def GenerateData(ftxt, data_path, output, net, argument=False):
if net == "PNet":
size = 12
elif net == "RNet":
size = 24
elif net == "ONet":
size = 48
else:
print('Net type error')
return
image_id = 0
f = open(join(OUTPUT, "landmark_%s.txt" % (size)), 'w')
data = getDataFromTxt(ftxt, data_path)
idx = 0
#image_path bbox landmark(5*2)
for (imgPath, bbox, landmarkGt) in data:
#print imgPath
F_imgs = []
F_landmarks = []
img = cv2.imread(imgPath)
assert (img is not None)
img_h, img_w, img_c = img.shape
gt_box = np.array([bbox.left, bbox.top, bbox.right, bbox.bottom])
f_face = img[bbox.top:bbox.bottom + 1, bbox.left:bbox.right + 1]
f_face = cv2.resize(f_face, (size, size))
landmark = np.zeros((5, 2))
#normalize
for index, one in enumerate(landmarkGt):
rv = ((one[0] - gt_box[0]) / (gt_box[2] - gt_box[0]),
(one[1] - gt_box[1]) / (gt_box[3] - gt_box[1]))
landmark[index] = rv
F_imgs.append(f_face)
F_landmarks.append(landmark.reshape(10))
landmark = np.zeros((5, 2))
if argument:
idx = idx + 1
if idx % 100 == 0:
print(idx, "images done")
x1, y1, x2, y2 = gt_box
#gt's width
gt_w = x2 - x1 + 1
#gt's height
gt_h = y2 - y1 + 1
if max(gt_w, gt_h) < 40 or x1 < 0 or y1 < 0:
continue
#random shift
for i in range(10):
bbox_size = npr.randint(int(min(gt_w, gt_h) * 0.8),
np.ceil(1.25 * max(gt_w, gt_h)))
delta_x = npr.randint(-gt_w * 0.2, gt_w * 0.2)
delta_y = npr.randint(-gt_h * 0.2, gt_h * 0.2)
nx1 = int(max(x1 + gt_w / 2 - bbox_size / 2 + delta_x, 0))
ny1 = int(max(y1 + gt_h / 2 - bbox_size / 2 + delta_y, 0))
nx2 = nx1 + bbox_size
ny2 = ny1 + bbox_size
if nx2 > img_w or ny2 > img_h:
continue
crop_box = np.array([nx1, ny1, nx2, ny2])
cropped_im = img[ny1:ny2 + 1, nx1:nx2 + 1, :]
resized_im = cv2.resize(cropped_im, (size, size))
#cal iou
iou = IoU(crop_box, np.expand_dims(gt_box, 0))
if iou > 0.65:
F_imgs.append(resized_im)
#normalize
for index, one in enumerate(landmarkGt):
rv = ((one[0] - nx1) / bbox_size,
(one[1] - ny1) / bbox_size)
landmark[index] = rv
F_landmarks.append(landmark.reshape(10))
landmark = np.zeros((5, 2))
landmark_ = F_landmarks[-1].reshape(-1, 2)
bbox = BBox([nx1, ny1, nx2, ny2])
#mirror
if random.choice([0, 1]) > 0:
face_flipped, landmark_flipped = flip(
resized_im, landmark_)
face_flipped = cv2.resize(face_flipped, (size, size))
#c*h*w
F_imgs.append(face_flipped)
F_landmarks.append(landmark_flipped.reshape(10))
#rotate
if random.choice([0, 1]) > 0:
face_rotated_by_alpha, landmark_rotated = rotate(img, bbox, \
bbox.reprojectLandmark(landmark_), 5)#逆时针旋转
#landmark_offset
landmark_rotated = bbox.projectLandmark(
landmark_rotated)
face_rotated_by_alpha = cv2.resize(
face_rotated_by_alpha, (size, size))
F_imgs.append(face_rotated_by_alpha)
F_landmarks.append(landmark_rotated.reshape(10))
#flip
face_flipped, landmark_flipped = flip(
face_rotated_by_alpha, landmark_rotated)
face_flipped = cv2.resize(face_flipped, (size, size))
F_imgs.append(face_flipped)
F_landmarks.append(landmark_flipped.reshape(10))
#inverse clockwise rotation
if random.choice([0, 1]) > 0:
face_rotated_by_alpha, landmark_rotated = rotate(img, bbox, \
bbox.reprojectLandmark(landmark_), -5)#顺时针旋转
landmark_rotated = bbox.projectLandmark(
landmark_rotated)
face_rotated_by_alpha = cv2.resize(
face_rotated_by_alpha, (size, size))
F_imgs.append(face_rotated_by_alpha)
F_landmarks.append(landmark_rotated.reshape(10))
