def load(self):
"""
Downloads the dataset following the specifification of the instantiated instance
"""
# donwload proper dataset
if self.onlyDigits:
logging.info('Downloading digits from EMNIST repository')
X, y = extract_test_samples('digits')
if self.kerasDB:
logging.info(
'Downloading the Original MNIST dataset from TensorFlow Datasets'
)
(X_train, y_train), (X_test, y_test) = mnist.load_data()
# concatenate train and test together
# we want to perform the training with the highest number of training instances
X = np.concatenate((X_train, X_test))
y = np.concatenate((y_train, y_test))
else:
logging.info(
'Downloading letters and digits from EMNIST repository')
X, y = extract_test_samples('balanced')
# save downloded data in the dataset folder as numpy array
np.save(os.path.join(self.dirData, 'data.npy'), X)
np.save(os.path.join(self.dirData, 'label.npy'), y)
if self.verbose:
self.printInfo(y)
return X, y
def load_dataset():
# load dataset
(trainX, trainY) = em.extract_training_samples('letters')
trainX, trainY = shuffle(trainX, trainY)
(testX, testY) = em.extract_test_samples('letters')
# reshape dataset to have a single channel
#(trainX,trainY),(testX,testY)=load_data()
trainX = trainX.reshape((trainX.shape[0], 28, 28, 1))
testX = testX.reshape((testX.shape[0], 28, 28, 1))
# one hot encode target values
#trainY = to_categorical(trainY)
testY = to_categorical(testY)
tX = []
tY = []
# print("tX.shape",tX.shape)
# print("tY.shape",tY.shape)
# #print(trainy[0])
shot = 300
ctr = [shot] * 27
for i in range(len(trainY)):
label = trainY[i]
ctr[label] = ctr[label] - 1
if (ctr[label] > 0):
tX.append(trainX[i])
tY.append(trainY[i])
print("tX.shape", len(tX))
tY = to_categorical(tY)
# print("tY.shape",tY.shape)
return tX, tY, testX, testY
def loadTestData(self, category='letters'):
"""
Load testing data for EMNIST uppercase/lowercase 26 characters and
format appropriately
"""
testImages, testLabels = emnist.extract_test_samples(category)
return reformat(testImages, testLabels)
def train(mode, dataset):
from tensorflow import keras
from emnist import list_datasets, extract_training_samples, extract_test_samples
import numpy as np
from numpy.random import seed
from tensorflow import set_random_seed
name = mode[0]
mode = mode[1]
seed(4)
set_random_seed(4)
(train_images, train_labels) = extract_training_samples(dataset)
(test_images, test_labels) = extract_test_samples(dataset)
train_labels = keras.utils.to_categorical(train_labels)
test_labels = keras.utils.to_categorical(test_labels)
if mode["reshape"]:
# Reshaping the array to 4-dims so that it can work with the Keras API
# The last number is 1, which signifies that the images are greyscale.
train_images = np.reshape(train_images,
(train_images.shape[0], 28, 28, 1))
test_images = np.reshape(test_images,
(test_images.shape[0], 28, 28, 1))
train_images = keras.utils.normalize(train_images, axis=1)
test_images = keras.utils.normalize(test_images, axis=1)
model = keras.Sequential()
for l in mode["architecture"]:
model.add(l)
es = keras.callbacks.EarlyStopping(monitor="val_loss",
mode="min",
patience=2)
model.compile(optimizer="adam",
loss="categorical_crossentropy",
metrics=["accuracy"])
print(model.summary())
model.fit(x=train_images,
y=train_labels,
epochs=100,
validation_split=0.1,
callbacks=[es])
model_name = dataset + "_" + name
model.save("./" + model_name + ".h5")
print("saved model to " + model_name + ".h5")
print("evaluating...")
