def get_next_batch_from_path(image_path,
image_labels,
pointer,
IMAGE_HEIGHT=299,
IMAGE_WIDTH=299,
batch_size=64,
is_train=True):
batch_x = np.zeros([batch_size, IMAGE_HEIGHT, IMAGE_WIDTH, 3])
num_classes = len(image_labels[0])
batch_y = np.zeros([batch_size, num_classes])
for i in range(batch_size):
image = cv2.imread(image_path[i + pointer * batch_size])
image = cv2.resize(image,
(int(IMAGE_HEIGHT * 1.5), int(IMAGE_WIDTH * 1.5)))
image = img_crop_pre(image, resize_size=336)
if is_train:
image = random_flip(image)
image = random_rotation(image)
image = random_crop(image)
image = random_exposure(image)
image = cv2.resize(image, (IMAGE_HEIGHT, IMAGE_WIDTH))
# 选择自己预处理方式：
'''
m = image.mean()
s = image.std()
min_s = 1.0/(np.sqrt(image.shape[0]*image.shape[1]))
std = max(min_s, s)
image = (image-m)/std'''
# image = (image-127.5)
image = image / 255.0
image = image - 0.5
image = image * 2
batch_x[i, :, :, :] = image
# print labels[i+pointer*batch_size]
batch_y[i] = image_labels[i + pointer * batch_size]
return batch_x, batch_y
def process_image(self, line, data_dir, mode):
""" process_image """
img1, img2, grt1, grt2, img1_name, img2_name, grt1_name, grt2_name = self.load_image(
line, data_dir, mode=mode)
grt1 = grt1 + 1 if grt1 is not None else None
if mode == ModelPhase.TRAIN:
img1, img2, grt1, grt2 = aug.resize(img1, img2, grt1, grt2, mode)
img1, img2, grt1, grt2 = aug.rand_crop(
img1, img2, grt1, grt2, mode=mode)
if cfg.AUG.RICH_CROP.ENABLE:
if cfg.AUG.RICH_CROP.BLUR:
if cfg.AUG.RICH_CROP.BLUR_RATIO <= 0:
n = 0
elif cfg.AUG.RICH_CROP.BLUR_RATIO >= 1:
n = 1
else:
n = int(1.0 / cfg.AUG.RICH_CROP.BLUR_RATIO)
if n > 0:
if np.random.randint(0, n) == 0:
radius = np.random.randint(3, 10)
if radius % 2 != 1:
radius = radius + 1
if radius > 9:
radius = 9
img1 = cv2.GaussianBlur(img1, (radius, radius), 0,
0)
if img2 is not None:
img2 = cv2.GaussianBlur(img2, (radius, radius),
0, 0)
img1, img2, grt1, grt2 = aug.random_rotation(
img1,
img2,
grt1,
grt2,
rich_crop_max_rotation=cfg.AUG.RICH_CROP.MAX_ROTATION,
mean_value=cfg.DATASET.PADDING_VALUE)
img1, img2, grt1, grt2 = aug.rand_scale_aspect(
img1,
img2,
grt1,
grt2,
rich_crop_min_scale=cfg.AUG.RICH_CROP.MIN_AREA_RATIO,
rich_crop_aspect_ratio=cfg.AUG.RICH_CROP.ASPECT_RATIO)
img1, img2 = aug.hsv_color_jitter(
img1,
img2,
brightness_jitter_ratio=cfg.AUG.RICH_CROP.
BRIGHTNESS_JITTER_RATIO,
saturation_jitter_ratio=cfg.AUG.RICH_CROP.
SATURATION_JITTER_RATIO,
contrast_jitter_ratio=cfg.AUG.RICH_CROP.