face_flipped, landmark_flipped = flip(
face_rotated_by_alpha, landmark_rotated)
face_flipped = cv2.resize(face_flipped, (size, size))
F_imgs.append(face_flipped)
F_landmarks.append(landmark_flipped.reshape(10))
F_imgs, F_landmarks = np.asarray(F_imgs), np.asarray(F_landmarks)
#print F_imgs.shape
#print F_landmarks.shape
for i in range(len(F_imgs)):
#print(image_id)
if np.sum(np.where(F_landmarks[i] <= 0, 1, 0)) > 0:
continue
if np.sum(np.where(F_landmarks[i] >= 1, 1, 0)) > 0:
continue
cv2.imwrite(join(dstdir, "%d.jpg" % (image_id)), F_imgs[i])
landmarks = map(str, list(F_landmarks[i]))
f.write(
join(dstdir, "%d.jpg" % (image_id)) + " -2 " +
" ".join(landmarks) + "\n")
image_id = image_id + 1
#print F_imgs.shape
#print F_landmarks.shape
#F_imgs = processImage(F_imgs)
#shuffle_in_unison_scary(F_imgs, F_landmarks)
f.close()
return F_imgs, F_landmarks
def GenerateData(ftxt, data_path, net, argument=False):
'''
:param ftxt: name/path of the text file that contains image path,
bounding box, and landmarks
:param output: path of the output dir
:param net: one of the net in the cascaded networks
:param argument: apply augmentation or not
:return: images and related landmarks
'''
if net == "PNet":
size = 12
elif net == "RNet":
size = 24
elif net == "ONet":
size = 48
else:
print('Net type error')
return
image_id = 0
#
f = open(join(OUTPUT, "landmark_%s_aug.txt" % (size)), 'w')
#dstdir = "train_landmark_few"
# get image path , bounding box, and landmarks from file 'ftxt'
data = getDataFromTxt(ftxt, data_path=data_path) # 图片路径，框-4，标注-（5，2）
idx = 0
#image_path bbox landmark(5*2)
for (imgPath, bbox, landmarkGt) in data:
#print imgPath
F_imgs = []
F_landmarks = []
#print(imgPath)
img = cv2.imread(imgPath)
assert (img is not None)
img_h, img_w, img_c = img.shape
gt_box = np.array([bbox.left, bbox.top, bbox.right, bbox.bottom])
#get sub-image from bbox 得到框出来的图
f_face = img[bbox.top:bbox.bottom + 1, bbox.left:bbox.right + 1]
# resize the gt image to specified size 将大小调整指定的尺寸
f_face = cv2.resize(f_face, (size, size))
#initialize the landmark
landmark = np.zeros((5, 2))
#normalize land mark by dividing the width and height of the ground truth bounding box
# landmakrGt is a list of tuples 对标注进行归一化（除以框）
for index, one in enumerate(landmarkGt):
# (( x - bbox.left)/ width of bounding box, (y - bbox.top)/ height of bounding box
rv = ((one[0] - gt_box[0]) / (gt_box[2] - gt_box[0]),
(one[1] - gt_box[1]) / (gt_box[3] - gt_box[1]))
# put the normalized value into the new list landmark
landmark[index] = rv
F_imgs.append(f_face)
F_landmarks.append(landmark.reshape(10))
landmark = np.zeros((5, 2))
if argument: # 数据集扩展
idx = idx + 1
if idx % 100 == 0:
print(idx, "images done")
x1, y1, x2, y2 = gt_box
#gt's width
gt_w = x2 - x1 + 1
#gt's height
gt_h = y2 - y1 + 1
if max(gt_w, gt_h) < 40 or x1 < 0 or y1 < 0: # 框的大小限制
continue
#random shift
for i in range(10):
bbox_size = npr.randint(int(min(gt_w, gt_h) * 0.8),
np.ceil(1.25 *
max(gt_w, gt_h))) # 框的大小
delta_x = npr.randint(-gt_w * 0.2, gt_w * 0.2)
delta_y = npr.randint(-gt_h * 0.2, gt_h * 0.2)
nx1 = int(max(x1 + gt_w / 2 - bbox_size / 2 + delta_x, 0))
ny1 = int(max(y1 + gt_h / 2 - bbox_size / 2 + delta_y, 0))
nx2 = nx1 + bbox_size
ny2 = ny1 + bbox_size
if nx2 > img_w or ny2 > img_h:
continue
crop_box = np.array([nx1, ny1, nx2, ny2])
cropped_im = img[ny1:ny2 + 1, nx1:nx2 + 1, :]
