def getDataSet():
mn = MNIST(".") #dir of files
images, labels = mn.load_training()
images = normalize_images(images)
labels = vectorize_labels(labels)
return np.array(images), np.array(labels)
def getDataSet():
mn = MNIST(".") #dir of files
images, labels = mn.load_training()
images = normalize_images(images)
labels = vectorize_labels(labels)
return np.array(images), np.array(labels)
def main():
nn = NeuronNetwork(input_size=784, output_size=10, hidden_layers=[15])
#input = np.random.randn(784).reshape(784,1)
#dic = nn.prediction(input, print_result=True)
# read data into variables
# x_train[0 - 59999][0 - 783], labels_train[0 - 59999]
mndata = MNIST('../data')
x_train_in, labels_train = mndata.load_training()
print('MNIST training data has been read')
x_test_in, labels_test = mndata.load_testing()
print('MNIST test data has been read')
x_train, x_test = normalize_data(x_train_in, x_test_in)
print('MNIST data has been normalized')
trainer = Trainer(nn)
# train(n_training_examples=60000, batch_size=200, n_epochs=20, learn_rate=1.5) = 0.872 accuracy
# train(n_training_examples=60000, batch_size=200, n_epochs=40, learn_rate=1.5) = 0.906 accuracy
trainer.train(x_train,
labels_train,
n_training_examples=60000,
batch_size=200,
n_epochs=50,
learn_rate=1.5)
error_list, acc = trainer.test(x_test, labels_test, n_test_examples=1000)
#print ('error: {} ----> {}'.format(error_list[0], error_list[-1]))
print('accuracy = {}'.format(acc))
#testing with examples
for i in range(10):
vec, pred = nn.prediction(x_test[i])
print('Image: {} ====> Prediction: {}'.format(labels_test[i], pred))
def get_natural_dataset_samples(num_of_samples):
from loader import MNIST
import random
mndata = MNIST('MNIST_dataset')
images, labels = mndata.load_training()
selected_img = []
selected_labels = []
selected_idxs = random.sample(range(0, len(images)), num_of_samples)
for i in range(0, len(selected_idxs)):
# newPoint = [float(j) for j in images[selected_idxs[i]]]
# selected_img.append(newPoint)
selected_img.append(images[selected_idxs[i]])
selected_labels.append(labels[selected_idxs[i]])
return selected_img, selected_labels
from loader import MNIST
import numpy as np
# This is intended to be called from the directory aboves
mndata = MNIST('./data')
# Load a list with training images and training labels
training_ims, training_labels = mndata.load_training()
testing_ims, testing_labels = mndata.load_testing()
# Transform everything into array
training_ims = np.array(training_ims)
training_labels = np.array(training_labels)
rand = noise.gauss(rand, rnd_gauss)
test_random[i] = serialize(rand)
filesave.as_text(test_clean, 'data/clean/test/file.my-obj')
filesave.as_text(test_gauss_5, 'data/noisy/test/gauss_5.my-obj')
filesave.as_text(test_gauss_10, 'data/noisy/test/gauss_10.my-obj')
filesave.as_text(test_gauss_15, 'data/noisy/test/gauss_15.my-obj')
filesave.as_text(test_snp_002, 'data/noisy/test/snp_002.my-obj')
filesave.as_text(test_snp_005, 'data/noisy/test/snp_005.my-obj')
filesave.as_text(test_snp_01, 'data/noisy/test/snp_01.my-obj')
filesave.as_text(test_5_005, 'data/noisy/test/gauss_5_snp_005.my-obj')
filesave.as_text(test_10_002, 'data/noisy/test/gauss_10_snp_002.my-obj')