val_loss, val_acc = model.evaluate(x=test_images, y=test_labels)
del train_images
del train_labels
del test_images
del test_labels
import gc
gc.collect()
def load_data() -> tuple:
images_train, labels_train = extract_training_samples("letters")
images_test, labels_test = extract_test_samples("letters")
images = np.concatenate((images_train, images_test))
labels = np.concatenate((labels_train, labels_test))
images = np.expand_dims(images, axis=-1)
labels = labels - 1
return images, labels
def load_emnist_balanced():
"""
Load EMNIST Balanced
:return: training inputs, training outputs, test inputs, test outputs, number of classes
"""
training_images, training_labels = emnist.extract_training_samples(
'balanced')
test_images, test_labels = emnist.extract_test_samples('balanced')
return training_images, training_labels, test_images, test_labels, len(
set(training_labels))
def load_emnist_letters():
"""
Load EMNIST Letters
:return: training inputs, training outputs, test inputs, test outputs, number of classes
"""
training_images, training_labels = emnist.extract_training_samples(
'letters')
test_images, test_labels = emnist.extract_test_samples('letters')
return training_images, training_labels, test_images, test_labels, len(
set(training_labels))
def save_emnist_uppercase_reduced_letters64_dataset():
x_train, y_train = emnist.extract_training_samples('byclass')
x_test, y_test = emnist.extract_test_samples('byclass')
train_mask = emnsit_uppercase_label_filter(y_train)
test_mask = emnsit_uppercase_label_filter(y_test)
x_train_reduced = x_train[train_mask]
x_train_reduced = [
cv2.resize(i, (64, 64), interpolation=cv2.INTER_NEAREST)
for i in x_train_reduced
]
y_train_reduced = y_train[train_mask]
# shift to 0 label
y_train_reduced -= 10
y_train_reduced = replace_x_letter_label(y_train_reduced)
x_test_reduced = x_test[test_mask]
x_test_reduced = [
cv2.resize(i, (64, 64), interpolation=cv2.INTER_NEAREST)
for i in x_test_reduced
]
y_test_reduced = y_test[test_mask]
y_test_reduced -= 10
y_test_reduced = replace_x_letter_label(y_test_reduced)
x_train_reduced, x_val_reduced, y_train_reduced, y_val_reduced = train_test_split(
x_train_reduced, y_train_reduced, test_size=0.1)
x_train_reduced = np.divide(x_train_reduced, 255).astype("float64")
x_val_reduced = np.divide(x_val_reduced, 255).astype("float64")
x_test_reduced = np.divide(x_test_reduced, 255).astype("float64")
#
x_train_reduced = x_train_reduced.reshape(x_train_reduced.shape[0],
x_train_reduced.shape[1],
x_train_reduced.shape[2], 1)
x_val_reduced = x_val_reduced.reshape(x_val_reduced.shape[0],
x_val_reduced.shape[1],
x_val_reduced.shape[2], 1)
x_test_reduced = x_test_reduced.reshape(x_test_reduced.shape[0],
x_test_reduced.shape[1],
x_test_reduced.shape[2], 1)
letters_dataset = {
"x_train": x_train_reduced,
"y_train": y_train_reduced,
"x_val": x_val_reduced,
"y_val": y_val_reduced,
"x_test": x_test_reduced,
"y_test": y_test_reduced
}
with open("eng_uppercase_letters64_dataset.bin", "wb") as file:
pickle.dump(letters_dataset, file)
def load_dataset():
# load dataset
trainX, trainY = extract_training_samples('letters')
testX, testY = extract_test_samples('letters')
# reshape dataset to have a single channel
trainX = trainX.reshape((trainX.shape[0], 28, 28, 1))
testX = testX.reshape((testX.shape[0], 28, 28, 1))
# one hot encode target values
trainY = to_categorical(trainY)
testY = to_categorical(testY)
return trainX, trainY, testX, testY
def preprocess():
train_images, train_labels = emnist.extract_training_samples('mnist')
train_images = train_images.reshape(
(train_images.shape[0], 1, 28, 28)).astype(np.float32)
train_images /= 255
train_labels = one_hot(train_labels.reshape(train_labels.shape[0], 1), 10)
test_images, test_labels = emnist.extract_test_samples('mnist')
test_images = test_images.reshape(
(test_images.shape[0], 1, 28, 28)).astype(np.float32)
