def get_data():
from cs231n.data_utils import load_CIFAR10
cifar10_dir = 'cs231n/datasets/cifar-10-batches-py'
X_train, y_train, X_test, y_test = load_CIFAR10(cifar10_dir)
plot_dataset(X_train, y_train)
num_training = 49000
num_validation = 1000
num_test = 1000
mask = range(num_training, num_training + num_validation)
X_val = X_train[mask]
y_val = y_train[mask]
mask = range(num_training)
X_train = X_train[mask]
y_train = y_train[mask]
mask = range(num_test)
X_test = X_test[mask]
y_test = y_test[mask]
X_train = np.reshape(X_train, (X_train.shape[0], -1))
X_val = np.reshape(X_val, (X_val.shape[0], -1))
X_test = np.reshape(X_test, (X_test.shape[0], -1))
print '[Reshaped] Training data shape: ', X_train.shape, y_train.shape
print '[Reshaped] Validation data shape: ', X_val.shape, y_val.shape
print '[Reshaped] Test data shape: ', X_test.shape, y_test.shape
return X_train, y_train, X_val, y_val, X_test, y_test
def get_CIFAR10_data(num_training=49000, num_validation=1000, num_test=10000):
"""
Load the CIFAR-10 dataset from disk and perform preprocessing to prepare
it for the two-layer neural net classifier. These are the same steps as
we used for the SVM, but condensed to a single function.
"""
# Load the raw CIFAR-10 data
cifar10_dir = 'cs231n/datasets/cifar-10-batches-py'
X_train, y_train, X_test, y_test = load_CIFAR10(cifar10_dir)
# Subsample the data
mask = range(num_training, num_training + num_validation)
X_val = X_train[mask]
y_val = y_train[mask]
mask = range(num_training)
X_train = X_train[mask]
y_train = y_train[mask]
mask = range(num_test)
X_test = X_test[mask]
y_test = y_test[mask]
# Normalize the data: subtract the mean image
mean_image = np.mean(X_train, axis=0)
X_train -= mean_image
X_val -= mean_image
X_test -= mean_image
return X_train, y_train, X_val, y_val, X_test, y_test
def get_CIFAR10_data(num_training=49000, num_validation=1000, num_test=1000):
"""
Load the CIFAR-10 dataset from disk and perform preprocessing to prepare
it for the two-layer neural net classifier.
"""
# Load the raw CIFAR-10 data
cifar10_dir = 'cs231n/datasets/cifar-10-batches-py'
X_train, y_train, X_test, y_test = load_CIFAR10(cifar10_dir)
# Subsample the data
mask = range(num_training, num_training + num_validation)
X_val = X_train[mask]
y_val = y_train[mask]
mask = range(num_training)
X_train = X_train[mask]
y_train = y_train[mask]
mask = range(num_test)
X_test = X_test[mask]
y_test = y_test[mask]
# Normalize the data: subtract the mean image
mean_image = np.mean(X_train, axis=0)
X_train -= mean_image
X_val -= mean_image
X_test -= mean_image
# Reshape data to rows
X_train = X_train.reshape(num_training, -1)
X_val = X_val.reshape(num_validation, -1)
X_test = X_test.reshape(num_test, -1)
return X_train, y_train, X_val, y_val, X_test, y_test
def get_CIFAR10_data(num_training=49000, num_validation=1000, num_test=1000):
"""
Load the CIFAR-10 dataset from disk and perform preprocessing to prepare
it for the two-layer neural net classifier. These are the same steps as
we used for the SVM, but condensed to a single function.
"""
# Load the raw CIFAR-10 data
cifar10_dir = 'cs231n/datasets/cifar-10-batches-py'
X_train, y_train, X_test, y_test = load_CIFAR10(cifar10_dir)
# Subsample the data
mask = range(num_training, num_training + num_validation)
X_val = X_train[mask]
y_val = y_train[mask]
mask = range(num_training)
X_train = X_train[mask]
y_train = y_train[mask]
mask = range(num_test)
X_test = X_test[mask]
y_test = y_test[mask]
# Normalize the data: subtract the mean image
mean_image = np.mean(X_train, axis=0)
X_train -= mean_image
X_val -= mean_image
X_test -= mean_image
# Reshape data to rows
X_train = X_train.reshape(num_training, -1)
X_val = X_val.reshape(num_validation, -1)
X_test = X_test.reshape(num_test, -1)
return X_train, y_train, X_val, y_val, X_test, y_test
def load_data():
# Load the raw CIFAR-10 data.
cifar10_dir = 'cs231n/datasets/cifar-10-batches-py'
X_train, y_train, X_test, y_test = load_CIFAR10(cifar10_dir)
# As a sanity check, we print out the size of the training and test data.
print 'Training data shape: ', X_train.shape
print 'Training labels shape: ', y_train.shape
print 'Test data shape: ', X_test.shape
print 'Test labels shape: ', y_test.shape
# Subsample the data for more efficient code execution in this exercise
num_training = 5000
mask = range(num_training)
X_train = X_train[mask]
y_train = y_train[mask]
num_test = 500
mask = range(num_test)
X_test = X_test[mask]
y_test = y_test[mask]
# visualize_data(X_train, y_train)
# Reshape the image data into rows
X_train = np.reshape(X_train, (X_train.shape[0], -1))
X_test = np.reshape(X_test, (X_test.shape[0], -1))
print X_train.shape, X_test.shape
return X_train, y_train, X_test, y_test, num_test
def get_CIFAR10_data(num_training=49000,
num_validation=1000,
num_test=1000,
num_dev=500):
"""
Load the CIFAR-10 dataset from disk and perform preprocessing to prepare
it for the linear classifier. These are the same steps as we used for the
SVM, but condensed to a single function.