filesave.as_text(test_15_01, 'data/noisy/test/gauss_15_snp_01.my-obj')
filesave.as_text(test_random, 'data/noisy/test/random.my-obj')
imgs_train, labels_train = mnist.load_training()
train_clean = np.empty(imgs_train.__len__(), dtype=object)
train_gauss_5 = np.empty(imgs_train.__len__(), dtype=object)
train_gauss_10 = np.empty(imgs_train.__len__(), dtype=object)
train_gauss_15 = np.empty(imgs_train.__len__(), dtype=object)
train_snp_002 = np.empty(imgs_train.__len__(), dtype=object)
train_snp_005 = np.empty(imgs_train.__len__(), dtype=object)
train_snp_01 = np.empty(imgs_train.__len__(), dtype=object)
train_5_005 = np.empty(imgs_train.__len__(), dtype=object)
train_10_002 = np.empty(imgs_train.__len__(), dtype=object)
train_15_01 = np.empty(imgs_train.__len__(), dtype=object)
train_random = np.empty(imgs_train.__len__(), dtype=object)
for i in xrange(imgs_train.__len__()):
im_arr = imgs_train[i]
class variables:
def setup(self,n,eta,batchSize,repetitions,Dataset):
print('Setting up Variables', end='')
self.n = np.array(n) #Layers
self.eta = eta #learning rate (now independent on batchSize)
self.batchSize = batchSize
self.repetitions = repetitions
self.Dataset = Dataset #DataSet Option
self.randrange = 1
self.dSetIndex = {0:'Database-MNIST',1:'Database-EMNIST'}
self.w = np.array([np.zeros((self.n[x],self.n[x-1])) for x in range(len(self.n))[1:]]) #weights
self.b = np.array([np.zeros((self.n[x],1)) for x in range(len(self.n))[1:]]) #biases
self.nRow = np.array([np.zeros((self.n[x],1)) for x in range(len(self.n))])#neuralRow
self.zRow = np.array([np.zeros((self.n[x],1)) for x in range(len(self.n))[1:]])#neuralRow pre-sigmoid
self.delta = np.array([np.zeros((self.n[x],1)) for x in range(len(self.n))[1:]]) #error
self.grad = np.array([ #gradient descent step
np.array([np.zeros((self.n[x],1)) for x in range(len(self.n))[1:]]),#dC/dbias
np.array([np.zeros((self.n[x],self.n[x-1])) for x in range(len(self.n))[1:]]) #dC/dweight
])
self.aveCost = 0
self.prevCost = 0
self.images = None
self.imagesTe = None
def imagesSetup(self,Dataset):
self.Dataset = Dataset
self.mndata = MNIST(self.dSetIndex[Dataset])
if Dataset == 0: #MNIST Setup
print('.', end='')
images = self.mndata.load_training()
self.images = [np.array([np.array(images[0][x]),images[1][x]]) for x in range(len(images[0]))]
#CONSIDER USING 'zip()' INSTEAD
print('.', end='')
self.mndata = MNIST(self.dSetIndex[Dataset])
imagesTe = self.mndata.load_testing()
self.imagesTe = [np.array([np.array(imagesTe[0][x]),imagesTe[1][x]]) for x in range(len(imagesTe[0]))]
elif Dataset == 1: #EMNIST Setup
print('.', end='')
images = self.mndata.load_training()
self.images = [np.array([np.ravel(np.transpose([np.reshape(images[0][x],(28,28))])),images[1][x]]) for x in range(len(images[0]))]
print('.', end='')
self.mndata = MNIST(self.dSetIndex[Dataset])
imagesTe = self.mndata.load_testing()
self.imagesTe = [np.array([np.ravel(np.transpose([np.reshape(imagesTe[0][x],(28,28))])),imagesTe[1][x]]) for x in range(len(imagesTe[0]))]
#EMNIST Database Digits image matrices were 'transposed' so had to be transposed back
#This method was used because the array containing the pixel data has to be an np.array
#There seems to be a bug where 'np.transpose()' seems to make every entry of 'images' the same
