def __call__(self, in_data):
# There are five data augmentation steps
# 1. Color augmentation
# 2. Random expansion
# 3. Random cropping
# 4. Resizing with random interpolation
# 5. Random horizontal flipping
# 6. Random vertical flipping
img, bbox, label = in_data
# 1. Color augmentation
img = random_distort(img)
# 2. Random expansion
if np.random.randint(2):
img, param = transforms.random_expand(img,
fill=self.mean,
return_param=True)
bbox = transforms.translate_bbox(bbox,
y_offset=param['y_offset'],
x_offset=param['x_offset'])
# 3. Random cropping
img, param = random_crop_with_bbox_constraints(img,
bbox,
return_param=True)
bbox, param = transforms.crop_bbox(bbox,
y_slice=param['y_slice'],
x_slice=param['x_slice'],
allow_outside_center=False,
return_param=True)
label = label[param['index']]
# 4. Resizing with random interpolatation
_, H, W = img.shape
img = resize_with_random_interpolation(img, (self.size, self.size))
bbox = transforms.resize_bbox(bbox, (H, W), (self.size, self.size))
# 5. Random horizontal flipping
img, params = transforms.random_flip(img,
x_random=True,
return_param=True)
bbox = transforms.flip_bbox(bbox, (self.size, self.size),
x_flip=params['x_flip'])
# 6. Random vertical flipping
img, params = transforms.random_flip(img,
y_random=True,
return_param=True)
bbox = transforms.flip_bbox(bbox, (self.size, self.size),
y_flip=params['y_flip'])
# Preparation for SSD network
img -= self.mean
mb_loc, mb_label = self.coder.encode(bbox, label)
return img, mb_loc, mb_label
def transform(data, mean, train=True):
img, lable = data
img = img.copy()
img -= mean
size = (224, 224)
if train:
h, w = img.shape[1:]
angles = [i for i in range(0, 360, 10)]
angle = np.random.choice(angles)
img = rotate(img, angle)
rad = angle * np.pi / 180
new_length = int(h / (np.abs(np.cos(rad)) + np.abs(np.sin(rad))))
img = transforms.center_crop(img, (new_length, new_length))
# img = transforms.random_rotate(img, return_param=False)
img = transforms.random_flip(img, x_random=True)
img = transforms.resize(img, size, interpolation=2)
img *= (1.0 / 255.0)
return img, lable
def _add_noise(self, x, expand, angle, offset_range, s_range, r_width):
ratio = random.uniform(1, expand)
out_h, out_w = int(self.crop_size[0] * ratio), int(self.crop_size[1] *
ratio)
x = cv2.resize(x.transpose(1, 2, 0), (out_h, out_w))
if x.shape[2] == 1:
x = cv2.cvtColor(x, cv2.COLOR_GRAY2RGB)
x = x.transpose((2, 0, 1))
# Color augmentation
# if self.pca_sigma != 0:
# x = transforms.pca_lighting(x, self.pca_sigma)
# Random rotate
angle = np.random.uniform(-angle, angle)
x = cv_rotate(x, angle)
# Random flip
x = transforms.random_flip(x, x_random=True, y_random=True)
# Random expand
#if expand_ratio > 1:
# img = transforms.random_expand(img, max_ratio=expand_ratio)
# Random crop
x = transforms.random_crop(x, self.crop_size)
x = random_erasing(x, offset_range, s_range, r_width)
return x
def get_example(self, i):
if self.imgtype == "npy":
img = np.load(self.get_img_path(i))
img = 2 * (np.clip(img, self.base, self.base + self.range) -
self.base) / self.range - 1.0
if len(img.shape) == 2:
img = img[np.newaxis, ]
else:
img = self.img2var(
read_image(self.get_img_path(i), color=self.color))
# img = resize(img, (self.resize_to, self.resize_to))
if self.crop:
H, W = self.crop
else:
H, W = (16 * ((img.shape[1] - 2 * self.random) // 16),
16 * ((img.shape[2] - 2 * self.random) // 16))
if img.shape[1] < H + 2 * self.random or img.shape[
2] < W + 2 * self.random:
p = max(H + 2 * self.random - img.shape[1],