test_images /= 255
return (train_images, train_labels), (test_images, test_labels)
def saveDataSet(dataSetType):
if dataSetType == 'digits':
# Extract Dataset
print('Extraction Dataset')
X_train, y_train = extract_training_samples('digits')
X_test, y_test = extract_test_samples('digits')
# Reshape Dataset
print('Reshaping Dataset ')
images_train, labels_train = manageDataSet(len(y_train), X_train,
y_train)
images_test, labels_test = manageDataSet(len(y_test), X_test, y_test)
# Save the Dataset
print('Saving Dataset')
save("images_numbers_train.npy", images_train)
save("labels_numbers_train.npy", labels_train)
save("images_numbers_test.npy", images_test)
save("labels_numbers_test.npy", labels_test)
if dataSetType == 'letters':
# Extract Dataset
print('Extraction Dataset')
X_train, y_train = extract_training_samples('letters')
X_test, y_test = extract_test_samples('letters')
# Reshape Dataset
print('Reshaping Dataset ')
imgs_train, labels_train = manageDataSet(len(y_train), X_train,
y_train)
imgs_test, labels_test = manageDataSet(len(y_test), X_test, y_test)
# Save reshape Dataset
print('Extraction Dataset')
save("images_letters_train.npy", imgs_train)
save("labels_letters_train.npy", labels_train)
save("images_letters_test.npy", imgs_test)
save("labels_letters_test.npy", labels_test)
def loadEmnist(self):
"""
Load Emnist dataset and do some data pre-processing
Split the training set 80/20% for training and validation set
Convert y labels to 1-k hot array
"""
x_train, y_train = extract_training_samples('balanced')
x_test, y_test = extract_test_samples('balanced')
# Get only the upper case letters
train_alphabet_list = (np.array(y_train) < 36) & (np.array(y_train) > 9)
test_alphabet_list = (np.array(y_test) < 36) & (np.array(y_test) > 9)
y_train = y_train[train_alphabet_list] - 10
x_train = x_train[train_alphabet_list]
y_test = y_test[test_alphabet_list] - 10
x_test = x_test[test_alphabet_list]
self.nclass = 26
self.width = x_train.shape[1]
self.height = x_train.shape[2]
self.total_train_size = len(x_train)
self.ntrain = int(0.9 * self.total_train_size)
self.nval = int(0.1 * self.total_train_size)
self.ntest = len(x_test)
self.train_counter = 0
self.train_index = np.arange(self.ntrain)
x_train = x_train.reshape(x_train.shape[0], self.width, self.height, 1)
x_test = x_test.reshape(x_test.shape[0], self.width, self.height, 1)
input_shape = (self.width, self.height, 1)
x_train = x_train.astype('float32')
x_test = x_test.astype('float32')
x_train /= 255
self.x_test = x_test/255
self.x_val = x_train[self.ntrain:self.total_train_size]
self.x_train = x_train[0:self.ntrain]
y_val = y_train[self.ntrain:self.total_train_size]
y_train = y_train[0:self.ntrain]
# convert class vectors to binary class matrices
self.y_train = keras.utils.to_categorical(y_train, 26)
self.y_val = keras.utils.to_categorical(y_val, 26)
self.y_test = keras.utils.to_categorical(y_test, 26)
print(self.x_train.shape)
print(self.x_val.shape)
print(self.x_test.shape)
def __init__(self,
number_of_authors,
number_of_pixels=4,
poisoned_ratio=0.2,
backdoor_value=1,
initial_shuffle=True,
seed=None):
X_train, y_train = emnist.extract_training_samples('digits')
X_test, y_test = emnist.extract_test_samples('digits')
X = np.concatenate((X_train, X_test))
y = np.concatenate((y_train, y_test))
# IMPORTANT:
# create imbalanced datasets, i.e., the number of elements in each digit class of the same author may vary.
# But the number of samples per author is balanced, i.e., each author has the same number of samples.
samples_per_author = len(X) // number_of_authors
author = np.repeat(np.arange(number_of_authors), samples_per_author)
# throw leftover datasamples away such that we have same number of samples for each author
skip_at_end = len(X) - len(author)
assert skip_at_end < samples_per_author, "Why do you throw so many samples away?"