#This was tested to be faster than 'np.transpose()'
print('.', end='')
self.costArr = np.array([
[np.zeros(self.n[-1]) for x in range(self.batchSize)]
for x in range(len(self.images)//self.batchSize)
])
self.cost = np.array([
np.zeros(self.batchSize) for x in range(len(self.images)//self.batchSize)
])
self.costArrTot = np.array([
np.zeros(self.n[-1]) for x in range(len(self.images)//self.batchSize)
])
self.costArrTe = np.array([np.zeros(self.n[-1]) for x in range(len(self.imagesTe))])
self.costTe = np.zeros(len(self.imagesTe))
print(' Complete.\n')
import numpy as np
from loader import MNIST
from nnCostFunction import nnCostFunction
from randInitializeWeights import randInitializeWeights
from computeNumericalGradient import unRolling
from predict import predict
from shuffle import shuffle
# Get data from Mnist
data = MNIST()
data.load_training()
data.load_testing()
x_train = data.train_images
y_train = data.train_labels
x_test = data.test_images
y_test = data.test_labels
x_train = np.reshape(x_train, (len(x_train), 784))
y_train = np.reshape(y_train, (len(y_train), 1))
y_train_fix = np.reshape(np.zeros(len(y_train)*10), (len(y_train), 10))
for i in range(len(y_train)):
for j in range(0, 10):
if y_train[i] == j:
y_train_fix[i][j] = 1
# Create Validation, Train
list_x_val = []
list_y_val = []
list_x_train = []
from sklearn import tree
import matplotlib.pyplot as plt
import StringIO
import pydotplus
from loader import MNIST
mndata = MNIST('./Datasets')
trainingImages, trainingLabels = mndata.load_training()
testImages, testLabels = mndata.load_testing()
clf = tree.DecisionTreeClassifier()
clf = clf.fit(trainingImages[:1000], trainingLabels[:1000])
scores = clf.score(testImages,testLabels.tolist())
print "Accuracy: %f " % scores
importances = clf.feature_importances_
importances = importances.reshape((28, 28))
plt.matshow(importances, cmap=plt.cm.hot)
plt.title("Pixel importances for decision tree")
plt.show()
dot_data = StringIO.StringIO()
tree.export_graphviz(clf, out_file=dot_data)
graph = pydotplus.graph_from_dot_data(dot_data.getvalue())
graph.write_pdf("Dtree.pdf")
print "The Decision Tree was saved!"
def loadMnist(self):
m = MNIST('./data')
self.trvec, self.train_labels = m.load_training()
return (-1.0 / n) * res
mndata = MNIST('data')
mndata.test_img_fname = 't10k-images.idx3-ubyte'
mndata.test_lbl_fname = 't10k-labels.idx1-ubyte'
mndata.train_img_fname = 'train-images.idx3-ubyte'
mndata.train_lbl_fname = 'train-labels.idx1-ubyte'
print "Params: "
print "Digits: " + str(digitA) + " -- -1 " + str(digitB) + " -- 1"
print "Iterations: ", iterations
print "Step (nu): ", nu
print "Loading data..."
mndata.load_training()
mndata.load_testing()
print "Training data count:", len(mndata.train_images)
print "Testing data count:", len(mndata.test_images)
[(train_imgs, train_classes), (test_imgs, test_classes)] = [
zip(*[(i, l) for (i, l) in zip(imgs, map(label_class, lbls)) if l == -1 or l == 1])
for (imgs, lbls) in [(mndata.train_images, mndata.train_labels), (mndata.test_images, mndata.test_labels)]]
train_imgs = map(color_binarization, train_imgs)
test_imgs = map(color_binarization, test_imgs)
w = numpy.array([0.0 for _ in xrange(img_size)])
print "Training..."
