def keras(self, img):
return keras.apply_affine_transform(img, theta=45, channel_axis=2, fill_mode='reflect')
def keras(self, img):
return keras.apply_affine_transform(img, theta=45, tx=50, ty=50, zx=0.5, zy=0.5, fill_mode='reflect')
def random_rotate(img, mask, rotate_limit=(-20, 20), u=0.5):
if np.random.random() < u:
theta = np.random.uniform(rotate_limit[0], rotate_limit[1])
img = image.apply_affine_transform(img, theta=theta)
mask = image.apply_affine_transform(mask, theta=theta)
return img, mask
def shift(x, wshift, hshift, row_axis=0, col_axis=1, channel_axis=2, fill_mode='nearest', cval=0.):
h, w = x.shape[row_axis], x.shape[col_axis]
tx = hshift * h
ty = wshift * w
x = image.apply_affine_transform(x, ty=ty, tx=tx)
return x
def keras(self, img):
img = keras.apply_affine_transform(img,
theta=45,
channel_axis=2,
fill_mode="reflect")
return np.ascontiguousarray(img)
def keras(self, img):
return keras.apply_affine_transform(img,
theta=45,
channel_axis=2,
fill_mode='reflect')
def random_shear(img, intensity_range=(-0.5, 0.5), u=0.5):
if np.random.random() < u:
sh = np.random.uniform(-intensity_range[0], intensity_range[1])
img = image.apply_affine_transform(img, shear=sh)
return img
def keras(self, img):
return keras.apply_affine_transform(img, theta=45, tx=50, ty=50, zx=0.5, zy=0.5, fill_mode='reflect')
def random_zoom(img, mask, zoom_range=(0.8, 1), u=0.5):
if np.random.random() < u:
zx, zy = np.random.uniform(zoom_range[0], zoom_range[1], 2)
img = image.apply_affine_transform(img, zx=zx, zy=zy)
mask = image.apply_affine_transform(mask, zx=zx, zy=zy)
return img, mask
def keras(self, img):
img = keras.apply_affine_transform(img, theta=45, tx=50, ty=50, zx=0.5, zy=0.5, fill_mode="reflect")
return np.ascontiguousarray(img)
]
if len(arr.shape) != 3 or arr.shape[2] != 3:
continue
transform_parameters = img_gen.get_random_transform(
arr.shape, seed=attr_count_crop[key])
res = img_gen.random_transform(arr, seed=attr_count_crop[key])
x = np.zeros((h, w, 3))
x[int(bbox[1] * h):int(bbox[3] * h) - 1,
int(bbox[0] * w):int(bbox[2] * w) - 1, 0] = 100
x = apply_affine_transform(
x,
transform_parameters.get('theta', 0),
transform_parameters.get('tx', 0),
transform_parameters.get('ty', 0),
transform_parameters.get('shear', 0),
transform_parameters.get('zx', 1),
transform_parameters.get('zy', 1),
row_axis=0,
col_axis=1,
channel_axis=2,
fill_mode='nearest',
cval=0.)
if transform_parameters.get('flip_horizontal', False):
x = flip_axis(x, 1)
if transform_parameters.get('flip_vertical', False):
x = flip_axis(x, 0)
x = x[:, :, 0]
arr_h = np.max(x, axis=1)
arr_w = np.max(x, axis=0)
i = 0
while (i < h and arr_h[i] < 1e-14):