"""
# Load the raw CIFAR-10 data
cifar10_dir = 'cs231n/datasets/cifar-10-batches-py'
# Cleaning up variables to prevent loading data multiple times (which may cause memory issue)
try:
del X_train, y_train
del X_test, y_test
print('Clear previously loaded data.')
except:
pass
X_train, y_train, X_test, y_test = load_CIFAR10(cifar10_dir)
# subsample the data
mask = list(range(num_training, num_training + num_validation))
X_val = X_train[mask]
y_val = y_train[mask]
mask = list(range(num_training))
X_train = X_train[mask]
y_train = y_train[mask]
mask = list(range(num_test))
X_test = X_test[mask]
y_test = y_test[mask]
mask = np.random.choice(num_training, num_dev, replace=False)
X_dev = X_train[mask]
y_dev = y_train[mask]
# Preprocessing: reshape the image data into rows
X_train = np.reshape(X_train, (X_train.shape[0], -1))
X_val = np.reshape(X_val, (X_val.shape[0], -1))
X_test = np.reshape(X_test, (X_test.shape[0], -1))
X_dev = np.reshape(X_dev, (X_dev.shape[0], -1))
# Normalize the data: subtract the mean image
mean_image = np.mean(X_train, axis=0)
X_train -= mean_image
X_val -= mean_image
X_test -= mean_image
X_dev -= mean_image
# add bias dimension and transform into columns
X_train = np.hstack([X_train, np.ones((X_train.shape[0], 1))])
X_val = np.hstack([X_val, np.ones((X_val.shape[0], 1))])
X_test = np.hstack([X_test, np.ones((X_test.shape[0], 1))])
X_dev = np.hstack([X_dev, np.ones((X_dev.shape[0], 1))])
return X_train, y_train, X_val, y_val, X_test, y_test, X_dev, y_dev
def get_CIFAR10_data():
"""
Load the CIFAR-10 dataset from disk and perform preprocessing to prepare
it for the two-layer neural net classifier. These are the same steps as
we used for the SVM, but condensed to a single function.
"""
# Load the raw CIFAR-10 data
cifar10_dir = 'cs231n/datasets/cifar-10-batches-py'
X_train, _, X_test, _ = load_CIFAR10(cifar10_dir)
X = np.concatenate((X_train, X_test), axis =0)
return X
def dataPrepare(cifar10_dir, num_training, num_test):
# Load the raw CIFAR-10 data.
X_train, y_train, X_test, y_test = load_CIFAR10(cifar10_dir)
# As a sanity check, we print out the size of the training and test data.
print('Training data shape: ', X_train.shape)
print('Training labels shape: ', y_train.shape)
print('Test data shape: ', X_test.shape)
print('Test labels shape: ', y_test.shape)
#print
# Training data shape: (50000, 32, 32, 3)
# Training labels shape: (50000,)
# Test data shape: (10000, 32, 32, 3)
# Test labels shape: (10000,)
# Visualize some examples from the dataset.
# We show a few examples of training images from each class.
classes = [
'plane', 'car', 'bird', 'cat', 'deer', 'dog', 'frog', 'horse', 'ship',
'truck'
]
num_classes = len(classes)
samples_per_class = 7
for y, cls in enumerate(classes):
idxs = np.flatnonzero(y_train == y)
idxs = np.random.choice(idxs, samples_per_class, replace=False)
for i, idx in enumerate(idxs):
plt_idx = i * num_classes + y + 1
plt.subplot(samples_per_class, num_classes, plt_idx)
plt.imshow(X_train[idx].astype('uint8'))
plt.axis('off')
if i == 0:
plt.title(cls)
# plt.show()
# Subsample the data for more efficient code execution in this exercise
# Only choose top 5000 in training data
# Only choose top 500 in test data
mask = list(range(num_training))
X_train = X_train[mask]
y_train = y_train[mask]
mask = list(range(num_test))
X_test = X_test[mask]
y_test = y_test[mask]
# Reshape the image data into rows
X_train = np.reshape(X_train, (X_train.shape[0], -1))
X_test = np.reshape(X_test, (X_test.shape[0], -1))
return X_train, y_train, X_test, y_test
def testNearestNeighbour(self):
Xtr, Ytr, Xte, Yte = datautils.load_CIFAR10('../../data/cifar10/')
Xtr_rows = Xtr.reshape(Xtr.shape[0],
32 * 32 * 3) # Xtr_rows becomes 50000 x 3072
Xte_rows = Xte.reshape(Xte.shape[0],
32 * 32 * 3) # Xte_rows becomes 10000 x 3072
Xte_rows = Xte_rows[0:20, :]
Yte = Yte[0:20]
nn = NearestNeighbour()
nn.train(Xtr_rows, Ytr)
Yte_predict = nn.predict(Xte_rows)
print('accuracy: %f' % (np.mean(Yte_predict == Yte)))
def get_datasets(num_train=100, num_test=20, preprocessing=True):
X_train, y_train, X_test, y_test = load_CIFAR10(cifar10_dir)
X_train -= np.mean(np.mean(np.mean(X_train, axis=0), axis=0),
axis=0) ###data preprocessing
X_train = X_train.reshape((X_train.shape[0], -1))
X_train = X_train[:num_train]
y_train = y_train[:num_train]
X_test -= np.mean(np.mean(np.mean(X_test, axis=0), axis=0),
axis=0) ###data preprocessing
X_test = X_test.reshape((X_test.shape[0], -1))
X_test = X_test[:num_test]
y_test = y_test[:num_test]
return X_train, y_train, X_test, y_test
def get_CIFAR10_data(num_training=49000,
num_validation=1000,
num_test=1000,
num_dev=500):
"""
Load the CIFAR-10 dataset from disk and perform preprocessing to prepare
it for the linear classifier. These are the same steps as we used for the
SVM, but condensed to a single function.
