def augment(img, split):
# resize input
height, width = img.shape[0], img.shape[1]
center = np.array([img.shape[1] / 2., img.shape[0] / 2.], dtype=np.float32)
scale = max(img.shape[0], img.shape[1]) * 1.0
if not isinstance(scale, np.ndarray) and not isinstance(scale, list):
scale = np.array([scale, scale], dtype=np.float32)
if split != 'train':
center = np.array([img.shape[1] / 2., img.shape[0] / 2.], dtype=np.float32)
scale = max(width, height) * 1.0
scale = np.array([scale, scale])
x = 32
input_w, input_h = int((width / 1. + x - 1) // x * x), int((height / 1. + x - 1) // x * x)
trans_input = data_utils.get_affine_transform(center, scale, 0, [input_w, input_h])
inp = cv2.warpAffine(img, trans_input, (input_w, input_h), flags=cv2.INTER_LINEAR)
# color augmentation
orig_img = inp.copy()
inp = (inp.astype(np.float32) / 255.)
if split == 'train':
data_utils.color_aug(_data_rng, inp, _eig_val, _eig_vec)
# normalize the image
inp = (inp - mean) / std
inp = inp.transpose(2, 0, 1)
output_h, output_w = input_h // tless_config.down_ratio, input_w // tless_config.down_ratio
trans_output = data_utils.get_affine_transform(center, scale, 0, [output_w, output_h])
inp_out_hw = (input_h, input_w, output_h, output_w)
return orig_img, inp, trans_input, trans_output, center, scale, inp_out_hw
def augment(img, split, _data_rng, _eig_val, _eig_vec, mean, std, polys=None):
# resize input
height, width = img.shape[0], img.shape[1]
center = np.array([img.shape[1] / 2., img.shape[0] / 2.], dtype=np.float32)
scale = max(img.shape[0], img.shape[1]) * 1.0
if not isinstance(scale, np.ndarray) and not isinstance(scale, list):
scale = np.array([scale, scale], dtype=np.float32)
# random crop and flip augmentation
flipped = False
if split == 'train':
scale = scale * np.random.uniform(0.6, 1.4)
x, y = center
w_border = data_utils.get_border(width / 4, scale[0]) + 1
h_border = data_utils.get_border(height / 4, scale[0]) + 1
center[0] = np.random.randint(low=max(x - w_border, 0),
high=min(x + w_border, width - 1))
center[1] = np.random.randint(low=max(y - h_border, 0),
high=min(y + h_border, height - 1))
# flip augmentation
if np.random.random() < 0.5:
flipped = True
img = img[:, ::-1, :]
center[0] = width - center[0] - 1
input_h, input_w = snake_config.voc_input_h, snake_config.voc_input_w
if split != 'train':
center = np.array([img.shape[1] / 2., img.shape[0] / 2.],
dtype=np.float32)
scale = max(width, height) * 1.0
scale = np.array([scale, scale])
x = 32
input_w, input_h = 512, 512
# input_w, input_h = (width + x - 1) // x * x, (height + x - 1) // x * x
trans_input = data_utils.get_affine_transform(center, scale, 0,
[input_w, input_h])
inp = cv2.warpAffine(img,
trans_input, (input_w, input_h),
flags=cv2.INTER_LINEAR)
# color augmentation
orig_img = inp.copy()
inp = (inp.astype(np.float32) / 255.)
