def __call__(self, in_data):
img, bbox, label = in_data
# 1. Color augumentation
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 interpolation
_, 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. Transformation for SSD network input
img -= self.mean
mb_loc, mb_lab = self.coder.encode(bbox, label)
return img, mb_loc, mb_lab
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, bbox, label = in_data
# 1. Color augumentation
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 interpolation
_, 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. Transformation for SSD network input
img -= self.mean
mb_loc, mb_lab = self.coder.encode(bbox, label)
return img, mb_loc, mb_lab
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=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):
# 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 __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 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 test_random_expand(self):
img = np.random.uniform(-1, 1, size=(3, 64, 32))
out = random_expand(img)
out = random_expand(img, max_ratio=1)
np.testing.assert_equal(out, img)
out, param = random_expand(
img, max_ratio=self.max_ratio, return_param=True)
ratio = param['ratio']
y_offset = param['y_offset']
x_offset = param['x_offset']
np.testing.assert_equal(
out[:, y_offset:y_offset + 64, x_offset:x_offset + 32], img)
self.assertGreaterEqual(ratio, 1)
self.assertLessEqual(ratio, self.max_ratio)
self.assertEqual(out.shape[1], int(64 * ratio))
self.assertEqual(out.shape[2], int(32 * ratio))
out = random_expand(img, max_ratio=2)
def test_random_expand(self):
img = np.random.uniform(-1, 1, size=(3, 64, 32))
out = random_expand(img)
out = random_expand(img, max_ratio=1)
np.testing.assert_equal(out, img)
out, param = random_expand(
img, max_ratio=self.max_ratio, return_param=True)
ratio = param['ratio']
y_offset = param['y_offset']
x_offset = param['x_offset']
np.testing.assert_equal(
out[:, y_offset:y_offset + 64, x_offset:x_offset + 32], img)
self.assertGreaterEqual(ratio, 1)
self.assertLessEqual(ratio, self.max_ratio)
self.assertEqual(out.shape[1], int(64 * ratio))
self.assertEqual(out.shape[2], int(32 * ratio))
out = random_expand(img, max_ratio=2)
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
bbox = np.array(bbox).astype(np.float32)
if len(bbox) == 0:
warnings.warn("No bounding box detected", RuntimeWarning)
img = resize_with_random_interpolation(img, (self.size, self.size))
mb_loc, mb_label = self.coder.encode(bbox, label)
return img, mb_loc, mb_label
# 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'])
mb_loc, mb_label = self.coder.encode(bbox, label)
return img, mb_loc, mb_label
def test_random_expand_fill(self):
img = np.random.uniform(-1, 1, size=(3, 64, 32))
while True:
out, param = random_expand(img, fill=self.fill, return_param=True)
y_offset = param['y_offset']
x_offset = param['x_offset']
if y_offset > 0 or x_offset > 0:
break
if isinstance(self.fill, int):
fill = (self.fill, ) * 3
else:
fill = self.fill
np.testing.assert_equal(out[:, 0, 0], np.array(fill).flatten())
def __call__(self, inputs, train=True):
img, label = inputs
img = img.copy()
# Color augmentation
if train and self.pca:
img = transforms.pca_lighting(img, 76.5)
# Standardization
img -= self.mean
img *= self.invstd
# Random crop
if train and self.trans:
img = transforms.random_flip(img, x_random=True)
img = transforms.random_expand(img, max_ratio=1.5)
img = transforms.random_crop(img, (28, 28))
return img, label
def transform_img(inputs,
mean,
std,
pca_sigma=0,
random_angle=0,
x_random_flip=False,
y_random_flip=False,
expand_ratio=1.,
random_crop_size=(224, 224),
random_erase=False,
output_size=(224, 224),
train=False):
x, lab = inputs
x = x.copy()
# Color augmentation
if train and pca_sigma != 0:
x = transforms.pca_lighting(x, pca_sigma)
x -= mean[:, None, None]
x /= std[:, None, None]
x = x[::-1]
if train:
# Random rotate
if random_angle != 0:
angle = np.random.uniform(-random_angle, random_angle)
x = cv_rotate(x, angle)
# Random flip
if x_random_flip or y_random_flip:
x = transforms.random_flip(x,
x_random=x_random_flip,
y_random=y_random_flip)
# Random expand
if expand_ratio > 1:
x = transforms.random_expand(x, max_ratio=expand_ratio)
if all(random_crop_size) > 0:
x = transforms.random_crop(x, random_crop_size)
else:
if random_erase:
x = random_erasing(x)
if all(random_crop_size) > 0:
x = transforms.resize(x, random_crop_size)
else:
x = transforms.resize(x, output_size)
return x, lab
def test_random_expand_fill(self):
img = np.random.uniform(-1, 1, size=(3, 64, 32))
while True:
out, param = random_expand(img, fill=self.fill, return_param=True)
x_offset = param['x_offset']
y_offset = param['y_offset']
if x_offset > 0 or y_offset > 0:
break
if isinstance(self.fill, int):
np.testing.assert_equal(
out[:, 0, 0], (self.fill,) * 3)
else:
np.testing.assert_equal(
out[:, 0, 0], self.fill)
def test_random_expand_fill(self):
img = np.random.uniform(-1, 1, size=(3, 64, 32))
while True:
out, param = random_expand(img, fill=self.fill, return_param=True)
y_offset = param['y_offset']
x_offset = param['x_offset']
if y_offset > 0 or x_offset > 0:
break
if isinstance(self.fill, int):
fill = (self.fill,) * 3
else:
fill = self.fill
np.testing.assert_equal(
out[:, 0, 0], np.array(fill).flatten())
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
def __call__(self, in_data):
img, bbox, label = in_data
img = random_distort(img)
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'])
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']]
_, 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))
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
mb_loc, mb_label = self.coder.encode(bbox, label)
return img, mb_loc, mb_label
def random_expand(img, expand_ratio):
if expand_ratio > 1:
img = transforms.random_expand(img, max_ratio=expand_ratio)
return img
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'])
# Random expansion:This method randomly place the input image on
# a larger canvas. The size of the canvas is (rH,rW), r is a random ratio drawn from [1,max_ratio].
# The canvas is filled by a value fill except for the region where the original image is placed.
if np.random.randint(2):
fill_value = img.mean(axis=1).mean(axis=1).reshape(-1, 1, 1)
img, param = transforms.random_expand(img,
max_ratio=2,
fill=fill_value,
return_param=True)
bbox = transforms.translate_bbox(bbox,
y_offset=param['y_offset'],
x_offset=param['x_offset'])
# Random crop
# crops the image with bounding box constraints
img, param = random_crop_with_bbox_constraints(img,
bbox,
min_scale=0.5,
max_aspect_ratio=1.5,
return_param=True)
# this translates bounding boxes to fit within the cropped area of an image, bounding boxes whose centers are outside of the cropped area are removed.
bbox, param = transforms.crop_bbox(bbox,
y_slice=param['y_slice'],
x_slice=param['x_slice'],
allow_outside_center=False,
return_param=True)
#assigning new labels to the bounding boxes after cropping
label = label[param['index']]
# if the bounding boxes are all removed,
if bbox.shape[0] == 0:
img, bbox, label = in_data
# update the height and width of the image
_, t_H, t_W = img.shape
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 transform(in_data):
img, label = in_data
img = transforms.random_expand(img, max_ratio=3)
img = transforms.resize(img, (28, 28))
return img, label
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
# mask = None
img, bbox, label, mask = in_data
# TODO: show information
# self._show_img(img)
# self._show_mask(mask)
# 1. Color augmentation
img = random_distort(img)
# self._show_img(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'])
if mask is not None:
_, new_height, new_width = img.shape
param['new_height'] = new_height
param['new_width'] = new_width
mask = self._random_expand_mask(mask, param)
# self._show_img(img)
# self._show_mask(mask)
# 3. Random cropping
img, param = random_crop_with_bbox_constraints(
img, bbox, return_param=True)
# self._show_img(img)
mask = self._fixed_crop_mask(mask, param['y_slice'], param['x_slice'])
# self._show_mask(mask)
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))
# self._show_img(img)
if mask is not None:
if mask.size == 0:
raise RuntimeError
mask = self._resize_with_nearest(mask, (self.size, self.size))
# self._show_mask(mask)
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'])
if mask is not None:
mask = self._random_flip_mask(mask, x_flip=params['x_flip'], y_flip=params['y_flip'])
# self._show_img(img)
# self._show_mask(mask)
# Preparation for SSD network
img -= self.mean
mb_loc, mb_label = self.coder.encode(bbox, label)
if mask is None:
mask = np.ones([self.size, self.size], dtype=np.int32) * -1
# print("Dtype is :"+str(mask.dtype))
data_type = str(mask.dtype)
target_type = 'int32'
if data_type != target_type:
mask = mask.astype(np.int32)
if img is None:
raise RuntimeError
return img, mb_loc, mb_label, mask
