def aug_train(split_dir, mode):
train_dir = split_dir + os.sep + "train"
for subdir, dirs, files in os.walk(train_dir):
for f in files:
file_path = subdir + os.sep + f
if (is_image(f)):
print(file_path)
name, ext = os.path.splitext(f)
img = cv2.imread(file_path)
for i in range(1, 4):
rot_dir = (subdir + os.sep + name + "_aug_" + str(i * 90) +
ext)
if (mode == 'random'):
cv2.imwrite(rot_dir, aug.rotation(img, 0, 'random'))
elif (mode == 'strict'):
cv2.imwrite(rot_dir, aug.rotation(img, i, 'strict'))
else:
print("The mode should be either random | strict")
sys.exit(1)
def preprocess_data(seq_length,
size,
dirname,
path=None,
data=None,
aug_num=1,
save=True):
'''
Parameters
----------
seq_length : int
This is the complete length of each trajectory offset and occupancy,
Note: one-step difference for the offset and occupancy and traj_data.
size : [height, width, channels]
The occupancy grid size and channels:
orientation, speed and position for the neighbors in the vicinity
dirname : string
"train" or "challenge"
path : string, optional
only for extract offsets, traj_data, and occupancy from the original data files
data : numpy, optional
it is the predicted complete trajectories after the first prediction,
it is used to calculate the occupancy in the predicted time.
aug_num : int, optional
the number for augmenting the data by rotation.
save : boolen, optional
Only save the processed training data. The default is True.
Returns
-------
offsets : numpy array
[frameId, userId, x, y, delta_x, delta_y, theata, velocity].
traj_data : numpy array
[frameId, userId, x, y]
Note: this is one-step longer
occupancy : numpy array
[height, width, channels].
'''
start = time.time()
if np.all(data) == None:
data = np.genfromtxt(path, delimiter='')
# challenge dataset have nan for prediction time steps
data = data[~np.isnan(data).any(axis=1)]
dataname = path.split('\\')[-1].split('.')[0]
print("process data %s ..." % dataname)
for r in range(aug_num):
# Agument the data by orientating if the agumentation number if more than one
if r > 0:
data[:, 2:4] = rotation(data[:, 2:4], r / aug_num)
# Get the environment maps
maps = Maps(data)
traj_map = maps.trajectory_map()
orient_map, speed_map = maps.motion_map(max_speed=10)
map_info = [traj_map, orient_map, speed_map]
enviro_maps = concat_maps(map_info)
print("enviro_maps shape", enviro_maps.shape)
offsets = np.reshape(maps.offsets, (-1, seq_length, 8))
print("offsets shape", offsets.shape)
traj_data = np.reshape(maps.sorted_data, (-1, seq_length + 1, 4))
print("traj_data shape", traj_data.shape)
occupancy = circle_group_grid(offsets, maps.sorted_data, size)
print("occupancy shape", occupancy.shape)
if save:
if r == 0:
# Save the original one
np.savez("../processed_data/%s/%s" % (dirname, dataname),
offsets=offsets,
traj_data=traj_data,
occupancy=occupancy)
end = time.time()
else:
# Save the rotated one(s)
np.savez("../processed_data/%s/%s_%.0f" %
(dirname, dataname, r),
offsets=offsets,
traj_data=traj_data,
occupancy=occupancy)
end = time.time()
print("It takes ", round(end - start, 2), "seconds!\n")
else:
return offsets, traj_data, occupancy
test_loader = loader_from_dataset(cifar10_test)
cifar10_normalize_rotate = transforms.Compose([
# transforms.Grayscale(num_output_channels=1),
transforms.RandomRotation((-5, 5)),
transforms.ToTensor(),
transforms.Normalize((0.5, ), (0.5, ))
])
cifar10_test_rotated = datasets.CIFAR10('../data',
train=False,
download=True,
transform=cifar10_normalize_rotate)
test_loader_rotated = loader_from_dataset(cifar10_test_rotated)
augmentations = [
rotation(cifar10_train, cifar10_normalize, angles=range(-5, 6, 1)),
resized_crop(cifar10_train, cifar10_normalize, size=32),
blur(cifar10_train, cifar10_normalize),
rotation_crop_blur(cifar10_train, cifar10_normalize, size=32),
hflip(cifar10_train, cifar10_normalize),
hflip_vflip(cifar10_train, cifar10_normalize),
brightness(cifar10_train, cifar10_normalize),
contrast(cifar10_train, cifar10_normalize)
]
n_channels = 3
size = 32
n_features = n_channels * size * size
n_classes = 10
gamma = 0.003 # gamma hyperparam for RBF kernel exp(-gamma ||x - y||^2). Best gamma is around 0.001--0.003
n_components = 10000
# Construct loader from MNIST dataset, then construct loaders corresponding to
# augmented dataset (wrt to different transformations).
mnist_normalize = transforms.Compose([
transforms.ToTensor(),
transforms.Normalize((0.1307, ), (0.3081, ))
])
mnist_train = datasets.MNIST(
'../data', train=True, download=True, transform=mnist_normalize)
mnist_test = datasets.MNIST(
'../data', train=False, download=True, transform=mnist_normalize)
mnist_train, mnist_valid = get_train_valid_datasets(mnist_train)
train_loader = loader_from_dataset(mnist_train)
valid_loader = loader_from_dataset(mnist_valid)
test_loader = loader_from_dataset(mnist_test)
augmentations = [rotation(mnist_train, mnist_normalize),
resized_crop(mnist_train, mnist_normalize),
blur(mnist_train, mnist_normalize),
rotation_crop_blur(mnist_train, mnist_normalize),
hflip(mnist_train, mnist_normalize),
hflip_vflip(mnist_train, mnist_normalize),
brightness(mnist_train, mnist_normalize),
contrast(mnist_train, mnist_normalize)]
n_features = 28 * 28
n_classes = 10
gamma = 0.003 # gamma hyperparam for RBF kernel exp(-gamma ||x - y||^2). Best gamma is around 0.001--0.003
n_components = 10000
sgd_n_epochs = 15
n_trials = 10