"""
# Load the raw CIFAR-10 data
current_file = os.getcwd()
cifar10_dir = current_file + '\cs231n\datasets\cifar-10-python\cifar-10-batches-py'
X_train, y_train, X_test, y_test = load_CIFAR10(cifar10_dir)
# subsample the data
mask = list(range(num_training, num_training + num_validation))
X_val = X_train[mask]
y_val = y_train[mask]
mask = list(range(num_training))
X_train = X_train[mask]
y_train = y_train[mask]
mask = list(range(num_test))
X_test = X_test[mask]
y_test = y_test[mask]
mask = np.random.choice(num_training, num_dev, replace=False)
X_dev = X_train[mask]
y_dev = y_train[mask]
# Preprocessing: reshape the image data into rows
X_train = np.reshape(X_train, (X_train.shape[0], -1))
X_val = np.reshape(X_val, (X_val.shape[0], -1))
X_test = np.reshape(X_test, (X_test.shape[0], -1))
X_dev = np.reshape(X_dev, (X_dev.shape[0], -1))
# Normalize the data: subtract the mean image
mean_image = np.mean(X_train, axis=0)
X_train -= mean_image
X_val -= mean_image
X_test -= mean_image
X_dev -= mean_image
# add bias dimension and transform into columns
X_train = np.hstack([X_train, np.ones((X_train.shape[0], 1))])
X_val = np.hstack([X_val, np.ones((X_val.shape[0], 1))])
X_test = np.hstack([X_test, np.ones((X_test.shape[0], 1))])
X_dev = np.hstack([X_dev, np.ones((X_dev.shape[0], 1))])
# the last column is the bias parameter . WX+b
return X_train, y_train, X_val, y_val, X_test, y_test, X_dev, y_dev
def get_CIFAR10_data(num_training=49000,
num_validation=1000,
num_test=1000,
num_dev=500):
"""
Load the CIFAR-10 dataset from disk and perform preprocessing to prepare
it for the linear classifier. These are the same steps as we used for the
SVM, but condensed to a single function.
"""
# Load the raw CIFAR-10 data
cifar10_dir = 'cs231n/datasets/cifar-10-batches-py'
X_train, y_train, X_test, y_test = load_CIFAR10(cifar10_dir)
# subsample the data
mask = range(num_training, num_training + num_validation)
X_val = X_train[mask]
y_val = y_train[mask]
mask = range(num_training)
X_train = X_train[mask]
y_train = y_train[mask]
mask = range(num_test)
X_test = X_test[mask]
y_test = y_test[mask]
mask = np.random.choice(num_training, num_dev, replace=False)
X_dev = X_train[mask]
y_dev = y_train[mask]
# Preprocessing: reshape the image data into rows
X_train = np.reshape(X_train, (X_train.shape[0], -1))
X_val = np.reshape(X_val, (X_val.shape[0], -1))
X_test = np.reshape(X_test, (X_test.shape[0], -1))
X_dev = np.reshape(X_dev, (X_dev.shape[0], -1))
# Normalize the data: subtract the mean image
# It is along a row (axis=0) because you calculate the mean for a given pixel
# at every coordinate
mean_image = np.mean(X_train, axis=0)
X_train -= mean_image
X_val -= mean_image
X_test -= mean_image
X_dev -= mean_image
# add bias dimension and transform into columns
X_train = np.hstack([X_train, np.ones((X_train.shape[0], 1))])
X_val = np.hstack([X_val, np.ones((X_val.shape[0], 1))])
X_test = np.hstack([X_test, np.ones((X_test.shape[0], 1))])
X_dev = np.hstack([X_dev, np.ones((X_dev.shape[0], 1))])
return X_train, y_train, X_val, y_val, X_test, y_test, X_dev, y_dev
def get_CIFAR10_data(num_training=49000,
num_validation=1000,
num_test=1000,
num_dev=500):
"""
Load the CIFAR-10 dataset from disk and perform preprocessing to prepare
it for the linear classifier. These are the same steps as we used for the
SVM, but condensed to a single function.
"""
# Load the raw CIFAR-10 data
cifar10_dir = os.path.dirname(
'C:\\Users\\Matthew\\Documents\\jerusml_deeplearning\\assignments\\spring1617_assignment1\\cs231n\datasets\\cifar-10-python\\'
)
X_train, y_train, X_test, y_test = load_CIFAR10(cifar10_dir)
# subsample the data
mask = list(range(num_training, num_training + num_validation))
X_val = X_train[mask]
y_val = y_train[mask]
mask = list(range(num_training))
X_train = X_train[mask]
y_train = y_train[mask]
mask = list(range(num_test))
X_test = X_test[mask]
y_test = y_test[mask]
mask = np.random.choice(num_training, num_dev, replace=False)
X_dev = X_train[mask]
y_dev = y_train[mask]
# Preprocessing: reshape the image data into rows
X_train = np.reshape(X_train, (X_train.shape[0], -1))
X_val = np.reshape(X_val, (X_val.shape[0], -1))
X_test = np.reshape(X_test, (X_test.shape[0], -1))
X_dev = np.reshape(X_dev, (X_dev.shape[0], -1))
# Normalize the data: subtract the mean image
mean_image = np.mean(X_train, axis=0)
X_train -= mean_image
X_val -= mean_image
X_test -= mean_image
X_dev -= mean_image
# add bias dimension and transform into columns
X_train = np.hstack([X_train, np.ones((X_train.shape[0], 1))])
X_val = np.hstack([X_val, np.ones((X_val.shape[0], 1))])
X_test = np.hstack([X_test, np.ones((X_test.shape[0], 1))])
X_dev = np.hstack([X_dev, np.ones((X_dev.shape[0], 1))])
return X_train, y_train, X_val, y_val, X_test, y_test, X_dev, y_dev
def get_CIFAR10_data(num_training=49000, num_validation=1000, num_test=1000):
# Load the raw CIFAR-10 data
cifar10_dir = 'cs231n/datasets/cifar-10-batches-py'
X_train, y_train, X_test, y_test = load_CIFAR10(cifar10_dir)
# Subsample the data
mask = list(range(num_training, num_training + num_validation))
X_val = X_train[mask]
y_val = y_train[mask]
mask = list(range(num_training))
X_train = X_train[mask]
y_train = y_train[mask]
mask = list(range(num_test))
X_test = X_test[mask]
y_test = y_test[mask]
return X_train, y_train, X_val, y_val, X_test, y_test
def get_CIFAR10_data(num_training=49000,
num_validation=1000,
num_test=1000,
num_dev=500):
# Load the raw CIFAR-10 data
cifar10_dir = 'cs231n/datasets/cifar-10-batches-py'
X_train, y_train, X_test, y_test = load_CIFAR10(cifar10_dir)