if split == 'train':
data_utils.color_aug(_data_rng, inp, _eig_val, _eig_vec)
# blur_aug(inp)
# normalize the image
inp = (inp - mean) / std
inp = inp.transpose(2, 0, 1)
output_h, output_w = input_h // snake_config.down_ratio, input_w // snake_config.down_ratio
trans_output = data_utils.get_affine_transform(center, scale, 0,
[output_w, output_h])
inp_out_hw = (input_h, input_w, output_h, output_w)
return orig_img, inp, trans_input, trans_output, flipped, center, scale, inp_out_hw
def augment(img, split, _data_rng, _eig_val, _eig_vec, mean, std, polys):
# resize input
height, width = img.shape[0], img.shape[1]
center = np.array([img.shape[1] / 2., img.shape[0] / 2.], dtype=np.float32)
scale = snake_config.scale
if not isinstance(scale, np.ndarray) and not isinstance(scale, list):
scale = np.array([scale, scale], dtype=np.float32)
# random crop and flip augmentation
flipped = False
if split == 'train':
scale = scale * np.random.uniform(0.4, 1.6)
seed = np.random.randint(0, len(polys))
index = np.random.randint(0, len(polys[seed]))
poly = polys[seed][index]['poly']
center[0], center[1] = poly[np.random.randint(len(poly))]
border = scale[0] // 2 if scale[0] < width else width - scale[0] // 2
center[0] = np.clip(center[0], a_min=border, a_max=width - border)
border = scale[1] // 2 if scale[1] < height else height - scale[1] // 2
center[1] = np.clip(center[1], a_min=border, a_max=height - border)
# flip augmentation
if np.random.random() < 0.5:
flipped = True
img = img[:, ::-1, :]
center[0] = width - center[0] - 1
input_w, input_h = snake_config.input_w, snake_config.input_h
if split != 'train':
center = np.array([width // 2, height // 2])
scale = np.array([width, height])
# input_w, input_h = width, height
input_w, input_h = int((width / 0.85 + 31) // 32 * 32), int(
(height / 0.85 + 31) // 32 * 32)
trans_input = data_utils.get_affine_transform(center, scale, 0,
[input_w, input_h])
inp = cv2.warpAffine(img,
trans_input, (input_w, input_h),
flags=cv2.INTER_LINEAR)
# color augmentation
orig_img = inp.copy()
inp = (inp.astype(np.float32) / 255.)
if split == 'train':
data_utils.color_aug(_data_rng, inp, _eig_val, _eig_vec)
# data_utils.blur_aug(inp)
# normalize the image
inp = (inp - mean) / std
inp = inp.transpose(2, 0, 1)
output_h, output_w = input_h // snake_config.down_ratio, input_w // snake_config.down_ratio
trans_output = data_utils.get_affine_transform(center, scale, 0,
[output_w, output_h])
inp_out_hw = (input_h, input_w, output_h, output_w)
return orig_img, inp, trans_input, trans_output, flipped, center, scale, inp_out_hw
def augment(img, split):
# resize input
height, width = img.shape[0], img.shape[1]
center = np.array([img.shape[1] / 2., img.shape[0] / 2.], dtype=np.float32)
scale = max(img.shape[0], img.shape[1]) * 1.0
if not isinstance(scale, np.ndarray) and not isinstance(scale, list):
scale = np.array([scale, scale], dtype=np.float32)
if split == 'train':
scale = scale * np.random.uniform(0.6, 1.4)
center = np.array([0, 0])
border = scale[0] // 2 if scale[0] < width else width - scale[0] // 2
border_r = max(width - border, border + 1)
center[0] = np.random.randint(border, border_r)
border = scale[1] // 2 if scale[1] < height else height - scale[1] // 2
border_r = max(height - border, border + 1)
center[1] = np.random.randint(border, border_r)
input_w, input_h = input_scale
if split != 'train':
center = np.array([img.shape[1] / 2., img.shape[0] / 2.],
dtype=np.float32)
scale = max(width, height) * 1.0
scale = np.array([scale, scale])
x = 32
input_w, input_h = (width + x - 1) // x * x, (height + x - 1) // x * x
trans_input = data_utils.get_affine_transform(center, scale, 0,
[input_w, input_h])
inp = cv2.warpAffine(img,
trans_input, (input_w, input_h),
flags=cv2.INTER_LINEAR)
# color augmentation
orig_img = inp.copy()
inp = (inp.astype(np.float32) / 255.)
