def main():
start_time = time()
print("---------- main1 --------------")
f0 = gzip.open('/home/luca/data/mnist/train-images-idx3-ubyte.gz', 'r')
f1 = gzip.open('/home/luca/data/mnist/t10k-images-idx3-ubyte.gz', 'r')
l0 = gzip.open('/home/luca/data/mnist/train-labels-idx1-ubyte.gz', 'r')
l1 = gzip.open('/home/luca/data/mnist/t10k-labels-idx1-ubyte.gz', 'r')
X_train = np.frombuffer(f0.read(), dtype=np.uint8,
offset=16).reshape(-1, 28 * 28)
X_test = np.frombuffer(f1.read(), dtype=np.uint8,
offset=16).reshape(-1, 28 * 28)
y_train = np.frombuffer(l0.read(), dtype=np.uint8, offset=8)
y_test = np.frombuffer(l1.read(), dtype=np.uint8, offset=8)
y_train = one_hot_encoding(y_train)
y_label = one_hot_encoding(y_test)
mean = np.mean(X_train)
std = np.std(X_train)
X_train, X_test = X_train - mean, X_test - mean
X_train, X_test = X_train / std, X_test / std
model = neural_network((89, 'TanH'), (10, 'Sigmoid'),
input_nodes=784,
seed=20190119)
model = fit(x_train=X_train,
y_train=y_train,
x_test=X_test,
y_test=y_label,
model=model,
optimizer=sgd(epochs=50,
eta=0.35,
etaN=0.15,
decay_type='exponential'),
batch_size=60,
eval_every=5,
early_stop=True,
seed=20190119)
validate_accuracy(x_test=X_test, y_test=y_test, model=model)
# print(model[0][0][0].shape)
# print(np.sum(model[0][0][0]))
# print(model[0][0][1].shape)
# print(np.sum(model[0][0][1]))
#
# print(model[1][0][0].shape)
# print(np.sum(model[1][0][0]))
# print(model[1][0][1].shape)
# print(np.sum(model[1][0][1]))
# print()
print("--- %s seconds ---" % (time() - start_time))
def main():
start_time = time()
print("---------- main5 --------------")
f0 = gzip.open('/home/luca/data/mnist/train-images-idx3-ubyte.gz', 'r')
f1 = gzip.open('/home/luca/data/mnist/t10k-images-idx3-ubyte.gz', 'r')
l0 = gzip.open('/home/luca/data/mnist/train-labels-idx1-ubyte.gz', 'r')
l1 = gzip.open('/home/luca/data/mnist/t10k-labels-idx1-ubyte.gz', 'r')
X_train = np.frombuffer(f0.read(), dtype=np.uint8,
offset=16).reshape(-1, 28 * 28)
X_test = np.frombuffer(f1.read(), dtype=np.uint8,
offset=16).reshape(-1, 28 * 28)
y_train = np.frombuffer(l0.read(), dtype=np.uint8, offset=8)
y_test = np.frombuffer(l1.read(), dtype=np.uint8, offset=8)
y_train = one_hot_encoding(y_train)
y_label = one_hot_encoding(y_test)
mean = np.mean(X_train)
std = np.std(X_train)
X_train, X_test = X_train - mean, X_test - mean
X_train, X_test = X_train / std, X_test / std
model = neural_network((89, 'TanH'), (10, 'Softmax'),
input_nodes=784,
seed=20190119,
weight_init='scaled')
model = fit(x_train=X_train,
y_train=y_train,
x_test=X_test,
y_test=y_label,
model=model,
optimizer=sgd(epochs=50,
eta=0.15,
etaN=0.05,
decay_type='exponential',
beta=0.85),
batch_size=60,
eval_every=5,
early_stop=True,
loss_function='cross-entropy',
seed=20190119,
dropout=0.8)
validate_accuracy(x_test=X_test, y_test=y_test, model=model)
print("--- %s seconds ---" % (time() - start_time))
print(train_set_x.shape)
print(test_set_x_orig.shape)
test_set_x = test_set_x_orig
print(test_set_x.shape)
num_px = train_set_x_orig.shape[1]
X = train_set_x / 255
Y = train_set_y
X_test = test_set_x / 255
Y_test = test_set_y
print(Y)
print(Y_test)
print("Y_test.shape : " + str(Y_test.shape))
#print("X_test.shape : " + str(X_test.shape))
dict = one_hot_encoding(dict={"Y": Y, "Y_test": Y_test})
Y = dict["Y"]
Y_test = dict["Y_test"]
print(Y)
print(Y_test)
print("Y.shape : " + str(Y.shape))
print("X.shape : " + str(X.shape))
print("Y_test.shape : " + str(Y_test.shape))
print("X_test.shape : " + str(X_test.shape))
elif dataset_option == "S":
train_set_x_orig, train_set_y, test_set_x_orig, test_set_y, classes = load_dataset_SIGNS(
)
train_set_x = train_set_x_orig
print(train_set_x.shape)
X_test = test_set_x / 255
Y_test = test_set_y
print(Y_test)
# Normalize Inputs
# Normailze Mean
X -= np.mean(X, axis=0)
X_test -= np.mean(X_test, axis=0)
# Normalize Variance
X /= np.var(X, axis=0)
X_test /= np.var(X_test, axis=0)
# One Hot Encoding
dict = {'Y': Y, 'Y_test': Y_test}
dict = one_hot_encoding(dict)
Y = dict['Y']
Y_test = dict["Y_test"]
del dict
print(Y)
print("Y.shape : " + str(Y.shape))
print("X.shape : " + str(X.shape))
print("Y_test.shape : " + str(Y_test.shape))
print("X_test.shape : " + str(X_test.shape))
elif dataset_option == "N":
#test = sio.loadmat('datasets/Digit_Classification-BigDataset.mat')
#X = test['X'][:]
#Y = test['Y'][:]
tot_bedrooms_clear = tot_bedrooms[
~np.isnan(tot_bedrooms)] # removing NaN values
median = np.median(
tot_bedrooms_clear) # computing the median of the distribution
tot_bedrooms.fillna(median,
inplace=True) # replacing NaN values with median value
dataset[
'total_bedrooms'] = tot_bedrooms # assigning fixed feature column to dataset
# second problem: ocean_proximity has categorical values --> one-hot encoding
drop = True
if drop:
dataset_drop = f.one_hot_encoding(dataset, drop=drop)
# put the label column at the end of the dataset
label = dataset_drop['median_house_value']
dataset_drop.pop('median_house_value')
dataset_drop['median_house_value'] = label
# show the correlation between variables
plt.figure(figsize=(15, 8))
corr = dataset_drop.corr()
mask = np.zeros_like(corr, dtype=np.bool)
mask[np.triu_indices_from(mask)] = True
sb.heatmap(abs(corr),
linewidths=.5,
annot=True,
mask=mask,