# Our validation set will be num_validation points from the original
# training set.
mask = list(range(num_training, num_training + num_validation))
X_val = X_train[mask]
y_val = y_train[mask]
# Our training set will be the first num_train points from the original
# training set.
mask = list(range(num_training))
X_train = X_train[mask]
y_train = y_train[mask]
# We use the first num_test points of the original test set as our
# test set.
mask = list(range(num_test))
X_test = X_test[mask]
y_test = y_test[mask]
# We will also make a development set, which is a small subset of
# the training set.
mask = np.random.choice(num_training, num_dev, replace=False)
X_dev = X_train[mask]
y_dev = y_train[mask]
# Preprocessing: reshape the image data into rows
X_train = np.reshape(X_train, (X_train.shape[0], -1))
X_val = np.reshape(X_val, (X_val.shape[0], -1))
X_test = np.reshape(X_test, (X_test.shape[0], -1))
X_dev = np.reshape(X_dev, (X_dev.shape[0], -1))
# Normalize the data: subtract the mean image
mean_image = np.mean(X_train, axis=0)
X_train -= mean_image
X_val -= mean_image
X_test -= mean_image
X_dev -= mean_image
# add bias dimension and transform into columns
X_train = np.hstack([X_train, np.ones((X_train.shape[0], 1))])
X_val = np.hstack([X_val, np.ones((X_val.shape[0], 1))])
X_test = np.hstack([X_test, np.ones((X_test.shape[0], 1))])
X_dev = np.hstack([X_dev, np.ones((X_dev.shape[0], 1))])
return X_train, y_train, X_val, y_val, X_test, y_test, X_dev, y_dev
def get_CIFAR10_data(num_training=49000,
num_validation=1000,
num_test=1000,
num_dev=500):
"""
Load the CIFAR-10 dataset from disk and perform preprocessing to prepare
it for the linear classifier.
"""
# Load the raw CIFAR-10 data
cifar10_dir = '../datasets/cifar-10-batches-py'
X_train, y_train, X_test, y_test = load_CIFAR10(cifar10_dir)
# subsample the data
mask = list(range(num_training, num_training + num_validation))
X_val = X_train[mask]
y_val = y_train[mask]
mask = list(range(num_training))
X_train = X_train[mask]
y_train = y_train[mask]
mask = list(range(num_test))
X_test = X_test[mask]
y_test = y_test[mask]
mask = np.random.choice(num_training, num_dev, replace=False)
X_dev = X_train[mask]
y_dev = y_train[mask]
# Preprocessing: reshape the image data into rows
X_train = np.reshape(X_train, (X_train.shape[0], -1))
X_val = np.reshape(X_val, (X_val.shape[0], -1))
X_test = np.reshape(X_test, (X_test.shape[0], -1))
X_dev = np.reshape(X_dev, (X_dev.shape[0], -1))
# Normalize the data: subtract the mean image
mean_image = np.mean(X_train, axis=0)
X_train -= mean_image
X_val -= mean_image
X_test -= mean_image
X_dev -= mean_image
# add bias dimension and transform into columns
X_train = np.hstack([X_train, np.ones((X_train.shape[0], 1))])
X_val = np.hstack([X_val, np.ones((X_val.shape[0], 1))])
X_test = np.hstack([X_test, np.ones((X_test.shape[0], 1))])
X_dev = np.hstack([X_dev, np.ones((X_dev.shape[0], 1))])
return X_train, y_train, X_val, y_val, X_test, y_test, X_dev, y_dev
def main():
plt.rcParams['figure.figsize'] = (10.0, 8.0) # set default size of plots
plt.rcParams['image.interpolation'] = 'nearest'
plt.rcParams['image.cmap'] = 'gray'
# Load data
# Load the raw CIFAR-10 data.
cifar10_dir = 'cs231n/datasets/cifar-10-batches-py'
X_train, y_train, X_test, y_test = load_CIFAR10(cifar10_dir)