if skip_at_end > 0:
print(
f"Warning: throwing {skip_at_end} samples away to have balanced number of samples per author"
)
X = X[:len(author)]
y = y[:len(author)]
# flatten X[:,-]
print(X.shape)
X = X.reshape((len(X), 784))
print(X.shape)
# binarize data
# X[X<128] = 0
# X[X>127] = 255
X = X / 255
super(PoisonedDataset_EMNIST_DIGITS,
self).__init__(X,
y,
author,
number_of_classes=10,
number_of_pixels=number_of_pixels,
poisoned_ratio=poisoned_ratio,
backdoor_value=backdoor_value,
initial_shuffle=initial_shuffle,
seed=seed)
def load_data():
# Get numbers and letters data from EMNIST
X_train, train_labels = extract_training_samples('byclass')
X_test, test_labels = extract_test_samples('byclass')
# Remove capital letters
X_train, train_labels = remove_upper(X_train, train_labels)
X_test, test_labels = remove_upper(X_test, test_labels)
# Merge train and test datasets
X = np.vstack((X_train, X_test))
labels = np.hstack((train_labels, test_labels))
return X, labels
def load_data():
X_train, train_labels = extract_training_samples('byclass')
X_test, test_labels = extract_test_samples('byclass')
X_train, train_labels = remove_upper(X_train, train_labels)
X_test, test_labels = remove_upper(X_test, test_labels)
chars = '0123456789' + string.ascii_lowercase
num_chars = len(chars)
X_train = X_train.reshape(-1, 28, 28, 1)
X_test = X_test.reshape(-1, 28, 28, 1)
return X_train, X_test, train_labels, test_labels
def save_emnist_reduced_letters_dataset():
x_train, y_train = emnist.extract_training_samples('letters')
x_test, y_test = emnist.extract_test_samples('letters')
# Переход к меткам диапазона [0..25]
y_train = np.subtract(y_train, 1)
y_test = np.subtract(y_test, 1)
# train_mask = label_filter(y_train)
train_mask = label_filter(y_train)
test_mask = label_filter(y_test)
x_train_reduced = x_train[train_mask]
y_train_reduced = y_train[train_mask]
y_train_reduced = replace_x_letter_label(y_train_reduced)
x_test_reduced = x_test[test_mask]
y_test_reduced = y_test[test_mask]
y_test_reduced = replace_x_letter_label(y_test_reduced)
x_train_reduced, x_val_reduced, y_train_reduced, y_val_reduced = train_test_split(
x_train_reduced, y_train_reduced, test_size=0.1)
x_train_reduced = np.divide(x_train_reduced, 255).astype("float64")
x_val_reduced = np.divide(x_val_reduced, 255).astype("float64")
x_test_reduced = np.divide(x_test_reduced, 255).astype("float64")
#
x_train_reduced = x_train_reduced.reshape(x_train_reduced.shape[0],
x_train_reduced.shape[1],
x_train_reduced.shape[2], 1)
x_val_reduced = x_val_reduced.reshape(x_val_reduced.shape[0],
x_val_reduced.shape[1],
x_val_reduced.shape[2], 1)
x_test_reduced = x_test_reduced.reshape(x_test_reduced.shape[0],
x_test_reduced.shape[1],
x_test_reduced.shape[2], 1)
letters_dataset = {
"x_train": x_train_reduced,
"y_train": y_train_reduced,
"x_val": x_val_reduced,
"y_val": y_val_reduced,
"x_test": x_test_reduced,
"y_test": y_test_reduced
}
with open("eng_letters_dataset.bin", "wb") as file:
pickle.dump(letters_dataset, file)
def get_data(self, s0):
self.x_train, self.y_train = extract_training_samples('byclass')
self.x_test, self.y_test = extract_test_samples('byclass')
self.y_test = oneHotEncodeY(self.y_test, 62)
self.y_train = oneHotEncodeY(self.y_train, 62)
self.x_train = self.x_train.astype('float32')
self.y_train = self.y_train.astype('float32')
self.x_test = self.x_test.astype('float32')
self.y_test = self.y_test.astype('float32')
#print(np.amax(self.y_train))
#print(self.x_train.shape, self.y_train.shape, self.x_test.shape, self.y_test.shape)
self.x_train = self.x_train /255.
self.y_train = self.y_train
self.x_test = self.x_test/ 255.
self.y_test = self.y_test
self.x_train = np.reshape(self.x_train,(self.x_train.shape[0], 28, 28, 1))
self.x_test = np.reshape(self.x_test,(self.x_test.shape[0], 28, 28, 1))
#self.y_test = np.reshape(self.y_test,(self.y_test.shape[0],1))
#self.y_train = np.reshape(self.y_train,(self.y_train.shape[0],1))
self.img_rows, self.img_cols, self.nchannels = self.x_train.shape[1:4]
#images = np.reshape(images,(images.shape[0], 28, 28, 1))
#self.x_train, self.y_train = mnist.get_set('train')
#self.x_test, self.y_test = mnist.get_set('test')
#print("//////////////////////////////")
#print(type(images))
#print(images.shape[1:4])
#print(labels.shape)
#print(images.shape)
'''
self.x_train, self.y_train = mnist.get_set('train')
self.x_test, self.y_test = mnist.get_set('test')
self.img_rows, self.img_cols, self.nchannels = self.x_train.shape[1:4]
self.nb_classes = self.y_train.shape[1]
print(np.amax(self.y_train))
'''
self.nb_classes = 62
self.x_sub = self.x_test[:s0]
self.y_sub = np.argmax(self.y_test[:s0], axis=1)
self.x_test = self.x_test[s0:]
self.y_test = self.y_test[s0:]
def load_data(self):
"""
Load data from emnist package
# Returns:
all_data : train data, train labels, test data and test labels
"""
self._train_data, self._train_labels = emnist.extract_training_samples(
'digits')
self._train_labels = np.eye(10)[self._train_labels]
self._test_data, self._test_labels = emnist.extract_test_samples(
'digits')
self._test_labels = np.eye(10)[self._test_labels]
self.shuffle()
return self.data
def get_data(experiment, occlusion=None, bars_type=None, one_hot=False):
