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 __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 random_sized_crop(image, keypoints, bbox):
image, param = transforms.random_sized_crop(
image,
scale_ratio_range=(0.5, 5),
aspect_ratio_range=(0.75, 1.3333333333333333),
return_param=True
)
keypoints = [
transforms.translate_point(points,
x_offset=-param['x_slice'].start,
y_offset=-param['y_slice'].start
)
for points in keypoints
]
_, cropped_H, cropped_W = image.shape
bbox = translate_bbox(
bbox,
size=(cropped_H, cropped_W),
x_offset=-param['x_slice'].start,
y_offset=-param['y_slice'].start,
)
return image, keypoints, bbox, {random_sized_crop.__name__: param}
def test_random_sized_crop(self):
img = np.random.uniform(size=(3, self.H, self.W))
scale_ratio_interval = (0.08, 1)
aspect_ratio_interval = (3 / 4, 4 / 3)
out, params = random_sized_crop(img,
scale_ratio_interval,
aspect_ratio_interval,
return_param=True)
expected = img[:, params['y_slice'], params['x_slice']]
np.testing.assert_equal(out, expected)
_, H_crop, W_crop = out.shape
scale_ratio = params['scale_ratio']
aspect_ratio = params['aspect_ratio']
area = scale_ratio * self.H * self.W
expected_H_crop = int(math.floor(np.sqrt(area * aspect_ratio)))
expected_W_crop = int(math.floor(np.sqrt(area / aspect_ratio)))
self.assertEqual(H_crop, expected_H_crop)
self.assertEqual(W_crop, expected_W_crop)
self.assertTrue((aspect_ratio_interval[0] <= aspect_ratio)
and (aspect_ratio <= aspect_ratio_interval[1]))
self.assertTrue(scale_ratio <= scale_ratio_interval[1])
scale_ratio_max = min(
(scale_ratio_interval[1], self.H / (self.W * aspect_ratio),
(aspect_ratio * self.W) / self.H))
self.assertTrue(
min((scale_ratio_max, scale_ratio_interval[0])) <= scale_ratio)
def transform(self, image, keypoints, bbox, is_labeled):
_, H, W = image.shape
# PCA Lighting
image = transforms.pca_lighting(image, sigma=5)
# Random rotate
degree = np.random.uniform(-40, 40)
image, keypoints, bbox = rotate(image, keypoints, bbox, degree)
# Random flip
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)[self.flip_indices]
for points in keypoints
]
is_labeled = [label[self.flip_indices] for label in is_labeled]
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
# Random resize
scalew, scaleh = np.random.uniform(1.0, 2.0, 2)
resizeW, resizeH = int(W * scalew), int(H * scalew)
image, keypoints, bbox = self.resize(image, keypoints, bbox,
(resizeH, resizeW))
# Random crop
image, param = transforms.random_sized_crop(image,
scale_ratio_range=(0.5, 5),
return_param=True)
keypoints = [
transforms.translate_point(points,
x_offset=-param['x_slice'].start,
y_offset=-param['y_slice'].start)
for points in keypoints
]
new_bbox = []
for x, y, w, h in bbox:
new_bbox.append(
[x - param['x_slice'].start, y - param['y_slice'].start, w, h])
bbox = new_bbox
return image, keypoints, bbox, is_labeled
def train_transform(sample):
img, label = sample
img = np.transpose(img, (2, 0, 1))
img = transforms.random_sized_crop(img)
img = transforms.resize(img, patchsize)
img = transforms.random_flip(img, x_random=True)
if not no_autoaugment:
img = np.transpose(img, (1, 2, 0))
img = Image.fromarray(img)
img = policy(img)
img = np.asarray(img)
img = np.transpose(img, (2, 0, 1))
img = img - mean
img = img.astype(dtype)
if soft:
label = hard_to_soft(label, dtype=dtype)
return img, label
def _transform(in_data):
img, label = in_data
img = random_sized_crop(img, scale_ratio_range=(0.3, 1))
img = random_flip(img, x_random=True)
img = chainer.links.model.vision.vgg.prepare(img)
return img, label