# As a sanity check, we print out the size of the training and test data.
print 'Training data shape: ', X_train.shape
print 'Training labels shape: ', y_train.shape
print 'Test data shape: ', X_test.shape
print 'Test labels shape: ', y_test.shape
VisualizeDataSetSamples(X_train, y_train)
def get_CIFAR10_data(num_training=49000, num_validation=1000, num_test=1000):
# Load the raw CIFAR-10 data
cifar10_dir = 'C:\Satan\HW\#cs231n\prog1\cs231n\datasets\cifar-10-batches-py'
X_train, y_train, X_test, y_test = load_CIFAR10(cifar10_dir)
# Subsample the data
mask = range(num_training, num_training + num_validation)
X_val = X_train[mask]
y_val = y_train[mask]
mask = range(num_training)
X_train = X_train[mask]
y_train = y_train[mask]
mask = range(num_test)
X_test = X_test[mask]
y_test = y_test[mask]
return X_train, y_train, X_val, y_val, X_test, y_test
def get_CIFAR10_data(num_training=49000, num_validation=1000, num_test=1000): # Load the raw CIFAR-10 data cifar10_dir = 'cs231n/datasets/cifar-10-batches-py' X_train, y_train, X_test, y_test = load_CIFAR10(cifar10_dir) # Subsample the data mask = range(num_training, num_training + num_validation) X_val = X_train[mask] y_val = y_train[mask] mask = range(num_training) X_train = X_train[mask] y_train = y_train[mask] mask = range(num_test) X_test = X_test[mask] y_test = y_test[mask] return X_train, y_train, X_val, y_val, X_test, y_test
def get_CIFAR10_data(num_training=16000, num_validation=1000, num_test=1000): # Load the raw CIFAR-10 data cifar10_dir = 'F:/jupyter/assignment1/cs231n/datasets/CIFAR10/' X_train, y_train, X_test, y_test = load_CIFAR10(cifar10_dir) # Subsample the data mask = range(num_training, num_training + num_validation) X_val = X_train[mask] y_val = y_train[mask] mask = range(num_training) X_train = X_train[mask] y_train = y_train[mask] mask = range(num_test) X_test = X_test[mask] y_test = y_test[mask] return X_train, y_train, X_val, y_val, X_test, y_test
def testKNearestNeightbour(self):
test_images = 10
validation_accuracies = []
Xtr, Ytr, Xte, Yte = datautils.load_CIFAR10('../../data/cifar10/')
Xtr_rows = Xtr.reshape(Xtr.shape[0],
32 * 32 * 3) # Xtr_rows becomes 50000 x 3072
Xte_rows = Xte.reshape(Xte.shape[0],
32 * 32 * 3) # Xte_rows becomes 10000 x 3072
Xte_rows = Xte_rows[0:test_images, :]
Yte = Yte[0:test_images]
nn = KNearestNeighbour()
nn.train(Xtr_rows, Ytr)
for k in [1, 3, 5, 7, 10, 20, 50, 10]:
Yte_predict = nn.predict(Xte_rows, k)
acc = np.mean(Yte_predict == Yte)
print('accuracy: %f' % acc)
validation_accuracies.append(acc)
plt.bar(validation_accuracies)
def get_CIFAR10_data(num_training=49000, num_validation=1000, num_test=1000, num_dev=500): """ Load the CIFAR-10 dataset from disk and perform preprocessing to prepare it for the linear classifier. These are the same steps as we used for the SVM, but condensed to a single function. """ # Load the raw CIFAR-10 data cifar10_dir = 'cs231n/datasets/cifar-10-batches-py' X_train, y_train, X_test, y_test = load_CIFAR10(cifar10_dir) # subsample the data mask = range(num_training, num_training + num_validation) X_val = X_train[mask] y_val = y_train[mask] mask = range(num_training) X_train = X_train[mask] y_train = y_train[mask] mask = range(num_test) X_test = X_test[mask] y_test = y_test[mask] mask = np.random.choice(num_training, num_dev, replace=False) X_dev = X_train[mask] y_dev = y_train[mask] # Preprocessing: reshape the image data into rows X_train = np.reshape(X_train, (X_train.shape[0], -1)) X_val = np.reshape(X_val, (X_val.shape[0], -1)) X_test = np.reshape(X_test, (X_test.shape[0], -1)) X_dev = np.reshape(X_dev, (X_dev.shape[0], -1)) # Normalize the data: subtract the mean image mean_image = np.mean(X_train, axis = 0) X_train -= mean_image X_val -= mean_image X_test -= mean_image X_dev -= mean_image # add bias dimension and transform into columns X_train = np.hstack([X_train, np.ones((X_train.shape[0], 1))]) X_val = np.hstack([X_val, np.ones((X_val.shape[0], 1))]) X_test = np.hstack([X_test, np.ones((X_test.shape[0], 1))]) X_dev = np.hstack([X_dev, np.ones((X_dev.shape[0], 1))]) return X_train, y_train, X_val, y_val, X_test, y_test, X_dev, y_dev
def getQoS(self):
X_train, y_train, X_test, y_test = load_CIFAR10(self.data_path)
X_test = np.reshape(X_test, (X_test.shape[0], -1))
X_train = np.reshape(X_train, (X_train.shape[0], -1))
mean_image = np.mean(X_train, axis=0)
X_test -= mean_image
X_test = np.hstack([X_test, np.ones((X_test.shape[0], 1))])
svm = LinearSVM()
try:
svm.W = pickle.load(open(self.run_dir + "model_svm.p", "rb"),
encoding='latin1')
y_test_pred = svm.predict(X_test)
test_accuracy = np.mean(y_test == y_test_pred)