# Load EMNIST data, as part of TensorFlow.
(train_images,
train_labels), (test_images,
test_labels) = emnist.extract_training_samples(
'balanced'), emnist.extract_test_samples('balanced')
# (train_images, train_labels), (test_images, test_labels) = emnist.extract_training_samples(
# 'letters'), emnist.extract_test_samples('letters')
# # train_labels = train_labels.reshape(-1, )
# # test_labels = test_labels.reshape(-1, )
all_data = np.concatenate((train_images, test_images), axis=0)
all_labels = np.concatenate((train_labels, test_labels), axis=0)
# all_labels = all_labels - 1 # Change to 0-base index for letters
# Para tabla 1 y el experimento 2
# for i, l in enumerate(all_labels):
# all_labels[i] = {
# 36: 10,
# 37: 11,
# 38: 13,
# 39: 14,
# 40: 15,
# 41: 16,
# 42: 17,
# 43: 23,
# 44: 26,
# 45: 27,
# 46: 29
# }.get(l, l)
all_data = add_noise(all_data, experiment, occlusion, bars_type)
all_data = all_data.reshape(
(131600, img_columns, img_rows, constants.colors))
all_data = all_data.astype('float32') / 255
if one_hot:
# Changes labels to binary rows. Each label correspond to a column, and only
# the column for the corresponding label is set to one.
all_labels = to_categorical(all_labels)
return (all_data, all_labels)
def test():
testData, testLabels = emnist.extract_test_samples('letters')
# import testing data from emnist
# call them data and labels
correct = 0
for x in range(testData.shape[0]):
inputs = norm(np.ndarray.flatten(testData[x]))
guess = nn.guess(inputs)
print("the number was: " + str(testLabels[x]))
guess = whatIndex(guess) + 1
print("it guessed it was :" + str(guess))
if guess == testLabels[x]:
correct += 1
# print("it correctly predicted " + str(correct / len(data) * 100) + "%")
return (correct / testData.shape[0] * 100)
def load_data(plot=True):
# extract data from EMNIST [letters]
images_train, labels_train = extract_training_samples('letters')
images_test, labels_test = extract_test_samples('letters')
if plot:
# randomly plot 25 letters
f, axarr = plt.subplots(5, 5)
indices, ctr = random.sample(range(labels_train.shape[0]), 25), 0
for i in range(5):
for j in range(5):
idx = indices[ctr]
axarr[i, j].imshow(images_train[idx], cmap="gray")
axarr[i, j].set_title(f"{letters[labels_train[idx] - 1]}")
ctr += 1
plt.show()
# flatten last two dimensions to be (N, 784,)
return images_train.reshape((images_train.shape[0], images_train.shape[1] * images_train.shape[2])), images_test.reshape((images_test.shape[0], images_test.shape[1] * images_test.shape[2])), labels_train, labels_test
def test(networkFilePath):
n = NN.NeuralNetwork()
n.loadFrom(networkFilePath)
test_images, test_labels = emnist.extract_test_samples("letters")
scorecard = []
for i in range(len(test_images)):
correctLabel = test_labels[i] - 1
print("Corret label is", correctLabel)
inputs = (np.asfarray(test_images[i].flatten()) / 255 * 0.99) + 0.01
outputs = n.query(inputs)
label = np.argmax(outputs)
print("Network respone is", label)
print()
scorecard.append(correctLabel == label)
print("Report: ", scorecard)
print("Total:", len(scorecard))
print("Correct:", sum(scorecard))
print(sum(scorecard) / len(scorecard))
def load_mnist_data(type='channel_last'):
from emnist import extract_training_samples, extract_test_samples
from keras.utils import np_utils
# input image dimensions
nb_classes = 26
img_rows, img_cols = 28, 28
X_train, Y_1 = extract_training_samples('letters')
X_test, Y_2 = extract_test_samples('letters')
y_train = []