W + 2 * self.random - img.shape[2])
img = np.pad(img, ((0, 0), (p, p), (p, p)), 'edge')
img = random_crop(
center_crop(img, (H + 2 * self.random, W + 2 * self.random)),
(H, W))
if self.random:
img = random_flip(img, x_random=True)
return img.astype(self.dtype)
def transform(images):
input, answer = copy.deepcopy(images)
# rotate
deg = np.random.choice(DEG_RANGE)
input = rotate_image(input, deg)
answer = rotate_image(answer, deg)
# resize
H, W = input.shape[1:]
h_resize = int(np.random.uniform(240, H * 2.0))
w_resize = int(np.random.uniform(320, W * 2.0))
input = chainercv.transforms.resize(input, (h_resize, w_resize))
answer = chainercv.transforms.resize(answer, (h_resize, w_resize))
# crop
input, slice = transforms.random_crop(input, (240, 320), return_param=True)
answer = answer[:, slice["y_slice"], slice['x_slice']]
# flip
input, param = transforms.random_flip(input,
x_random=True,
return_param=True)
if param['x_flip']:
transforms.flip(answer, x_flip=True)
# pca_lighting:
input = transforms.pca_lighting(input, sigma=5)
return resize((input, answer))
def _transform2(data, mean, train=True, mean_flag=False):
img, label = data
img = img.copy()
size316 = (316, 316)
size = (224, 224)
img_o = transforms.scale(img, 316)
img_o = transforms.center_crop(img_o, size316)
# 学習のときだけ実行
if train:
img_o = transforms.random_flip(img_o, y_random=True)
img_o = transforms.random_rotate(img_o)
# img = random_erase(img)
img_o = transforms.resize(img_o, size)
# 画像から平均を引く
if mean_flag:
img_o -= mean
img_o *= (1.0 / 255.0)
r = random.randint(316, 1500)
img_st = transforms.scale(img, r)
img_st = transforms.center_crop(img_st, (224, 224))
# 画像から平均を引く
if mean_flag:
img_st -= mean
img_st *= (1.0 / 255.0)
return img_o, label, img_st
def transform(in_data):
img, bbox, label = in_data
img, params = transforms.random_flip(img, x_random=True, return_param=True)
bbox = transforms.flip_bbox(bbox, img.shape[1:], x_flip=params['x_flip'])
return img, bbox, label
def __call__(self, in_data):
img, label = in_data
img = random_sized_crop(img)
img = resize(img, (224, 224))
img = random_flip(img, x_random=True)
img -= self.mean
return img, label
def get_example(self, index):
x, y = super().get_example(index)
# random_expandをする代わりに、最初に target_size * random_expandの大きさにリサイズしておいて、
# あとでrandom croppingすればいいのではないかと思いました
ratio = random.uniform(1, self.expand_ratio)
out_h, out_w = int(
self.crop_size[0] * ratio), int(self.crop_size[1] * ratio)
x = cv2.resize(x.transpose(1, 2, 0), (out_h, out_w))
# x = cv2.resize(x.transpose(1,2,0), (128, 128))
if x.shape[2] == 1:
x = cv2.cvtColor(x, cv2.COLOR_GRAY2RGB)
x = x.transpose((2, 0, 1))
if self.train:
# Color augmentation
# if self.pca_sigma != 0:
# x = transforms.pca_lighting(x, self.pca_sigma)
# Random rotate
if self.random_angle != 0:
angle = np.random.uniform(-self.random_angle,
self.random_angle)
x = cv_rotate(x, angle)
# Random flip
x = transforms.random_flip(x, x_random=True, y_random=True)
# Random expand
# if expand_ratio > 1:
# img = transforms.random_expand(img, max_ratio=expand_ratio)
# Random crop
x = transforms.random_crop(x, self.crop_size)
x /= 255.0
return x, y
def transform(inputs):
img, label = inputs
img = img.copy()
img = pad(img, pad=4)
img = transforms.random_flip(img, x_random=True)
img = transforms.random_crop(img, (32, 32))
return img, label
def _transform(data, mean, train=True, mean_flag=False):
img, label = data
img = img.copy()
size316 = (316, 316)
size = (224, 224)
img = transforms.scale(img, 316)
img = transforms.center_crop(img, size316)