except:
test_accuracy = 0.0
return test_accuracy * 100.0
def get_CIFAR10_data(num_training=49000,
num_validation=1000,
num_test=1000,
num_dev=500):
# Load the raw CIFAR-10 data
cifar10_dir = 'cs231n/datasets/cifar-10-batches-py'
X_train, y_train, X_test, y_test = load_CIFAR10(cifar10_dir)
# sampling the data
mask = range(num_training, num_training + num_validation)
X_val = X_train[mask]
y_val = y_train[mask]
mask = range(num_training)
X_train = X_train[mask]
y_train = y_train[mask]
mask = range(num_test)
X_test = X_test[mask]
y_test = y_test[mask]
mask = np.random.choice(num_training, num_dev, replace=False)
X_dev = X_train[mask]
y_dev = y_train[mask]
#reshape the image data into rows
X_train = np.reshape(X_train, (X_train.shape[0], -1))
X_val = np.reshape(X_val, (X_val.shape[0], -1))
X_test = np.reshape(X_test, (X_test.shape[0], -1))
X_dev = np.reshape(X_dev, (X_dev.shape[0], -1))
#Normalizing the data around center by subtracting it with mean value of pixel values
mean_image = np.mean(X_train, axis=0)
X_train -= mean_image
X_val -= mean_image
X_test -= mean_image
X_dev -= mean_image
# for converting into columns , adding a bias
X_train = np.hstack([X_train, np.ones((X_train.shape[0], 1))])
X_val = np.hstack([X_val, np.ones((X_val.shape[0], 1))])
X_test = np.hstack([X_test, np.ones((X_test.shape[0], 1))])
X_dev = np.hstack([X_dev, np.ones((X_dev.shape[0], 1))])
return X_train, y_train, X_val, y_val, X_test, y_test, X_dev, y_dev
def get_CIFAR10_data(num_training = 49000, num_validation = 1000, num_test = 1000, num_dev = 500):
#加载原始cifar10数据
X_train, y_train, X_test, y_test = load_CIFAR10(r"C:\Users\Michael-School\PycharmProjects\datasets\cifar-10-batches-py")
# print("X_train:",np.shape(X_train)) #(50000, 32, 32, 3)
# print("y_train:",np.shape(y_train)) #(50000,)
# print("X_test:",np.shape(X_test)) #X_test: (10000, 32, 32, 3)
# print("y_test",np.shape(y_test)) #y_test (10000,)
#对数据二次采样：从数据集中取数据子集用于后面的训练
mask = list(range(num_training, num_training + num_validation))
X_val = X_train[mask]
y_val = y_train[mask]
mask = list(range(num_training))
X_train = X_train[mask]
y_train = y_train[mask]
mask = list(range(num_test))
X_test = X_test[mask]
y_test = y_test[mask]
mask = np.random.choice(num_training, num_dev, replace=False)
X_dev = X_train[mask]
y_dev = y_train[mask]
#数据预处理：将一幅图像变成一行存在相应的矩阵里
X_train = np.reshape(X_train, (X_train.shape[0], -1))
X_val = np.reshape(X_val, (X_val.shape[0], -1))
X_test = np.reshape(X_test, (X_test.shape[0], -1))
X_dev = np.reshape(X_dev, (X_dev.shape[0], -1))
#标准化数据：先求平均图像，再将每个图像都减去平均图像，这样预处理可以加速后期优化过程中权重参数的收敛性
mean_image = np.mean(X_train, axis=0)
X_train -= mean_image
X_val -= mean_image
X_test -= mean_image
X_dev -= mean_image
#增加偏置的维度：在原矩阵后加一个全是1的列
X_train = np.hstack([X_train, np.ones((X_train.shape[0], 1))])
X_val = np.hstack([X_val, np.ones((X_val.shape[0], 1))])
X_test = np.hstack([X_test, np.ones((X_test.shape[0], 1))])
X_dev = np.hstack([X_dev, np.ones((X_dev.shape[0], 1))])
return X_train, y_train, X_val, y_val, X_test, y_test, X_dev, y_dev
def get_CIFAR10_data(num_training=49000, num_validation=1000, num_test=1000):
"""
Load the CIFAR-10 dataset from disk and perform preprocessing to prepare
it for the two-layer neural net classifier. These are the same steps as
we used for the SVM, but condensed to a single function.
"""
# Load the raw CIFAR-10 data
cifar10_dir = 'cs231n/datasets/cifar-10-batches-py'
# Cleaning up variables to prevent loading data multiple times (which may cause memory issue)
try:
del X_train, y_train
del X_test, y_test
print('Clear previously loaded data.')
except:
pass
X_train, y_train, X_test, y_test = load_CIFAR10(cifar10_dir)
# Subsample the data
mask = list(range(num_training, num_training + num_validation))
X_val = X_train[mask]
y_val = y_train[mask]
mask = list(range(num_training))
X_train = X_train[mask]
y_train = y_train[mask]
mask = list(range(num_test))
X_test = X_test[mask]
y_test = y_test[mask]
# Normalize the data: subtract the mean image
mean_image = np.mean(X_train, axis=0)
X_train -= mean_image
X_val -= mean_image
X_test -= mean_image
# Reshape data to rows
X_train = X_train.reshape(num_training, -1)
X_val = X_val.reshape(num_validation, -1)
X_test = X_test.reshape(num_test, -1)
return X_train, y_train, X_val, y_val, X_test, y_test
def main():
X_train, y_train, X_test, y_test = load_CIFAR10('../cifar-10-batches-py')
num_training = 48000
mask = list(range(num_training))
X_train = X_train[mask]
y_train = y_train[mask]
num_test = 1000
mask = list(range(num_test))
X_test = X_test[mask]
y_test = y_test[mask]
# Reshape the image data into rows
print(X_train.shape)