y_test = []
for i in range(Y_1.shape[0]):
y_train.append( Y_1[i] - 1 )
for i in range(Y_2.shape[0]):
y_test.append( Y_2[i] - 1 )
y_train = np.array(y_train)
y_test = np.array(y_test)
if type == 'channel_first':
X_train = X_train.reshape(X_train.shape[0], 1, img_rows, img_cols)
X_test = X_test.reshape(X_test.shape[0], 1, img_rows, img_cols)
else:
X_train = X_train.reshape(X_train.shape[0], img_rows, img_cols, 1)
X_test = X_test.reshape(X_test.shape[0], img_rows, img_cols, 1)
X_train = X_train.astype('float32')
X_test = X_test.astype('float32')
print('X_train shape:', X_train.shape)
print(X_train.shape[0], 'train samples')
print(X_test.shape[0], 'test samples')
# convert class vectors to binary class matrices
Y_train = np_utils.to_categorical(y_train, nb_classes)
Y_test = np_utils.to_categorical(y_test, nb_classes)
return X_train, Y_train, X_test, Y_test
def main():
np.set_printoptions(suppress=True)
# prepare training and testing datasets
training_images, training_labels = extract_training_samples('digits')
test_images, test_labels = extract_test_samples('digits')
training_images = training_images[0:10000]
training_labels = training_labels[0:10000]
tr_i = [training_images[i].flatten().reshape(784).tolist() for i in range(len(training_images))]
for i in range(len(tr_i)):
for j in range(len(tr_i[i])):
tr_i[i][j] /= 255.0
tr_o = [[x] for x in training_labels.tolist()]
tr_o = [[0.01,0.01,0.01,0.01,0.01,0.01,0.01,0.01,0.01,0.01] for i in range(len(training_labels))]
for i in range(len(tr_o)):
tr_o[i][training_labels[i]] = 0.99
# initialize and train the network
nn = NeuralNetwork(784, [16,16], 10)
nn.train(tr_i, tr_o, 1000)
# gauge performance
correct = 0
for test_image, test_label in zip(test_images[0:500], test_labels[0:500]):
result = nn.feed_forward(test_image.flatten().reshape(784).tolist())
print("network result:\n", result);
max = 0
guess = -1
for i, res in enumerate(result):
if res > max:
max = res
guess = i
print('network thinks this is a: ', guess)
print("real answer:", test_label)
if guess == int(test_label):
correct += 1
print('network was correct on ', correct, '/', 500, 'images')
def build_dataset_manual(dataset_name, opts):
""" Build train, valid, test datasets based on model options """
opts = MnistDataOptions(**opts)
logging.info('Building dataset with options: %s', opts)
# Load train and test data (MNIST)
# train: 60k instances
# test: 10k instances
if (dataset_name == 'MNIST'):
train, test = tf.keras.datasets.mnist.load_data()
elif (dataset_name == 'EMNIST'):
train = extract_training_samples('bymerge')
test = extract_test_samples('bymerge')
else:
raise ValueError('Dataset is not supported!')
# ALL we need is the test dataset so the train/valid doesnot matter here
if (opts.split == 'train'):
images, labels = train[0][0:50000], train[1][0:50000]
elif (opts.split == 'valid'):
images, labels = train[0][50000:60000], train[1][50000:60000]
elif (opts.split == 'test'):
images, labels = test
else:
raise ValueError('opts.split is not valid!')
# Change images size
if (dataset_name == 'MNIST') | (dataset_name == 'EMNIST'):
images = np.expand_dims(images, -1)
images = images / 255
if opts.rotate_degs:
images = scipy.ndimage.rotate(images, opts.rotate_degs, axes=[-2, -3])
images = _crop_center(images, 28)
if opts.roll_pixels:
images = np.roll(images, opts.roll_pixels, axis=-2)
return images, labels
def download(self):
"""Download the MNIST data if it doesn't exist in processed_folder already."""
