show_plots = True
save_plots = True
# Load in MNIST data, process it for multiclass classification
print("Loading MNIST data...")
X_train, y_train = mu.load_mnist(dataset='training')
y_train_true = np.asarray(y_train[:, None] == np.arange(max(y_train) + 1),
dtype=int).squeeze()
X_test, y_test = mu.load_mnist(dataset='testing')
y_test_true = np.asarray(y_test[:, None] == np.arange(max(y_test) + 1),
dtype=int).squeeze()
# Solve for all principal components but do calculations using only 50
# Can reset l later if need be as all principal components are retained
print("Performing PCA with k = %d components..." % k)
PCA = pca.PCA(l=k, center=False)
PCA.fit(X_train)
X_train = PCA.transform(X_train)
X_test = PCA.transform(X_test)
print("Training neural network...")
activators = [deep.relu, deep.linear]
activators_prime = [deep.relu_prime, deep.linear_prime]
y_hat, w_1, w_2, b_1, b_2, iter_arr, train_sq_loss, train_01_loss, test_sq_loss, \
test_01_loss = \
deep.neural_net(X_train, y_train_true, nodes=nodes,
activators=activators,
activators_prime=activators_prime, scale=scale,
eps=eps, eta=eta, lam=lam, adaptive=True,
batchsize=batchsize, nout=nout, nclass=nclass,
# Load in MNIST data
print("Loading MNIST Training data...")
X_train, y_train = mu.load_mnist(dataset='training')
# Training using only one digit?
if use_one_digit:
mask = y_train.squeeze() == 5
X_train = X_train[mask]
print(X_train.shape)
y_train = y_train[mask]
# Init PCA object
# Solve for all principal components but do calculations using only 50
# Can reset l later if need be as all principal components are retained
PCA = pca.PCA(l=50, center=True)
# Fit model
print("Fitting PCA model...")
PCA.fit(X_train)
#####################################################
#
# 1.2.1: Eigenvalues and you
#
#####################################################
eval_list = np.asarray([1, 2, 10, 30, 50]) - 1 # my 1st eigenvalue is evals[0]
for ev in eval_list:
print("%d eigenvalue: %lf" % ((ev+1),PCA.evals[ev]))
print("Sum of eigenvalues: %lf" % np.sum(PCA.evals))
import matplotlib as mpl
import matplotlib.pyplot as plt
# Flags to control functionality
show_plots = True
save_plots = True
use_one_digit = False
# Load in MNIST data
print("Loading MNIST Training data...")
X_train, y_train = mu.load_mnist(dataset='training')
# Init PCA object
# Solve for all principal components but do calculations using only 50
# Can reset l later if need be as all principal components are retained
PCA = pca.PCA(l=12, center=True)
# Fit model
print("Fitting PCA model...")
PCA.fit(X_train)
#####################################################
#
# 1.3.1: Eigenvectors and you: Plot first 10
#
#####################################################
if show_plots:
fig, axes = plt.subplots(nrows=4, ncols=4)