def create_moving_mnist_png(which, frames=FRAMES):
assert which in ['test', 'train', 'val']
# setting up
settings = ProjectVariable()
settings.dataset = 'mnist'
settings.train = False
settings.val = False
settings.test = False
if which == 'train':
settings.train = True
SEED = 6
elif which == 'val':
settings.val = True
SEED = 7
elif which == 'test':
settings.test = True
SEED = 8
else:
SEED = None
np.random.seed(SEED)
mov_mnist_data_folder = os.path.join(PP.moving_mnist_png, which)
if not os.path.exists(mov_mnist_data_folder):
os.mkdir(mov_mnist_data_folder)
label_file = os.path.join(PP.moving_mnist_location,
'labels_%s.csv' % which)
with open(label_file, 'w') as my_file:
pass
# get original mnist
mnist_all = D.load_mnist(settings)
data = np.array(mnist_all[1][0])
labels = np.array(mnist_all[2][0])
# make data
for i in tqdm.tqdm(range(data.shape[0])):
lab = labels[i]
image = data[i][0]
video = None
if lab == 0:
video = move_horizontal(image, frames)
elif lab == 1:
video = move_vertical(image, frames)
elif lab == 2:
video = scale(image, frames)
elif lab == 3:
video = rotate(-1, image, frames)
elif lab == 4:
video = rotate(1, image, frames)
elif lab == 5:
video = move_in_circle(image, frames)
elif lab == 6:
video = scale_up_rotate_clockwise(image, frames)
elif lab == 7:
video = move_horizontal_rotate_counter(image, frames)
elif lab == 8:
video = rotate_clock_and_counter(image, frames)
elif lab == 9:
video = random_transformations(image, frames)
else:
print('Error: lab with value not expected %d' % lab)
# save arrays as pngs
folder = os.path.join(mov_mnist_data_folder, '%d' % i)
if not os.path.exists(folder):
os.mkdir(folder)
for j in range(FRAMES):
im = Image.fromarray(video[j].astype(DTYPE), mode=MODE)
path = os.path.join(folder, '%d.png' % j)
im.save(path)
# save label
with open(label_file, 'a') as my_file:
my_file.write('%d\n' % lab)
import torch
from torch.utils.data import DataLoader, Dataset
import numpy as np
import os
from relative_baseline.omg_emotion.settings import ProjectVariable
from relative_baseline.omg_emotion import data_loading as D
project_variable = ProjectVariable(debug_mode=True)
project_variable.dataset = 'omg_emotion'
project_variable.data_points = [10 * 7, 0, 0]
project_variable.train = True
project_variable.test = False
project_variable.val = False
project_variable.label_type = 'categories'
all_data = D.load_data(project_variable, seed=42)
data = all_data[1][0]
labels = all_data[2][0]
print('gabi')
class FaceLandmarksDataset(Dataset):
"""Face Landmarks dataset."""
def __init__(self, csv_file, root_dir, transform=None):
"""
Args:
csv_file (string): Path to the csv file with annotations.