'''
(48000, 32, 32, 3)
'''
X_train = np.reshape(X_train, (X_train.shape[0], -1))
print(X_train.shape)
'''
(48000, 3072)
'''
X_test = np.reshape(X_test, (X_test.shape[0], -1))
print(X_train.shape, X_test.shape)
'''
(48000, 3072) (1000, 3072)
'''
classifier = KNearestNeighbor()
classifier.train(X_train, y_train)
y_test_pred = classifier.predict(X_test, k=5)
print(y_test_pred)
# Compute and display the accuracy
num_correct = np.sum(y_test_pred == y_test)
accuracy = float(num_correct) / num_test
print('Got %d / %d correct => accuracy: %f' %
(num_correct, num_test, accuracy))
'''
def get_CIFAR10_data(num_training=49000,num_validation=1000,num_test=10000):
cifar10_path = 'cs231n/datasets/cifar-10-batches-py'
X_train, y_train, X_test, y_test = load_CIFAR10(cifar10_path)
mask = range(num_training,num_training+num_validation)
X_val = X_train[mask]
y_val = y_train[mask]
mask = range(num_training)
X_train = X_train[mask]
y_train = y_train[mask]
mask = range(num_test)
X_test = X_test[mask]
y_test = y_test[mask]
mean_image = np.mean(X_train,axis=0)
X_train -= mean_image
X_val -= mean_image
X_test -= mean_image
return X_train,y_train,X_val,y_val,X_test,y_test
def get_CIFAR10_data(num_training=49000, num_validation=1000, num_test=1000): cifar10_dir = 'cs231n/datasets/cifar-10-batches-py' X_train, y_train, X_test, y_test = load_CIFAR10(cifar10_dir) mask = list(range(num_training, num_training + num_validation)) X_val = X_train[mask] y_val = y_train[mask] mask = list(range(num_training)) X_train = X_train[mask] y_train = y_train[mask] mask = list(range(num_test)) X_test = X_test[mask] y_test = y_test[mask] # Normalize the data: subtract the mean image mean_image = np.mean(X_train, axis=0) X_train -= mean_image X_val -= mean_image X_test -= mean_image # Reshape data to rows X_train = X_train.reshape(num_training, -1) X_val = X_val.reshape(num_validation, -1) X_test = X_test.reshape(num_test, -1) return X_train, y_train, X_val, y_val, X_test, y_test
def get_CIFAR10_data(num_training=49000, num_validation=1000, num_test=1000, num_dev=500):
"""
从硬盘中加载cifar-10数据集并预处理，为2层前联接网络分类器作准备. 采取的步骤和SVM
实验中相同，只不过这里把它压缩成了一个函数.
"""
# 加载原始cifar-10数据集
cifar10_dir = 'cs231n/datasets/cifar-10-batches-py'
X_train, y_train, X_test, y_test = load_CIFAR10(cifar10_dir)
# #验证集中的样本是原始训练集中的num_validation(1000)个样本
mask = list(range(num_training, num_training + num_validation))
X_val = X_train[mask]
y_val = y_train[mask]
# 训练集是原始训练集中的前num_training(49000)个样本
mask = list(range(num_training))
X_train = X_train[mask]
y_train = y_train[mask]
# 测试集是原始测试集中的前num_test(1000)个样本
mask = list(range(num_test))
X_test = X_test[mask]
y_test = y_test[mask]
# 预处理 将每张图像(32,32,3)拉伸为一维数组(3072,)
# 各个数据集从四维数组(m,32,32,3) 转型为2维数组(m,3072)
X_train = np.reshape(X_train, (X_train.shape[0], -1))
X_val = np.reshape(X_val, (X_val.shape[0], -1))
X_test = np.reshape(X_test, (X_test.shape[0], -1))
# 预处理 0均值化 减去图像每个像素/特征上的平均值
# 基于训练数据 计算图像每个像素/特征上的平均值
mean_image = np.mean(X_train, axis=0)
# 各个数据集减去基于训练集计算的各个像素/特征的平均值
# (m,3072) - (3072,) 广播运算
X_train -= mean_image
X_val -= mean_image
X_test -= mean_image
return X_train, y_train, X_val, y_val, X_test, y_test
def get_CIFAR10_data(num_training=49000, num_validation=1000, num_test=1000):
"""
Load the CIFAR-10 dataset from disk and perform preprocessing to prepare
it for the two-layer neural net classifier. These are the same steps as
we used for the SVM, but condensed to a single function.
"""
# Load the raw CIFAR-10 data
cifar10_dir = 'cs231n/datasets/cifar-10-batches-py'
X_train, y_train, X_test, y_test = load_CIFAR10(cifar10_dir)
# Subsample the data
mask = range(num_training, num_training + num_validation)
X_val = X_train[mask]
y_val = y_train[mask]
mask = range(num_training)
X_train = X_train[mask]
y_train = y_train[mask]
mask = range(num_test)
X_test = X_test[mask]
y_test = y_test[mask]
# Normalize the data: subtract the mean image
mean_image = np.mean(X_train, axis=0)
X_train -= mean_image
X_val -= mean_image
X_test -= mean_image
# Reshape data to rows
X_train = X_train.reshape(num_training, -1)
X_val = X_val.reshape(num_validation, -1)
X_test = X_test.reshape(num_test, -1)
pca = decomposition.PCA(n_components=None, whiten=False)
X_train = pca.fit_transform(X_train)
X_val = pca.transform(X_val)
X_test = pca.transform(X_test)
return X_train, y_train, X_val, y_val, X_test, y_test
def get_CIFAR10_data(num_training=9000, num_validation=1000, num_test=1000):
"""
Load the CIFAR-10 dataset from disk and perform preprocessing to prepare
it for the linear classifier. These are the same steps as we used for the
SVM, but condensed to a single function.