# 学習のときだけ実行
if train:
img = transforms.random_rotate(img)
img = transforms.random_flip(img, x_random=True, y_random=True)
# imgのリサイズ
img = img.transpose(1, 2, 0)
img = resize(img, size)
# 画像から平均を引く
if mean_flag:
img -= mean
print("mean use")
img *= (1.0 / 255.0)
img = img.transpose(2, 0, 1)
return img, label
def transform(
inputs, mean, std, random_angle=15., pca_sigma=255., expand_ratio=1.0,
crop_size=(32, 32), train=True):
img, label = inputs
img = img.copy()
# Random rotate
if random_angle != 0:
angle = np.random.uniform(-random_angle, random_angle)
img = cv_rotate(img, angle)
# Color augmentation
if train and pca_sigma != 0:
img = transforms.pca_lighting(img, pca_sigma)
# Standardization
img -= mean[:, None, None]
img /= std[:, None, None]
if train:
# Random flip
img = transforms.random_flip(img, x_random=True)
# Random expand
if expand_ratio > 1:
img = transforms.random_expand(img, max_ratio=expand_ratio)
# Random crop
if tuple(crop_size) != (32, 32):
img = transforms.random_crop(img, tuple(crop_size))
return img, label
def __call__(self, in_data):
if len(in_data) == 4:
img, mask, label, bbox = in_data
else:
img, bbox, label = in_data
# Flipping
img, params = transforms.random_flip(img,
x_random=True,
return_param=True)
x_flip = params['x_flip']
bbox = transforms.flip_bbox(bbox, img.shape[1:], x_flip=x_flip)
# Scaling and mean subtraction
img, scale = scale_img(img, self.min_size, self.max_size)
img -= self.mean
bbox = bbox * scale
if len(in_data) == 4:
mask = transforms.flip(mask, x_flip=x_flip)
mask = transforms.resize(mask.astype(np.float32),
img.shape[1:],
interpolation=PIL.Image.NEAREST).astype(
np.bool)
return img, bbox, label, mask
else:
return img, bbox, label
def transform(inputs,
mean,
std,
random_angle=15.,
expand_ratio=1.0,
crop_size=(32, 32),
train=True):
img, label = inputs
img = img.copy()
# Random rotate
if random_angle != 0:
angle = np.random.uniform(-random_angle, random_angle)
img = cv_rotate(img, angle)
# Cut out
img = cut_out(img)
# Standardization
img -= mean[:, None, None]
img /= std[:, None, None]
if train:
# Random flip
img = transforms.random_flip(img, x_random=True)
# Random expand
if expand_ratio > 1:
img = transforms.random_expand(img, max_ratio=expand_ratio)
# Random crop
if tuple(crop_size) != (32, 32):
img = transforms.random_crop(img, tuple(crop_size))
return img, label
def transform(
inputs, mean, std, random_angle=15., pca_sigma=25.5, expand_ratio=1.2,
crop_size=(28, 28), train=True):
img = inputs
img = img.copy()
# Random rotate
if random_angle != 0:
angle = np.random.uniform(-random_angle, random_angle)
img = cv_rotate(img, angle)
# Color augmentation
if train and pca_sigma != 0:
img = transforms.pca_lighting(img, pca_sigma)
"""
# Standardization
img -= mean[:, None, None]
img /= std[:, None, None]
"""
if train:
# Random flip
img = transforms.random_flip(img, x_random=True)
# Random expand
if expand_ratio > 1:
img = transforms.random_expand(img, max_ratio=expand_ratio)
# Random crop
if tuple(crop_size) != (32, 32):
img = transforms.random_crop(img, tuple(crop_size))
return img
def __call__(self, in_data):
img, label = in_data
img = transforms.random_sized_crop(img)
img = transforms.resize(img, (224, 224))
img = transforms.random_flip(img, x_random=True)
img -= self.mean
return img.astype(chainer.get_dtype()), label
def random_flip(image, keypoints, bbox, is_labeled, is_visible, flip_indices):
"""
random x_flip
Note that if image is flipped, `flip_indices` translate elements.
e.g. left_shoulder -> right_shoulder.
