def gen_layers_for_image(i, img):
"""
Generate laplacian pyramids and normalize every channel of every
pyramid.
"""
img = resize(img[:, :, :], requested_shape)
new_imgs = yuv_laplacian_norm(img, requested_shape, 3)
return i, new_imgs
def gen_layers_for_image_hog(i, img):
"""
Generate laplacian pyramids and normalize every channel of every
pyramid of RGB.
Calc HOG of depth at every scale.
"""
img = resize(img[:, :, :], requested_shape)
rgb_img = img[:, :, 0:3]
depth_img = img[:, :, 3]
# transform
rgb_imgs = yuv_laplacian_norm(rgb_img, requested_shape, n_layers=3)
# depth_img = calc_hog(depth_img)
depth_img = depth_img.astype('float32') / 255.0
new_imgs = []
for img in rgb_imgs:
shp = (img.shape[1], img.shape[2])
new_img = np.concatenate(
(img, resize(depth_img, shp).reshape((1, shp[0], shp[1]))), axis=0)
new_imgs.append(new_img)
return i, new_imgs
def gen_layers_for_image(i, img):
layers = yuv_laplacian_norm(img, requested_shape, n_layers)
return i, layers
from dataset.loader_msrc import load_dataset
from preprocessing.transform_in import yuv_laplacian_norm
from preprocessing.transform_out import process_out
# load one sample
sample = None
l = load_dataset("/home/student/Downloads/MSRC_ObjCategImageDatabase_v2/")
print(l)
for s in load_dataset("/home/student/Downloads/MSRC_ObjCategImageDatabase_v2/"):
print(s)
sample = s
break
shape = (216, 320)
# process input image
x = yuv_laplacian_norm(s.image, shape)
print "x shape", x[0].shape
print x
pylab.imshow(x[0][0])
pylab.show()
# process output image
cc = ClassCounter()
y = process_out(s.marked_image, cc, shape)
print "y shape", y.shape
print y
pylab.imshow(y)
pylab.show()
def gen_layers_for_image(i, img):
# 3 layers, lapacian pyramid
layers = yuv_laplacian_norm(img, requested_shape, 3)
return i, layers
import pylab
from preprocessing.class_counter import ClassCounter
from dataset.loader_msrc import load_dataset
from preprocessing.transform_in import yuv_laplacian_norm
from preprocessing.transform_out import process_out
# load one sample
sample = None
for s in load_dataset("/media/Win/Data/MSRC_images"):
sample = s
break
shape = (216, 320)
# process input image
x = yuv_laplacian_norm(s.image, shape)
print "x shape", x[0].shape
print x
pylab.imshow(x[0][0])
pylab.show()
# process output image
cc = ClassCounter()
y = process_out(s.marked_image, cc, shape)
print "y shape", y.shape
print y
pylab.imshow(y)
pylab.show()
def gen_layers_for_image(i, img):
layers = yuv_laplacian_norm(img, requested_shape, n_layers)
return i, layers