,2,2)
plt.plot(h.history['acc'], label='Training')
plt.plot(h.history['val_acc'], label='Validation')
plt.title('model accuracy')
plt.ylabel('accuracy')
plt.xlabel('epoch')
plt.legend()
plt.show()
Testing Performance¶
In [10]:
from sklearn.metrics import confusion_matrix, classification_report
In [11]:
testing_results = model.evaluate(Xs_test, y_test, verbose=0)
print('Test Loss = ', testing_results[0])
print('Test Accuracy =', testing_results[1])
In [12]:
y_pred = model.predict_classes(Xs_test)
confmat = confusion_matrix(y_test, y_pred)
df = pd.DataFrame(confmat)
df
Out[12]:
In [13]:
print(classification_report(y_test, y_pred))
View Misclassified Samples¶
In [14]:
import math
# Find misclassified samples in the test set.
sel = y_pred != y_test
n_mc = np.sum(sel) # number misclassified
X_mc = X_test[sel,:]
y_mc = y_test[sel]
yp_mc = y_pred[sel]
idx = np.argsort(y_mc)
X_mc = X_mc[idx,:]
y_mc = y_mc[idx]
yp_mc = yp_mc[idx]
rows = math.ceil(n_mc / 4)
plt.figure(figsize=(12,360))
for i in range(0, n_mc):
plt.subplot(rows,4,i+1)
plt.imshow(X_mc[i], cmap=cm.binary)
plt.text(-1, 10, s = str(int(y_mc[i])), fontsize=16, color='b')
plt.text(-1, 16, s = str(int(yp_mc[i])), fontsize=16, color='r')
plt.axis('off')