"""
_, H, W = image.shape
image, param = transforms.random_flip(image, x_random=True, return_param=True)
if param['x_flip']:
keypoints = [
transforms.flip_point(points, (H, W), x_flip=True)[flip_indices]
for points in keypoints
]
is_labeled = [label[flip_indices] for label in is_labeled]
is_visible = [vis[flip_indices] for vis in is_visible]
new_bbox = []
for x, y, w, h in bbox:
[[y, x]] = transforms.flip_point(np.array([[y, x + w]]), (H, W), x_flip=True)
new_bbox.append([x, y, w, h])
bbox = new_bbox
return image, keypoints, bbox, is_labeled, is_visible, param
def transform_cifar10(data: Tuple[np.ndarray, np.ndarray],
mean: np.ndarray,
std: np.ndarray,
cutout_length: int,
crop_size=(32, 32),
train=True):
img, label = data
img = img.copy()
# Standardization
img -= mean[:, None, None]
img /= std[:, None, None]
if type(crop_size) == int:
crop_size = (crop_size, crop_size)
if train:
# padding
img = padding(img, pad=4)
# Random flip
img = transforms.random_flip(img, x_random=True)
# Random crop
if crop_size != (32, 32):
img = transforms.random_crop(img, tuple(crop_size))
# cutout
img = cutout(img, cutout_length)
return img.astype(np.float32), label
def get_example(self, i):
image = super().get_example(i)
if image.shape[0] == 1:
image = numpy.tile(image, (3, 1, 1))
if self.augmentations is not None and self.use_imgaug:
image = numpy.transpose(image, (1, 2, 0))
image = image.astype(numpy.uint8)
image = self.augmentations.augment_images([image])[0]
image = image.astype(numpy.float32)
image = numpy.transpose(image, (2, 0, 1))
elif random.random() < self.transform_probability:
if self.crop_always or random.random() <= 0.5:
crop_ratio = random.uniform(self.min_crop_ratio,
self.max_crop_ratio)
image = transforms.random_crop(
image,
tuple(
[int(size * crop_ratio) for size in image.shape[-2:]]))
image = transforms.random_flip(image, x_random=True)
if self.image_size is not None:
image = resize_image(image,
self.image_size,
image_mode=self.image_mode)
if len(image.shape) == 2:
image = image[None, ...]
return image / 255
def __call__(self, in_data):
img, bbox, label = in_data
_, H, W = img.shape
# random brightness and contrast
img = random_distort(img)
