mhjensen
142 lines
4.3 KiB
Python
142 lines
4.3 KiB
Python
# import necessary packages
|
|
import numpy as np
|
|
import matplotlib.pyplot as plt
|
|
from sklearn import datasets
|
|
|
|
|
|
# ensure the same random numbers appear every time
|
|
np.random.seed(0)
|
|
|
|
# display images in notebook
|
|
plt.rcParams['figure.figsize'] = (12,12)
|
|
|
|
|
|
# download MNIST dataset
|
|
digits = datasets.load_digits()
|
|
|
|
# define inputs and labels
|
|
inputs = digits.images
|
|
labels = digits.target
|
|
|
|
# RGB images have a depth of 3
|
|
# our images are grayscale so they should have a depth of 1
|
|
inputs = inputs[:,:,:,np.newaxis]
|
|
|
|
print("inputs = (n_inputs, pixel_width, pixel_height, depth) = " + str(inputs.shape))
|
|
print("labels = (n_inputs) = " + str(labels.shape))
|
|
|
|
|
|
# choose some random images to display
|
|
n_inputs = len(inputs)
|
|
indices = np.arange(n_inputs)
|
|
random_indices = np.random.choice(indices, size=5)
|
|
|
|
for i, image in enumerate(digits.images[random_indices]):
|
|
plt.subplot(1, 5, i+1)
|
|
plt.axis('off')
|
|
plt.imshow(image, cmap=plt.cm.gray_r, interpolation='nearest')
|
|
plt.title("Label: %d" % digits.target[random_indices[i]])
|
|
plt.show()
|
|
|
|
from keras.utils import to_categorical
|
|
from sklearn.model_selection import train_test_split
|
|
|
|
# representation of labels
|
|
labels = to_categorical(labels)
|
|
|
|
# split into train and test data
|
|
# one-liner from scikit-learn library
|
|
train_size = 0.8
|
|
test_size = 1 - train_size
|
|
X_train, X_test, Y_train, Y_test = train_test_split(inputs, labels, train_size=train_size,
|
|
test_size=test_size)
|
|
|
|
#import tensorflow as tf
|
|
import tensorflow.compat.v1 as tf
|
|
tf.disable_v2_behavior()
|
|
tf.reset_default_graph()
|
|
|
|
|
|
from keras.models import Sequential
|
|
from keras.layers.convolutional import Conv2D
|
|
from keras.layers.convolutional import MaxPooling2D
|
|
from keras.layers import Flatten
|
|
from keras.layers import Dense
|
|
from keras.regularizers import l2
|
|
from keras.optimizers import SGD
|
|
|
|
def create_convolutional_neural_network_keras(input_shape, receptive_field,
|
|
n_filters, n_neurons_connected, n_categories,
|
|
eta, lmbd):
|
|
model = Sequential()
|
|
model.add(Conv2D(n_filters, (receptive_field, receptive_field), input_shape=input_shape, padding='same',
|
|
activation='relu', kernel_regularizer=l2(lmbd)))
|
|
model.add(MaxPooling2D(pool_size=(2, 2)))
|
|
model.add(Flatten())
|
|
model.add(Dense(n_neurons_connected, activation='relu', kernel_regularizer=l2(lmbd)))
|
|
model.add(Dense(n_categories, activation='softmax', kernel_regularizer=l2(lmbd)))
|
|
|
|
sgd = SGD(lr=eta)
|
|
model.compile(loss='categorical_crossentropy', optimizer=sgd, metrics=['accuracy'])
|
|
|
|
return model
|
|
|
|
epochs = 100
|
|
batch_size = 100
|
|
input_shape = X_train.shape[1:4]
|
|
receptive_field = 3
|
|
n_filters = 10
|
|
n_neurons_connected = 50
|
|
n_categories = 10
|
|
|
|
eta_vals = np.logspace(-5, 1, 7)
|
|
lmbd_vals = np.logspace(-5, 1, 7)
|
|
|
|
CNN_keras = np.zeros((len(eta_vals), len(lmbd_vals)), dtype=object)
|
|
|
|
for i, eta in enumerate(eta_vals):
|
|
for j, lmbd in enumerate(lmbd_vals):
|
|
CNN = create_convolutional_neural_network_keras(input_shape, receptive_field,
|
|
n_filters, n_neurons_connected, n_categories,
|
|
eta, lmbd)
|
|
CNN.fit(X_train, Y_train, epochs=epochs, batch_size=batch_size, verbose=0)
|
|
scores = CNN.evaluate(X_test, Y_test)
|
|
|
|
CNN_keras[i][j] = CNN
|
|
|
|
print("Learning rate = ", eta)
|
|
print("Lambda = ", lmbd)
|
|
print("Test accuracy: %.3f" % scores[1])
|
|
print()
|
|
|
|
# visual representation of grid search
|
|
# uses seaborn heatmap, could probably do this in matplotlib
|
|
import seaborn as sns
|
|
|
|
sns.set()
|
|
|
|
train_accuracy = np.zeros((len(eta_vals), len(lmbd_vals)))
|
|
test_accuracy = np.zeros((len(eta_vals), len(lmbd_vals)))
|
|
|
|
for i in range(len(eta_vals)):
|
|
for j in range(len(lmbd_vals)):
|
|
CNN = CNN_keras[i][j]
|
|
|
|
train_accuracy[i][j] = CNN.evaluate(X_train, Y_train)[1]
|
|
test_accuracy[i][j] = CNN.evaluate(X_test, Y_test)[1]
|
|
|
|
|
|
fig, ax = plt.subplots(figsize = (10, 10))
|
|
sns.heatmap(train_accuracy, annot=True, ax=ax, cmap="viridis")
|
|
ax.set_title("Training Accuracy")
|
|
ax.set_ylabel("$\eta$")
|
|
ax.set_xlabel("$\lambda$")
|
|
plt.show()
|
|
|
|
fig, ax = plt.subplots(figsize = (10, 10))
|
|
sns.heatmap(test_accuracy, annot=True, ax=ax, cmap="viridis")
|
|
ax.set_title("Test Accuracy")
|
|
ax.set_ylabel("$\eta$")
|
|
ax.set_xlabel("$\lambda$")
|
|
plt.show()
|