from relative_baseline.omg_emotion import data_loading as D
from relative_baseline.omg_emotion.settings import ProjectVariable
from relative_baseline.omg_emotion import project_paths as PP
FRAMES = 30
DTYPE = np.uint8
RESAMPLE = Image.BILINEAR
SIDE = 28
MODE = 'L'
PV = ProjectVariable()
PV.dataset = 'mnist'
PV.train = False
PV.val = False
PV.test = True
def get_next_x(x_current, y_current, direction, speed):
x_next = x_current + direction * speed
if x_next > (SIDE - 1) or x_next < 1:
direction *= -1
speed += 1
x_next = x_current + direction * speed
if x_next > (SIDE - 1) or x_next < 1:
print('Something is wrong: x_next=%d' % x_next)
return 0, direction, speed
loc = (x_current, 0, x_current + SIDE, SIDE)
return loc, x_next, y_current, direction, speed
def random_sampling():
project_variable = ProjectVariable(debug_mode=True)
project_variable.dataset = 'mnist'
project_variable.train = False
project_variable.val = True
project_variable.test = False
how_many = 200
num_params = 4
# num_params = 6
# get MNIST images
splits, data, labels = D.load_mnist(project_variable)
data = data[0].numpy()[0:how_many].reshape((how_many, 28, 28))
transformed_mnist = np.zeros((data.shape[0], 28, 28))
if num_params == 6:
params = np.zeros((data.shape[0], 2, 3))
else:
params = np.zeros((data.shape[0], 4))
for i in range(data.shape[0]):
# make transformation grids
out_channels = 1
# 1: theta = torch.nn.init.normal(torch.nn.Parameter(torch.zeros((out_channels, 2, 3))))
# 2: theta = torch.eye(3)[:2] + torch.nn.init.normal(torch.nn.Parameter(torch.zeros((out_channels, 2, 3))), std=0.1)
# 3: theta = torch.eye(3)[:2] + torch.nn.init.normal(torch.nn.Parameter(torch.zeros((out_channels, 2, 3))), std=0.5)
# 4: theta = torch.eye(3)[:2] + torch.nn.init.normal(torch.nn.Parameter(torch.zeros((out_channels, 2, 3))), std=0.5)
# theta[0][0][2] = 0
# theta[0][1][2] = 0
# 5:
scale = torch.nn.init.normal(torch.nn.Parameter(torch.zeros(1)))
rotate = torch.nn.init.normal(torch.nn.Parameter(torch.zeros(1)))
translate_x = torch.nn.init.normal(torch.nn.Parameter(torch.zeros(1)))
translate_y = torch.nn.init.normal(torch.nn.Parameter(torch.zeros(1)))
theta = make_theta_matrix(scale, rotate, translate_x, translate_y)
# theta = torch.zeros((out_channels, 2, 3))
# theta[0][0][0] = scale * torch.cos(rotate)
# theta[0][0][1] = -scale * torch.sin(rotate)
# theta[0][0][2] = translate_x * scale * torch.cos(rotate) - translate_y * scale * torch.sin(rotate)
# theta[0][1][0] = scale * torch.sin(rotate)
# theta[0][1][1] = -scale * torch.cos(rotate)
# theta[0][1][2] = translate_x * scale * torch.sin(rotate) + translate_y * scale * torch.cos(rotate)
grid = F.affine_grid(theta, torch.Size([out_channels, 1, 28, 28]))
# apply transformations to MNIST
d = np.expand_dims(data[i], 0)
d = np.expand_dims(d, 0)
transformed_mnist[i] = F.grid_sample(torch.Tensor(d),
grid).detach().numpy().reshape(
(28, 28))
if num_params == 6:
params[i] = theta.detach().numpy().reshape((2, 3))
else:
params[i] = float(scale), float(rotate), float(translate_x), float(
translate_y)
# save data & visualize
save_location_images = '/scratch/users/gabras/data/convttn3d_project/sanity_check_affine/images'
save_location_log = '/scratch/users/gabras/data/convttn3d_project/sanity_check_affine/log.txt'
if os.path.exists(save_location_log):
os.remove(save_location_log)
for i in range(data.shape[0]):
# make image, before and after
the_mode = 'L'
canvas = Image.new(mode=the_mode, size=(28 + 5 + 28, 28))
im1 = Image.fromarray(data[i].astype(np.uint8), mode=the_mode)
im2 = Image.fromarray(transformed_mnist[i].astype(np.uint8),
mode=the_mode)
canvas.paste(im1, (0, 0))
canvas.paste(im2, (28 + 5, 0))
canvas_path = os.path.join(save_location_images, '%d.jpg' % i)
canvas.save(canvas_path)
# write line
if num_params == 6:
p = params[i].flatten()
line = '%d,%f,%f,%f,%f,%f,%f\n' % (i, p[0], p[1], p[2], p[3], p[4],
p[5])
with open(save_location_log, 'a') as my_file:
my_file.write(line)
else:
p = params[i]
line = '%d,%f,%f,%f,%f\n' % (i, p[0], p[1], p[2], p[3])
with open(save_location_log, 'a') as my_file:
my_file.write(line)