CONTRAST_JITTER_RATIO)
if cfg.AUG.RANDOM_ROTATION90:
rot_k = np.random.randint(0, 4)
img1 = np.rot90(img1, k=rot_k)
img2 = np.rot90(img2, k=rot_k) if img2 is not None else None
grt1 = np.rot90(grt1, k=rot_k)
grt2 = np.rot90(grt2, k=rot_k) if grt2 is not None else None
if cfg.AUG.FLIP:
if cfg.AUG.FLIP_RATIO <= 0:
n = 0
elif cfg.AUG.FLIP_RATIO >= 1:
n = 1
else:
n = int(1.0 / cfg.AUG.FLIP_RATIO)
if n > 0:
if np.random.randint(0, n) == 0:
img1 = img1[::-1, :, :]
img2 = img2[::-1, :, :] if img2 is not None else None
grt1 = grt1[::-1, :]
grt2 = grt2[::-1, :] if grt2 is not None else None
if cfg.AUG.MIRROR:
if np.random.randint(0, 2) == 1:
img1 = img1[:, ::-1, :]
img2 = img2[:, ::-1, :] if img2 is not None else None
grt1 = grt1[:, ::-1]
grt2 = grt2[:, ::-1] if grt2 is not None else None
elif ModelPhase.is_eval(mode):
img1, img2, grt1, grt2 = aug.resize(
img1, img2, grt1, grt2, mode=mode)
img1, img2, grt1, grt2 = aug.rand_crop(
img1, img2, grt1, grt2, mode=mode)
if cfg.TEST.TEST_AUG:
img1 = self.test_aug(img1)
img2 = self.test_aug(img2) if img2 is not None else None
elif ModelPhase.is_visual(mode):
org_shape = [img1.shape[0], img1.shape[1]]
img1, img2, grt1, grt2 = aug.resize(
img1, img2, grt1, grt2, mode=mode)
valid_shape = [img1.shape[0], img1.shape[1]]
img1, img2, grt1, grt2 = aug.rand_crop(
img1, img2, grt1, grt2, mode=mode)
else:
raise ValueError("Dataset mode={} Error!".format(mode))
# Normalize image
img1 = self.normalize_image(img1)
img2 = self.normalize_image(img2) if img2 is not None else None
if grt2 is not None:
grt = grt1 * cfg.DATASET.NUM_CLASSES + grt2
unchange_idx = np.where((grt1 - grt2) == 0)
grt[unchange_idx] = 0
if cfg.DATASET.NUM_CLASSES == 2:
grt[np.where(grt != 0)] = 1
ignore_idx = np.where((grt1 == cfg.DATASET.IGNORE_INDEX)
| (grt2 == cfg.DATASET.IGNORE_INDEX))
grt[ignore_idx] = cfg.DATASET.IGNORE_INDEX
else:
grt = grt1
if ModelPhase.is_train(mode) or ModelPhase.is_eval(mode):
grt = np.expand_dims(np.array(grt).astype('int32'), axis=0)
ignore = (grt != cfg.DATASET.IGNORE_INDEX).astype('int32')
if cfg.DATASET.INPUT_IMAGE_NUM == 1:
if ModelPhase.is_train(mode):
return (img1, grt, ignore)
elif ModelPhase.is_eval(mode):
return (img1, grt, ignore)
elif ModelPhase.is_visual(mode):
return (img1, grt, img1_name, valid_shape, org_shape)
else:
if ModelPhase.is_train(mode):
return (img1, img2, grt, ignore)
elif ModelPhase.is_eval(mode):
return (img1, img2, grt, ignore)
elif ModelPhase.is_visual(mode):
return (img1, img2, grt, img1_name, img2_name, valid_shape,
org_shape)
def process_image(self, line, data_dir, mode):
""" process_image """
img, grt, img_name, grt_name = self.load_image(
line, data_dir, mode=mode)
if mode == ModelPhase.TRAIN:
img, grt = aug.resize(img, grt, mode)
if cfg.AUG.RICH_CROP.ENABLE:
if cfg.AUG.RICH_CROP.BLUR:
if cfg.AUG.RICH_CROP.BLUR_RATIO <= 0:
n = 0
elif cfg.AUG.RICH_CROP.BLUR_RATIO >= 1:
n = 1
else:
n = int(1.0 / cfg.AUG.RICH_CROP.BLUR_RATIO)
if n > 0:
if np.random.randint(0, n) == 0:
radius = np.random.randint(3, 10)
if radius % 2 != 1:
radius = radius + 1
if radius > 9:
radius = 9
img = cv2.GaussianBlur(img, (radius, radius), 0, 0)
img, grt = aug.random_rotation(
img,
grt,
rich_crop_max_rotation=cfg.AUG.RICH_CROP.MAX_ROTATION,
mean_value=cfg.DATASET.PADDING_VALUE)
img, grt = aug.rand_scale_aspect(
img,
grt,
rich_crop_min_scale=cfg.AUG.RICH_CROP.MIN_AREA_RATIO,
rich_crop_aspect_ratio=cfg.AUG.RICH_CROP.ASPECT_RATIO)
img = aug.hsv_color_jitter(
img,
brightness_jitter_ratio=cfg.AUG.RICH_CROP.