# rotate image
# return a tuple whose elements are rotated image, param.
# k (int in param)represents the number of times the image is rotated by 90 degrees.
img, params = transforms.random_rotate(img, return_param=True)
# restore the new hight and width
_, t_H, t_W = img.shape
# rotate bbox based on renewed parameters
bbox = rotate_bbox(bbox, (H, W), params['k'])
img = self.faster_rcnn.prepare(img)
# prepares the image to match the size of the image to be input into the RCNN
_, o_H, o_W = img.shape
# resize the bounding box according to the image resize
bbox = transforms.resize_bbox(bbox, (t_H, t_W), (o_H, o_W))
# horizontally & vertical flip
# simutaneously flip horizontally and vertically of the image
img, params = transforms.random_flip(img,
x_random=True,
y_random=True,
return_param=True)
# flip the bounding box with respect to the parameter
bbox = transforms.flip_bbox(bbox, (o_H, o_W),
x_flip=params['x_flip'],
y_flip=params['y_flip'])
scale = o_H / t_H
return img, bbox, label, scale
def __call__(self, in_data):
# There are five data augmentation steps
# 3. Random cropping
# 4. Resizing with random interpolation
# 5. Random horizontal flipping
img, bbox, label = in_data
# 3. Random cropping
if self.random_crop and np.random.rand() > 0.5:
next_img, param = random_crop_with_bbox_constraints(
img,
bbox,
min_scale=min(self.crop_rate),
max_scale=max(self.crop_rate),
return_param=True)
next_bbox, param = transforms.crop_bbox(bbox,
y_slice=param['y_slice'],
x_slice=param['x_slice'],
allow_outside_center=False,
return_param=True)
if (len(label[param['index']]) != 0):
label = label[param['index']]
img, bbox = next_img, next_bbox
# 4. Resizing with random interpolatation
_, H, W = img.shape
img = transforms.resize(img, (self.size, self.size))
bbox = transforms.resize_bbox(bbox, (H, W), (self.size, self.size))
# 5. Random horizontal flipping
if self.flip:
img, params = transforms.random_flip(img,
x_random=True,
return_param=True)
bbox = transforms.flip_bbox(bbox, (self.size, self.size),
x_flip=params['x_flip'])
img -= self.mean
img /= self.std
_, height, width = img.shape
ymin = bbox[:, 0]
xmin = bbox[:, 1]
ymax = bbox[:, 2]
xmax = bbox[:, 3]
one_hot_label = np.eye(self.n_class)[label]
xs = (xmin + (xmax - xmin) // 2) / width
ws = (xmax - xmin) / width
ys = (ymin + (ymax - ymin) // 2) / height
hs = (ymax - ymin) / height
t = [{
'label': l,
'x': x,
'w': w,
'y': y,
'h': h,
'one_hot_label': hot
} for l, x, w, y, h, hot in zip(label, xs, ws, ys, hs, one_hot_label)]
return img, t
def get_example(self, i):
img = read_image(self.get_img_path(i), color=self.color)
img = img * 2 / 255.0 - 1.0 # [-1, 1)
# img = resize(img, (self.resize_to, self.resize_to))
img = random_crop(img, self.crop)
if self.flip:
img = random_flip(img, x_random=True)
return img.astype(self.dtype)
def preprocess(self, image):
image = self.normalize(image, self.mean, self.std)
if not self.train:
return image
else:
image = T.random_flip(image, x_random=True)
image = padding(image, 4)
image = T.random_crop(image, (32, 32))
return image
def __call__(self, in_data):
if len(in_data) == 6:
img, bbox, label, mask, crowd, area = in_data
elif len(in_data) == 4:
img, bbox, label, mask = in_data
else:
raise ValueError
img = img.transpose(2, 0, 1) # H, W, C -> C, H, W
if not self.train:
if len(in_data) == 6:
return img, bbox, label, mask, crowd, area
elif len(in_data) == 4:
return img, bbox, label, mask
else:
raise ValueError
imgs, sizes, scales = self.mask_rcnn.prepare([img])
# print(type(imgs))
# print(type(sizes))
# print(type(scales))
img = imgs[0]