from six.moves import urllib
import gzip
print("download: trying to download")
if self._check_exists():
print("download: already exists so exiting")
return
# download files
try:
os.makedirs(os.path.join(self.root, self.raw_folder))
os.makedirs(os.path.join(self.root, self.processed_folder))
except OSError as e:
if e.errno == errno.EEXIST:
pass
else:
raise
for url in self.urls:
print('Downloading ' + url)
data = urllib.request.urlopen(url)
filename = url.rpartition('/')[2]
file_path = os.path.join(self.root, self.raw_folder, filename)
with open(file_path, 'wb') as f:
f.write(data.read())
with open(file_path.replace('.gz', ''), 'wb') as out_f, \
gzip.GzipFile(file_path) as zip_f:
out_f.write(zip_f.read())
os.unlink(file_path)
# process and save as torch files
print('Processing...')
train_label, train_non_few_shot_ids, train_few_shot_ids = read_label_file(
os.path.join(self.root, self.raw_folder,
'train-labels-idx1-ubyte'), self.few_shot_class)
train_img = read_image_file(os.path.join(self.root, self.raw_folder,
'train-images-idx3-ubyte'),
non_few_shot_ids=train_non_few_shot_ids)
training_set = (train_img, train_label)
test_label, test_non_few_shot_ids, test_few_shot_ids = read_label_file(
os.path.join(self.root, self.raw_folder, 't10k-labels-idx1-ubyte'),
self.few_shot_class)
test_img = read_image_file(os.path.join(self.root, self.raw_folder,
't10k-images-idx3-ubyte'),
few_shot_ids=test_few_shot_ids)
if self.test_emnist:
print("Download: Entering Emnist test")
from emnist import extract_test_samples
images, labels = extract_test_samples('letters')
print(images.shape)
print(labels.shape)
#randomly grab a letter
import random
rand_letter_idx = random.randint(0, 25)
#idx for selected letter clas
test_sample_ids = np.where(labels < 10)[0]
np.random.seed(10)
np.random.shuffle(test_sample_ids)
print('test_sample_ids_len', len(test_sample_ids))
#grab labels and images from that class
labels = labels[test_sample_ids]
images = images[test_sample_ids]
print("After selecting one class")
print(images.shape)
print(labels.shape)
#assert(self.few_shot_class not in labels)
if self.max_test_sample:
test_set = {
torch.ByteTensor(list(images[:self.max_test_sample])).view(
-1, 28, 28),
torch.LongTensor(list(labels[:self.max_test_sample]))
}
else:
test_set = {
torch.ByteTensor(list(images)).view(-1, 28, 28),
torch.LongTensor(list(labels))
}
else:
# test_label, test_non_few_shot_ids, test_few_shot_ids= read_label_file(os.path.join(self.root, self.raw_folder, 't10k-labels-idx1-ubyte'), self.few_shot_class)
# test_img = read_image_file(os.path.join(self.root, self.raw_folder, 't10k-images-idx3-ubyte'), few_shot_ids=test_few_shot_ids)
if (self.max_test_sample):
print('testing max test sample')
test_set = (test_img[:self.max_test_sample],
test_label[:self.max_test_sample])
else:
test_set = (test_img, test_label)
print('confirming test size')
#print(len(test_set[0]), len(test_set[1]))
with open(
os.path.join(self.root, self.processed_folder,
self.training_file), 'wb') as f:
torch.save(training_set, f)
with open(
os.path.join(self.root, self.processed_folder, self.test_file),
'wb') as f:
torch.save(test_set, f)
print('Done!')