"""
# Load the raw CIFAR-10 data
cifar10_dir = 'cs231n/datasets/cifar-10-batches-py'
X_train, y_train, X_test, y_test = load_CIFAR10(cifar10_dir)
# subsample the data
mask = range(num_training, num_training + num_validation)
X_val = X_train[mask]
y_val = y_train[mask]
mask = range(num_training)
X_train = X_train[mask]
y_train = y_train[mask]
mask = range(num_test)
X_test = X_test[mask]
y_test = y_test[mask]
# Preprocessing: reshape the image data into rows
X_train = np.reshape(X_train, (X_train.shape[0], -1))
X_val = np.reshape(X_val, (X_val.shape[0], -1))
X_test = np.reshape(X_test, (X_test.shape[0], -1))
# Normalize the data: subtract the mean image
mean_image = np.mean(X_train, axis=0)
X_train -= mean_image
X_val -= mean_image
X_test -= mean_image
# add bias dimension and transform into columns
X_train = np.hstack([X_train, np.ones((X_train.shape[0], 1))]).T
X_val = np.hstack([X_val, np.ones((X_val.shape[0], 1))]).T
X_test = np.hstack([X_test, np.ones((X_test.shape[0], 1))]).T
return X_train, y_train, X_val, y_val, X_test, y_test
def gen_train_test(num_training, num_test):
""" generate training and testing dataset
"""
cifar10_dir = 'cs231n/datasets/cifar-10-batches-py'
X_train, y_train, X_test, y_test = load_CIFAR10(cifar10_dir)
print 'Training data shape: ', X_train.shape
print 'Training labels shape: ', y_train.shape
print 'Test data shape: ', X_test.shape
print 'Test labels shape: ', y_test.shape
# Subsample the data for more efficient code execution
mask = range(num_training)
X_train = X_train[mask]
y_train = y_train[mask]
mask = range(num_test)
X_test = X_test[mask]
y_test = y_test[mask]
# Reshape the image data into rows
X_train = np.reshape(X_train, (X_train.shape[0], -1))
X_test = np.reshape(X_test, (X_test.shape[0], -1))
print X_train.shape, X_test.shape
return X_train, y_train, X_test, y_test
plt.rcParams['image.interpolation'] = 'nearest' plt.rcParams['image.cmap'] = 'gray' # Some more magic so that the notebook will reload external python modules; # see http://stackoverflow.com/questions/1907993/autoreload-of-modules-in-ipython #get_ipython().magic(u'load_ext autoreload') #get_ipython().magic(u'autoreload 2') # ## CIFAR-10 Data Loading and Preprocessing # In[2]: # Load the raw CIFAR-10 data. cifar10_dir = 'cs231n/datasets/cifar-10-batches-py' X_train, y_train, X_test, y_test = load_CIFAR10(cifar10_dir) # As a sanity check, we print out the size of the training and test data. print 'Training data shape: ', X_train.shape print 'Training labels shape: ', y_train.shape print 'Test data shape: ', X_test.shape print 'Test labels shape: ', y_test.shape # In[3]: # Visualize some examples from the dataset. # We show a few examples of training images from each class. classes = ['plane', 'car', 'bird', 'cat', 'deer', 'dog', 'frog', 'horse', 'ship', 'truck'] num_classes = len(classes) #samples_per_class = 7
def test1():
cifar10_dir = 'cs231n/datasets/cifar-10-batches-py'
X_train, y_train, X_test, y_test = load_CIFAR10(cifar10_dir)
print 'Training data shape:', X_train.shape
print 'Training label shape:', y_train.shape
print 'Test data shape:', X_test.shape
print 'Test label shape:', y_test.shape
# classes = ['plane','car','bird','cat','deer','dog','frog','horse','ship','truck']
# num_classes = len(classes)
# sample_per_class = 7
# for y,cls in enumerate(classes):
# idxs = np.flatnonzero(y_train == y)
# idxs = np.random.choice(idxs, sample_per_class, replace=False)
# for i, idx in enumerate(idxs):
# plt_idx = i*num_classes + y + 1
# plt.subplot(sample_per_class, num_classes, plt_idx)
# plt.imshow(X_train[idx].astype('uint8'))
# plt.axis('off')
# if i == 0:
# plt.title(cls)
# plt.savefig("./figures/cifar_sample.png")
# plt.show()
# plt.close()
num_training = 5000
mask = range(num_training)
X_train = X_train[mask]
y_train = y_train[mask]
num_test = 500
mask = range(num_test)
X_test = X_test[mask]
y_test = y_test[mask]
X_train = np.reshape(X_train, (X_train.shape[0],-1))
X_test = np.reshape(X_test,(X_test.shape[0],-1))
print X_train.shape, X_test.shape
from cs231n.classifiers import KNearestNeighbor
classifier = KNearestNeighbor()
classifier.train(X_train, y_train)
# two_loop_time = time_function(classifier.compute_distances_two_loops,X_test)
# print "two loop time %f" % two_loop_time
# one_loop_time = time_function(classifier.compute_distances_one_loop,X_test)
# print "one loop time %f " %one_loop_time
# no_loop_time = time_function(classifier.compute_distances_no_loops,X_test)
# print "no loop time %f "% no_loop_time
dists = classifier.compute_distances_no_loops(X_test)
# dist_one_loop = classifier.compute_distances_one_loop(X_test)
# dist_two_loops = classifier.compute_distances_two_loops(X_test)
#matrix_compare(dists,dist_one_loop)
#matrix_compare(dists,dist_two_loops)
y_test_pred = classifier.predict_labels(dists,k=5)
num_correct = np.sum(y_test_pred == y_test)
accuracy = float(num_correct)/num_test
print "God %d/%d correct => accuracy: %f" %(num_correct, num_test, accuracy)
cross_validate(X_train,y_train)
def Xtrain():
cifar10_dir = 'cs231n/datasets/cifar-10-batches-py'
X_train, y_train, *_ = load_CIFAR10(cifar10_dir)
return X_train
def ytrain():
cifar10_dir = 'cs231n/datasets/cifar-10-batches-py'
X_train, y_train, X_test, y_test = load_CIFAR10(cifar10_dir)
return y_train