return (-1.0 / n) * res
mndata = MNIST('data')
mndata.test_img_fname = 't10k-images.idx3-ubyte'
mndata.test_lbl_fname = 't10k-labels.idx1-ubyte'
mndata.train_img_fname = 'train-images.idx3-ubyte'
mndata.train_lbl_fname = 'train-labels.idx1-ubyte'
print "Params: "
print "Digits: " + str(digitA) + " -- -1 " + str(digitB) + " -- 1"
print "Iterations: ", iterations
print "Step (nu): ", nu
print "Loading data..."
mndata.load_training()
mndata.load_testing()
print "Training data count:", len(mndata.train_images)
print "Testing data count:", len(mndata.test_images)
[(train_imgs, train_classes), (test_imgs, test_classes)] = [
zip(*[(i, l) for (i, l) in zip(imgs, map(label_class, lbls))
if l == -1 or l == 1]) for (imgs, lbls) in [(
mndata.train_images,
mndata.train_labels), (mndata.test_images, mndata.test_labels)]
]
train_imgs = map(color_binarization, train_imgs)
test_imgs = map(color_binarization, test_imgs)
from loader import MNIST
mndata = MNIST("../data/input/")
trn_img, trn_labels = mndata.load_training()
tst_img, tst_labels = mndata.load_testing()
from algorithms.NearestCentroid.MyNearestCentroid import MyNearestCentroid
from algorithms.NearestCentroid.nc_classify import test_nc_classify, test_nc_classify_with_sklearn
from algorithms.NearestNeighbours.nearest_neighbour_classify import test_neigh_classify
from algorithms.NearestSubclass.MyNearestSubclassCentroid import MyNearestSubclassCentroid
from algorithms.NearestSubclass.nsc_classify import test_nsc_classify
from algorithms.PerceptronBP.perceptron_bp_test import test_perceptron_bp
from algorithms.PerceptronMSE.PerceptronMSEClassifier import PerceptronMSEClassifier
from algorithms.PerceptronMSE.perceptron_mse_test import test_perceptron_mse
from loader import MNIST
import numpy as np
from algorithms.PerceptronBP.PerceptronBPClassifier import PerceptronBPClassifier
mndata = MNIST('../samples/MNIST/')
trainingData, trainingLabels = mndata.load_training()
testData, testLabels = mndata.load_testing()
data = trainingData + testData
labels = trainingLabels + testLabels
# # ------- PCA ---------
# pca = PCA(n_components=2).fit(np.array(trainingData))
# trainingData = pca.transform(np.array(trainingData))
#
# pca = PCA(n_components=2).fit(np.array(testData))
# testData = pca.transform(np.array(testData))
#
# pca = PCA(n_components=2).fit(np.array(data))
# data = pca.transform(np.array(data))
from loader import MNIST
mndata = MNIST('../data/input/')
trn_img, trn_labels = mndata.load_training()
tst_img, tst_labels = mndata.load_testing()
###VECTORIZE METHODS!: @vectorize(['float32(float32, float32)'], target='cuda'), where the things are return(param a, param b) and so on
## Libraries
import numpy as np
from numpy import vectorize
from scipy import special # for logistic function
import matplotlib.pyplot as plt
from loader import MNIST
from sklearn import preprocessing
# import scipy optimizer too??
##### 1. Import data #####
print('Loading datasets...')
PATH = '/home/wataru/Uni/4997/programming_hw/ZhuFnn/MNIST_data'
mndata = MNIST(PATH)
X, y = mndata.load_training()
X_test, y_test = mndata.load_testing()
X, y = np.array(X), np.array(y).reshape(-1, 1) # X(60,0000 x 784) y(60,0000x1)
X_test, y_test = np.array(X_test), np.array(y_test).reshape(-1, 1)
##### 2. Set up parameters #####
m_train = X.shape[0]
m_test = X_test.shape[0]
input_size = X.shape[1] # number of features on the input + 1 (bias
hidden_size = 50
output_size = np.unique(y).shape[
0] # extract unique elements and count them as numbers of output labels
lr = 3e-2 # learning rate
epochs = 5000 # num of epoch