if split == 'train':
data_utils.color_aug(_data_rng, inp, _eig_val, _eig_vec)
# normalize the image
inp = (inp - mean) / std
inp = inp.transpose(2, 0, 1)
output_h, output_w = input_h // tless_config.down_ratio, input_w // tless_config.down_ratio
trans_output = data_utils.get_affine_transform(center, scale, 0,
[output_w, output_h])
inp_out_hw = (input_h, input_w, output_h, output_w)
return orig_img, inp, trans_input, trans_output, center, scale, inp_out_hw
def augment(img, split, down_ratio, _data_rng, _eig_val, _eig_vec, mean, std):
# resize input
height, width = img.shape[0], img.shape[1]
center = np.array([img.shape[1] / 2., img.shape[0] / 2.], dtype=np.float32)
scale = max(img.shape[0], img.shape[1]) * 1.0
# random crop and flip augmentation
flipped = False
if split == 'train':
scale = scale * np.random.choice(np.arange(0.6, 1.4, 0.1))
w_border = get_border(128, img.shape[1])
h_border = get_border(128, img.shape[0])
center[0] = np.random.randint(low=w_border,
high=img.shape[1] - w_border)
center[1] = np.random.randint(low=h_border,
high=img.shape[0] - h_border)
# flip augmentation
if np.random.random() < 0.5:
flipped = True
img = img[:, ::-1, :]
center[0] = width - center[0] - 1
input_h, input_w = (512, 512)
trans_input = get_affine_transform(center, scale, 0, [input_w, input_h])
inp = cv2.warpAffine(img,
trans_input, (input_w, input_h),
flags=cv2.INTER_LINEAR)
# color augmentation
orig_img = inp.copy()
inp = (inp.astype(np.float32) / 255.)
if split == 'train':
color_aug(_data_rng, inp, _eig_val, _eig_vec)
# normalize the image
inp = (inp - mean) / std
inp = inp.transpose(2, 0, 1)
# resize output
output_h = input_h // down_ratio
output_w = input_w // down_ratio
trans_output = get_affine_transform(center, scale, 0, [output_w, output_h])
return orig_img, inp, trans_input, trans_output, input_h, input_w, output_h, output_w, flipped
def augment(img,
split,
down_ratio,
_data_rng,
_eig_val,
_eig_vec,
mean,
std,
polys,
boxes=None,
label=None):
# resize input
height, width = img.shape[0], img.shape[1]
center = np.array([img.shape[1] / 2., img.shape[0] / 2.], dtype=np.float32)
scale = max(img.shape[0], img.shape[1]) * 1.0
scale = 800
# __import__('ipdb').set_trace()
# random crop and flip augmentation
flipped = False
if cfg.small_num > 0:
img, polys, boxes, label = small_aug(img, polys, boxes, label,
cfg.small_num)
if split == 'train':
scale = scale * np.random.choice(np.arange(0.6, 1.4, 0.1))
seed = np.random.randint(0, len(polys))
index = np.random.randint(0, len(polys[seed]))
x = polys[seed][index]['bbox'][0] + (polys[seed][index]['bbox'][2] -
1) / 2
y = polys[seed][index]['bbox'][1] + (polys[seed][index]['bbox'][3] -
1) / 2
w_border = get_border(200, scale)
h_border = get_border(200, scale)
if (w_border == 0) or (h_border == 0):
center[0] = x
center[1] = y
else:
center[0] = np.random.randint(low=max(x - w_border, 0),
high=min(x + w_border, width - 1))
center[1] = np.random.randint(low=max(y - h_border, 0),
high=min(y + h_border, height - 1))
# flip augmentation
if np.random.random() < 0.5:
flipped = True
img = img[:, ::-1, :]
center[0] = width - center[0] - 1
input_h, input_w = (800, 800)
if split == 'val':
center = np.array([1024, 512])
scale = [2048, 1024]
input_h, input_w = (1024, 2048)
# print(center,scale)
# print(flipped)
# center = np.array([1272., 718.])
# scale = 358.4
# import ipdb; ipdb.set_trace()
# center = np.array([1583., 306.])
# print(center)
# scale = 358.4
# print(center, scale)
trans_input = get_affine_transform(center, scale, 0, [input_w, input_h])
inp = cv2.warpAffine(img,
trans_input, (input_w, input_h),
flags=cv2.INTER_LINEAR)
# color augmentation
orig_img = inp.copy()
inp = (inp.astype(np.float32) / 255.)
if split == 'train':
color_aug(_data_rng, inp, _eig_val, _eig_vec)
# blur_aug(inp)
# normalize the image
inp = (inp - mean) / std
inp = inp.transpose(2, 0, 1)
# resize output
# if split == 'train':
output_h = input_h // down_ratio
output_w = input_w // down_ratio
trans_output = get_affine_transform(center, scale, 0, [output_w, output_h])
return orig_img, inp, trans_input, trans_output, input_h, input_w, output_h, output_w, flipped, center, scale, \
polys, boxes, label