def trainTransform(self, rgb, depth):
s = np.random.uniform(1.0, 1.5) # random scaling
depth_np = depth / s
angle = np.random.uniform(-5.0, 5.0) # random rotation degrees
do_flip = np.random.uniform(0.0, 1.0) < 0.5 # random horizontal flip
# perform 1st step of data augmentation
first_resize = tuple(
map(
int,
list((250.0 / IMAGE_HEIGHT) *
np.array([IMAGE_HEIGHT, IMAGE_WIDTH]))))
second_resize = tuple(
map(int, list(s * np.array([IMAGE_HEIGHT, IMAGE_WIDTH]))))
transform = T.Compose([
T.Resize(
first_resize
), # this is for computational efficiency, since rotation can be slow
T.Rotate(angle),
T.Resize(second_resize),
T.CenterCrop((228, 304)),
T.HorizontalFlip(do_flip),
T.Resize(self.output_size),
])
rgb_np = transform(rgb)
rgb_np = self.color_jitter(rgb_np) # random color jittering
rgb_np = np.asfarray(rgb_np, dtype='float') / 255
depth_np = transform(depth_np)
return rgb_np, depth_np
def validationTransform(self, rgb, depth):
first_resize = tuple(
map(
int,
list((250.0 / IMAGE_HEIGHT) *
np.array([IMAGE_HEIGHT, IMAGE_WIDTH]))))
depth_np = depth
transform = T.Compose([
T.Resize(first_resize),
T.CenterCrop((228, 304)),
T.Resize(self.output_size),
])
rgb_np = transform(rgb)
rgb_np = np.asfarray(rgb_np, dtype='float') / 255
depth_np = transform(depth_np)
return rgb_np, depth_np