def read_data_sets(train_dir,
fake_data=False,
one_hot=False,
dtype=dtypes.float32,
reshape=True,
validation_size=5000):
if fake_data:
def fake():
return DataSet([], [],
fake_data=True,
one_hot=one_hot,
dtype=dtype)
train = fake()
validation = fake()
test = fake()
return base.Datasets(train=train, validation=validation, test=test)
TRAIN_IMAGES = 'emnist-letters-train-images-idx3-ubyte.gz'
TRAIN_LABELS = 'emnist-letters-train-labels-idx1-ubyte.gz'
TEST_IMAGES = 'emnist-letters-test-images-idx3-ubyte.gz'
TEST_LABELS = 'emnist-letters-test-labels-idx1-ubyte.gz'
eminst_train_images, eminst_train_labels = extract_training_samples(
'letters')
eminst_test_images, eminst_test_labels = extract_test_samples('letters')
train_images = eminst_train_images
train_labels = makes_one_hot_vectors(eminst_train_labels)
test_images = eminst_test_images
test_labels = makes_one_hot_vectors(eminst_test_labels)
## local_file = train_dir+'emnist-letters-train-images-idx3-ubyte.gz'
## with open(local_file, 'rb') as f:
## train_images = extract_images(f)
## local_file = train_dir+'emnist-letters-train-labels-idx1-ubyte.gz'
## with open(local_file, 'rb') as f:
## train_labels = extract_labels(f, one_hot=one_hot)
## local_file = train_dir+'emnist-letters-test-images-idx3-ubyte.gz'
## with open(local_file, 'rb') as f:
## test_images = extract_images(f)
## local_file = train_dir+'emnist-letters-test-labels-idx1-ubyte.gz'
## with open(local_file, 'rb') as f:
## test_labels = extract_labels(f, one_hot=one_hot)
if not 0 <= validation_size <= len(train_images):
raise ValueError(
'Validation size should be between 0 and {}. Received: {}.'.format(
len(train_images), validation_size))
validation_images = train_images[:validation_size]
validation_labels = train_labels[:validation_size]
train_images = train_images[validation_size:]
train_labels = train_labels[validation_size:]
train = DataSet(train_images, train_labels, dtype=dtype, reshape=reshape)
validation = DataSet(validation_images,
validation_labels,
dtype=dtype,
reshape=reshape)
test = DataSet(test_images, test_labels, dtype=dtype, reshape=reshape)
return base.Datasets(train=train, validation=validation, test=test)
# from sklearn.preprocessing import MinMaxScaler
from tensorflow import keras
from tensorflow.keras.utils import to_categorical
from tensorflow.keras.layers import Dense, Dropout, Flatten, Conv2D
# from keras.layers.convolutional import Conv2D
# from keras.layers.convolutional import MaxPooling2D
# from keras import backend as K
# from tensorflow.keras.datasets import mnist
# from sklearn.model_selection import train_test_split
# from sklearn.metrics import confusion_matrix
from emnist import extract_training_samples
images_train, labels_train = extract_training_samples('balanced')
from emnist import extract_test_samples
images_test, labels_test = extract_test_samples('balanced')
dims = images_train.shape[1] * images_train.shape[2]
## DENSE NN
X_train = images_train.reshape(images_train.shape[0], dims)
X_test = images_test.reshape(images_test.shape[0], dims)
## CONV NN
# X_train = images_train.reshape(images_train.shape[0], 28,28,1)
# X_test = images_test.reshape(images_test.shape[0], 28,28,1)
print("Training Shape:", X_train.shape)
print("Testing Shape:", X_test.shape)
X_train = X_train.astype('float32') / 255
#ignore warning messages
import warnings
warnings.filterwarnings('ignore')
sns.set()
# pip install emnist
# Import Dataset(s)
from emnist import list_datasets
list_datasets()
from emnist import extract_training_samples
images_train, labels_train = extract_training_samples('letters')
from emnist import extract_test_samples
images_test, labels_test = extract_test_samples('letters')
# Flatten Data
dims = images_train.shape[1] * images_train.shape[2]
X_train = images_train.reshape(images_train.shape[0], dims)
X_test = images_test.reshape(images_test.shape[0], dims)
# Rescale to 0 -> 1 by dividing by max pixel value (255)
X_train = X_train.astype('float32') / 255
X_test = X_test.astype('float32') / 255
# One-Hot Encoding
from keras.utils import np_utils # used to convert array of labeled data to one-hot vector
# should be 26 but out of index?
# Effects accuracy as have a class where their will be no results
from google.colab import drive
drive.mount('/content/gdrive/')
# Commented out IPython magic to ensure Python compatibility.
!pip install emnist
import emnist
import tensorflow as tf
from tensorflow import keras
from keras.utils import np_utils
import matplotlib.pyplot as plt
import os
# %matplotlib inline
#Load Dataset
train_data,train_labels=emnist.extract_training_samples('bymerge')
test_data,test_labels=emnist.extract_test_samples('bymerge')
test=test_labels
plt.imshow(test_data[0])
#Reshaping Training Data to make 28X28 grid image
train_data=train_data.reshape(train_data.shape[0],28,28,1).astype('float32')
test_data=test_data.reshape(test_data.shape[0],28,28,1).astype('float32')
#Normalizing data
train_data=train_data/255
test_data=test_data/255
#One Hot Encoding
train_labels=np_utils.to_categorical(train_labels)
test_labels=np_utils.to_categorical(test_labels)