BRIGHTNESS_JITTER_RATIO,
saturation_jitter_ratio=cfg.AUG.RICH_CROP.
SATURATION_JITTER_RATIO,
contrast_jitter_ratio=cfg.AUG.RICH_CROP.
CONTRAST_JITTER_RATIO)
if cfg.AUG.FLIP:
if cfg.AUG.FLIP_RATIO <= 0:
n = 0
elif cfg.AUG.FLIP_RATIO >= 1:
n = 1
else:
n = int(1.0 / cfg.AUG.FLIP_RATIO)
if n > 0:
if np.random.randint(0, n) == 0:
img = img[::-1, :, :]
grt = grt[::-1, :]
if cfg.AUG.MIRROR:
if np.random.randint(0, 2) == 1:
img = img[:, ::-1, :]
grt = grt[:, ::-1]
img, grt = aug.rand_crop(img, grt, mode=mode)
elif ModelPhase.is_eval(mode):
img, grt = aug.resize(img, grt, mode=mode)
img, grt = aug.rand_crop(img, grt, mode=mode)
elif ModelPhase.is_visual(mode):
org_shape = [img.shape[0], img.shape[1]]
img, grt = aug.resize(img, grt, mode=mode)
valid_shape = [img.shape[0], img.shape[1]]
img, grt = aug.rand_crop(img, grt, mode=mode)
else:
raise ValueError("Dataset mode={} Error!".format(mode))
# Normalize image
img = self.normalize_image(img)
if ModelPhase.is_train(mode) or ModelPhase.is_eval(mode):
grt = np.expand_dims(np.array(grt).astype('int32'), axis=0)
ignore = (grt != cfg.DATASET.IGNORE_INDEX).astype('int32')
if ModelPhase.is_train(mode):
return (img, grt, ignore)
elif ModelPhase.is_eval(mode):
return (img, grt, ignore)
elif ModelPhase.is_visual(mode):
return (img, grt, img_name, valid_shape, org_shape)
if __name__ == '__main__':
# path = '/home/eric/Desktop/CHNCXR_0327_1.jpg'
path = '/home/eric/Desktop/218.jpeg'
mask_path = '/home/eric/Desktop/218_mask.jpeg'
image = cv2.imread(path, 0)
image = tf.Variable(image, tf.float32)
mask = cv2.imread(mask_path, 0)
mask = tf.image.convert_image_dtype(mask, tf.float32)
image = tf.expand_dims(image, -1)
mask = tf.expand_dims(mask, -1)
# img = data_aug.random_flip(image)
#img = data_aug.random_light(image)
img, mask = data_aug.random_rotation(image, mask)
img, mask = data_aug.random_move(img, mask)
#print img.get_shape().as_list()
mask = tf.cast(mask, tf.float32)
mask = tf.image.resize_images(mask, (1024, 1024))
img = tf.squeeze(img)
msk = tf.squeeze(mask)
msk = tf.cast(msk, tf.uint8)
out = img * msk
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
img = sess.run(out)
cv2.imshow('', np.uint8(img))
cv2.waitKey()
cv2.destroyAllWindows()