H, W = sizes[0]
scale = scales[0]
_, o_H, o_W = img.shape
if len(bbox) > 0:
bbox = transforms.resize_bbox(bbox, (H, W), (o_H, o_W))
if len(mask) > 0:
mask = transforms.resize(
mask, size=(o_H, o_W), interpolation=0)
# # horizontally flip
# img, params = transforms.random_flip(
# img, x_random=True, return_param=True)
# bbox = transforms.flip_bbox(
# bbox, (o_H, o_W), x_flip=params['x_flip'])
# if mask.ndim == 2:
# mask = transforms.flip(
# mask[None, :, :], x_flip=params['x_flip'])[0]
# else:
# mask = transforms.flip(mask, x_flip=params['x_flip'])
# horizontally and vartically flip
img, params = transforms.random_flip(
img, y_random=True, x_random=True, return_param=True)
bbox = transforms.flip_bbox(
bbox, (o_H, o_W), y_flip=params['y_flip'], x_flip=params['x_flip'])
if mask.ndim == 2:
mask = transforms.flip(
mask[None, :, :], y_flip=params['y_flip'], x_flip=params['x_flip'])[0]
else:
mask = transforms.flip(mask, y_flip=params['y_flip'], x_flip=params['x_flip'])
return img, bbox, label, mask, scale, sizes
def __call__(self, in_data):
# 5段階のステップでデータの水増しを行う
# 1. 色の拡張
# 2. ランダムな拡大
# 3. ランダムなトリミング
# 4. ランダムな補完の再補正
# 5. ランダムな水平反転
img, bbox, label = in_data
# 1. 色の拡張
# 明るさ，コントラスト，彩度，色相を組み合わせ，データ拡張をする
img = random_distort(img)
# 2. ランダムな拡大
if np.random.randint(2):
# キャンバスの様々な座標に入力画像を置いて，様々な比率の画像を生成し，bounding boxを更新
img, param = transforms.random_expand(img,
fill=self.mean,
return_param=True)
bbox = transforms.translate_bbox(bbox,
y_offset=param['y_offset'],
x_offset=param['x_offset'])
# 3. ランダムなトリミング
img, param = random_crop_with_bbox_constraints(img,
bbox,
return_param=True)
# トリミングされた画像内にbounding boxが入るように調整
bbox, param = transforms.crop_bbox(bbox,
y_slice=param['y_slice'],
x_slice=param['x_slice'],
allow_outside_center=False,
return_param=True)
label = label[param['index']]
# 4. ランダムな補完の再補正
## 画像とbounding boxのリサイズ
_, H, W = img.shape
img = resize_with_random_interpolation(img, (self.size, self.size))
bbox = transforms.resize_bbox(bbox, (H, W), (self.size, self.size))
# 5. ランダムな水平反転
## 画像とbounding boxをランダムに水平方向に反転
img, params = transforms.random_flip(img,
x_random=True,
return_param=True)
bbox = transforms.flip_bbox(bbox, (self.size, self.size),
x_flip=params['x_flip'])
# SSDのネットワークに入力するための準備の処理
img -= self.mean
## SSDに入力するためのloc(デフォルトbounding boxのオフセットとスケール)と
## mb_label(クラスを表す配列)を出力
mb_loc, mb_label = self.coder.encode(bbox, label)
return img, mb_loc, mb_label
def __call__(self, in_data):
img, bbox, label = in_data
# Flipping
img, params = transforms.random_flip(img,
x_random=True,
return_param=True)
x_flip = params['x_flip']
bbox = transforms.flip_bbox(bbox, img.shape[1:], x_flip=x_flip)
return img, bbox, label
def __call__(self, img):
img = random_crop(img=img, size=self.resize_value)
img = random_flip(img=img, x_random=True)
img = pca_lighting(img=img, sigma=25.5)
img = scale(img=img, size=self.resize_value)
img = center_crop(img, self.input_image_size)
img /= 255.0
img -= self.mean
img /= self.std
return img
def transform(inputs,
mean=None,
std=None,
random_angle=15.,
pca_sigma=255.,
expand_ratio=1.0,
crop_size=(32, 32),
cutout=None,
flip=True,
train=True,
old_test_method=False):
img, label = inputs
img = img.copy()
if train:
# Random rotate
if random_angle != 0:
angle = np.random.uniform(-random_angle, random_angle)
img = cv_rotate(img, angle)
# Color augmentation
if pca_sigma != 0:
img = transforms.pca_lighting(img, pca_sigma)
elif old_test_method:
# There was a bug in prior versions, here it is reactivated to preserve
# the same test accuracy
if random_angle != 0:
angle = np.random.uniform(-random_angle, random_angle)
img = cv_rotate(img, angle)
# Standardization
if mean is not None:
img -= mean[:, None, None]
img /= std[:, None, None]
if train:
# Random flip
if flip:
img = transforms.random_flip(img, x_random=True)
# Random expand
if expand_ratio > 1:
img = transforms.random_expand(img, max_ratio=expand_ratio)
# Random crop
if tuple(crop_size) != (32, 32) or expand_ratio > 1:
img = transforms.random_crop(img, tuple(crop_size))
# Cutout
if cutout is not None:
h0, w0 = np.random.randint(0, 32 - cutout, size=(2, ))
img[:, h0:h0 + cutout, w0:w0 + cutout].fill(0.0)
return img, label
def get_example(self, i):
img = read_image(self.get_img_path(i))
img = img.astype('f')
img = img * 2 / 255.0 - 1.0 # [-1, 1)
img = resize(img, (self.resize_to, self.resize_to))
if self.resize_to > self.crop_to:
img = random_crop(img, (self.crop_to, self.crop_to))
if self.flip:
img = random_flip(img, x_random=True)
return img
def __call__(self, in_data):
img, label = in_data
img = np.pad(img, ((0, 0), (4, 4), (4, 4)), 'constant')
img = random_crop(img, (32, 32))
img = random_flip(img, x_random=True)
img = (img - CIFAR_MEAN[:, None, None]) / CIFAR_STD[:, None, None]
if self.use_cutout:
img = Cutout(self.cutout_length)(img)
return img, label
def transform(in_data):
img, label = in_data
img = img.copy()
img -= mean[:, None, None]
img /= std[:, None, None]
img = T.resize_contain(img, (40, 40))
img = T.random_crop(img, (32, 32))
img = T.random_flip(img, x_random=True)
return img, label
def test_random_flip(self):
img = np.random.uniform(size=(3, 24, 24))
out, param = random_flip(
img, y_random=True, x_random=True, return_param=True)
y_flip = param['y_flip']
x_flip = param['x_flip']
expected = img
if y_flip:
expected = expected[:, ::-1, :]
if x_flip:
expected = expected[:, :, ::-1]
np.testing.assert_equal(out, expected)
def __call__(self, in_data):
img, bbox, label = in_data
_, H, W = img.shape
img = self.faster_rcnn.prepare(img)
_, o_H, o_W = img.shape
scale = o_H / H
bbox = transforms.resize_bbox(bbox, (H, W), (o_H, o_W))
# horizontally flip
img, params = transforms.random_flip(
img, x_random=True, return_param=True)
bbox = transforms.flip_bbox(
bbox, (o_H, o_W), x_flip=params['x_flip'])
return img, bbox, label, scale
def __call__(self, in_data):
# There are five data augmentation steps
# 1. Color augmentation
# 2. Random expansion
# 3. Random cropping
# 4. Resizing with random interpolation
# 5. Random horizontal flipping
img, bbox, label = in_data
# 1. Color augmentation
img = random_distort(img)
# 2. Random expansion
if np.random.randint(2):
img, param = transforms.random_expand(
img, fill=self.mean, return_param=True)
bbox = transforms.translate_bbox(
bbox, y_offset=param['y_offset'], x_offset=param['x_offset'])
# 3. Random cropping
img, param = random_crop_with_bbox_constraints(
img, bbox, return_param=True)
bbox, param = transforms.crop_bbox(
bbox, y_slice=param['y_slice'], x_slice=param['x_slice'],
allow_outside_center=False, return_param=True)
label = label[param['index']]
# 4. Resizing with random interpolatation
_, H, W = img.shape
img = resize_with_random_interpolation(img, (self.size, self.size))
bbox = transforms.resize_bbox(bbox, (H, W), (self.size, self.size))
# 5. Random horizontal flipping
img, params = transforms.random_flip(
img, x_random=True, return_param=True)
bbox = transforms.flip_bbox(
bbox, (self.size, self.size), x_flip=params['x_flip'])
# Preparation for SSD network
img -= self.mean
mb_loc, mb_label = self.coder.encode(bbox, label)
return img, mb_loc, mb_label
