def prepareData():
raw_data, raw_label = loadTrainingData('dataset/train.csv')
test_data = loadTestingData('dataset/test.csv')
#nomalize the train & test data
raw_data = nnet.normalization(raw_data)
test_data = nnet.normalization(test_data)
#split training data to training set & validating set
training_data = raw_data[:37000,:]
training_label = raw_label[:37000,]
validating_data = raw_data[37000:,:]
validating_label = raw_label[37000:,]
return training_data.transpose(),training_label,validating_data.transpose(),validating_label,test_data.transpose()
def prepareData():
raw_data, raw_label = loadTrainingData('dataset/train.csv')
test_data = loadTestingData('dataset/test.csv')
#nomalize the train & test data
raw_data = nnet.normalization(raw_data)
test_data = nnet.normalization(test_data)
#split training data to training set & validating set
training_data = raw_data[:37000, :]
training_label = raw_label[:37000, ]
validating_data = raw_data[37000:, :]
validating_label = raw_label[37000:, ]
return training_data.transpose(
), training_label, validating_data.transpose(
), validating_label, test_data.transpose()
test_data = test_data[:,test_set[0].flatten()]
#step2 divide training set into feature learning set & supervised training set
labeled_set = np.nonzero(labels>=5)
unlabeled_set = np.nonzero(labels<=4)
labeled_dataset = data[:,(labels<=4).flatten()]
labeled_labelset = labels[(labels<=4).flatten()]
unlabeled_dataset = data[:,(labels>=5).flatten()]
unlabeled_dataset = unlabeled_dataset[:,:unlabeled_dataset.shape[1]/3]
print unlabeled_dataset.shape
#step3 feature learning using sparse autoencoder
#TODO move normalization to miscellaneous
unlabeled_dataset = nnet.normalization(unlabeled_dataset)
W = nnet.sparseAutoencoder(inputSize,hiddenSize,sparsityParam,lmd,beta,alpha,unlabeled_dataset)
W1 = np.reshape(W[:hiddenSize*inputSize,], (hiddenSize, inputSize))
b1 = np.reshape(W[2*hiddenSize*inputSize:2*hiddenSize*inputSize+hiddenSize,],(hiddenSize,1))
#step4 plot the learned feature
fig = plt.figure(2)
for index in range(hiddenSize/10):
weight = W1[index,:]
weight = np.reshape(weight,(28,28))
ax = fig.add_subplot(5,4,1+index)
ax.imshow(weight,mpl.cm.gray)
plt.show()
label = sio.loadmat('dataset/mnist_dataset/mnist_train_labels.mat')
data = image['mnist_train']
training_labels = label['mnist_train_labels']
training_data = data.transpose()
#testing data
image = sio.loadmat('dataset/mnist_dataset/mnist_test.mat')
label = sio.loadmat('dataset/mnist_dataset/mnist_test_labels.mat')
test_data = image['mnist_test']
test_labels = label['mnist_test_labels']
test_data = test_data.transpose()
start = time.time()
#step2 L1 feature learning using sparse autoencoder
#TODO move normalization to miscellaneous
training_data = nnet.normalization(training_data)
#W = nnet.sparseAutoencoder(inputSize,hiddenSizeL1,sparsityParam,lmd,beta,alpha,training_data,iters=500)
W = load_data('weightL1')
W = np.array(W)
W = W.transpose()
#savedata(W,'weightL1')
W11 = np.reshape(W[:hiddenSizeL1*inputSize,], (hiddenSizeL1, inputSize))
b11 = np.reshape(W[2*hiddenSizeL1*inputSize:2*hiddenSizeL1*inputSize+hiddenSizeL1,],(hiddenSizeL1,1))
#step3 L2 feature learning using sparse autoencoder
training_a1 = nnet.sigmoid(W11.dot(training_data)+b11)
#W = nnet.sparseAutoencoder(hiddenSizeL1,hiddenSizeL2,sparsityParam,lmd,beta,0.009,training_a1,iters=500)
W = load_data('weightL2')
W = np.array(W)
W = W.transpose()
#savedata(W,'weightL2')
numClasses = 10
hiddenSizeL1 = 5
sparsityParam = 0.1
beta = 3
lmd = 0.001
alpha = 0.07
# step1 load training data
# TODO move normalization to miscellaneous
file_path = "dataset/faces.mat"
images = sio.loadmat(file_path)
data = images["data"]
data = data.transpose()
# normalize data
data = nnet.normalization(data)
# split data to training set and testing set
testing_lables = []
training_labels = []
for index in range(10):
train = data[:, 90 * index : 90 * index + 80]
test = data[:, 90 * index + 80 : 90 * (index + 1)]
if index == 0:
training_set = train
testing_set = test
else:
training_set = np.c_[training_set, train]
testing_set = np.c_[testing_set, test]
labels = 10 * [index]
label = sio.loadmat('dataset/mnist_dataset/mnist_train_labels.mat')
data = image['mnist_train']
training_labels = label['mnist_train_labels']
training_data = data.transpose()
#testing data
image = sio.loadmat('dataset/mnist_dataset/mnist_test.mat')
label = sio.loadmat('dataset/mnist_dataset/mnist_test_labels.mat')
test_data = image['mnist_test']
test_labels = label['mnist_test_labels']
test_data = test_data.transpose()
start = time.time()
#step2 L1 feature learning using sparse autoencoder
#TODO move normalization to miscellaneous
training_data = nnet.normalization(training_data)
#W = nnet.sparseAutoencoder(inputSize,hiddenSizeL1,sparsityParam,lmd,beta,alpha,training_data,iters=500)
W = load_data('weightL1')
W = np.array(W)
W = W.transpose()
#savedata(W,'weightL1')
W11 = np.reshape(W[:hiddenSizeL1 * inputSize, ], (hiddenSizeL1, inputSize))
b11 = np.reshape(
W[2 * hiddenSizeL1 * inputSize:2 * hiddenSizeL1 * inputSize +
hiddenSizeL1, ], (hiddenSizeL1, 1))
#step3 L2 feature learning using sparse autoencoder
training_a1 = nnet.sigmoid(W11.dot(training_data) + b11)
#W = nnet.sparseAutoencoder(hiddenSizeL1,hiddenSizeL2,sparsityParam,lmd,beta,0.009,training_a1,iters=500)
W = load_data('weightL2')
W = np.array(W)
numClasses = 10
hiddenSizeL1 = 5
sparsityParam = 0.1
beta = 3
lmd = 0.001
alpha = 0.07
#step1 load training data
#TODO move normalization to miscellaneous
file_path = 'dataset/faces.mat'
images = sio.loadmat(file_path)
data = images['data']
data = data.transpose()
#normalize data
data = nnet.normalization(data)
#split data to training set and testing set
testing_lables = []
training_labels = []
for index in range(10):
train = data[:,90*index:90*index+80]
test = data[:,90*index+80:90*(index+1)]
if index == 0:
training_set = train
testing_set = test
else:
training_set = np.c_[training_set, train]
testing_set = np.c_[testing_set, test]
labels = 10*[index]