resized_im = cv2.resize(cropped_im, (size, size))
#cal iou
iou = IoU(crop_box, np.expand_dims(gt_box, 0))
if iou > 0.65:
F_imgs.append(resized_im)
#normalize
for index, one in enumerate(landmarkGt):
rv = ((one[0] - nx1) / bbox_size,
(one[1] - ny1) / bbox_size)
landmark[index] = rv
F_landmarks.append(landmark.reshape(10))
landmark = np.zeros((5, 2))
landmark_ = F_landmarks[-1].reshape(-1, 2)
bbox = BBox([nx1, ny1, nx2, ny2])
#mirror
if random.choice([0, 1]) > 0:
face_flipped, landmark_flipped = flip(
resized_im, landmark_)
face_flipped = cv2.resize(face_flipped, (size, size))
#c*h*w
F_imgs.append(face_flipped)
F_landmarks.append(landmark_flipped.reshape(10))
#rotate
if random.choice([0, 1]) > 0:
face_rotated_by_alpha, landmark_rotated = rotate(img, bbox, \
bbox.reprojectLandmark(landmark_), 5)#逆时针旋转
#landmark_offset
landmark_rotated = bbox.projectLandmark(
landmark_rotated)
face_rotated_by_alpha = cv2.resize(
face_rotated_by_alpha, (size, size))
F_imgs.append(face_rotated_by_alpha)
F_landmarks.append(landmark_rotated.reshape(10))
#flip
face_flipped, landmark_flipped = flip(
face_rotated_by_alpha, landmark_rotated)
face_flipped = cv2.resize(face_flipped, (size, size))
F_imgs.append(face_flipped)
F_landmarks.append(landmark_flipped.reshape(10))
#anti-clockwise rotation
if random.choice([0, 1]) > 0:
face_rotated_by_alpha, landmark_rotated = rotate(img, bbox, \
bbox.reprojectLandmark(landmark_), -5)#顺时针旋转
landmark_rotated = bbox.projectLandmark(
landmark_rotated)
face_rotated_by_alpha = cv2.resize(
face_rotated_by_alpha, (size, size))
F_imgs.append(face_rotated_by_alpha)
F_landmarks.append(landmark_rotated.reshape(10))
face_flipped, landmark_flipped = flip(
face_rotated_by_alpha, landmark_rotated)
face_flipped = cv2.resize(face_flipped, (size, size))
F_imgs.append(face_flipped)
F_landmarks.append(landmark_flipped.reshape(10))
F_imgs, F_landmarks = np.asarray(F_imgs), np.asarray(F_landmarks)
#print F_imgs.shape
#print F_landmarks.shape
for i in range(len(F_imgs)):
#if image_id % 100 == 0:
#print('image id : ', image_id)
if np.sum(np.where(F_landmarks[i] <= 0, 1, 0)) > 0:
continue
if np.sum(np.where(F_landmarks[i] >= 1, 1, 0)) > 0:
continue
cv2.imwrite(join(dstdir, "%d.jpg" % (image_id)), F_imgs[i])
landmarks = map(str, list(F_landmarks[i]))
f.write(
join(dstdir, "%d.jpg" % (image_id)) + " -2 " +
" ".join(landmarks) + "\n")
image_id = image_id + 1
#print F_imgs.shape
#print F_landmarks.shape
#F_imgs = processImage(F_imgs)
#shuffle_in_unison_scary(F_imgs, F_landmarks)
f.close()
return F_imgs, F_landmarks
def generateData_aug(data_dir, net, argument=False):
if net == "PNet":
size = 12
elif net == "RNet":
size = 24
elif net == "ONet":
size = 48
else:
print("Net type error! ")
return
OUTPUT = data_dir + "/%d" % size
if not exists(OUTPUT): os.mkdir(OUTPUT)
dstdir = data_dir + "/%d/train_%s_landmark_aug" % (size, net)
if not exists(dstdir): os.mkdir(dstdir)
assert (exists(dstdir) and exists(OUTPUT))
# get image path , bounding box, and landmarks from file 'ftxt'
data = getDataFromTxt("./prepare_data/trainImageList.txt",
data_path=data_dir + '/Align')
f = open(join(OUTPUT, "landmark_%s_aug.txt" % (size)), 'w')
image_id = 0
idx = 0
for (imgPath, bbox, landmarkGt) in data:
F_imgs = []
F_landmarks = []
img = cv2.imread(imgPath)
assert (img is not None)
img_h, img_w, img_c = img.shape
gt_box = np.array([bbox.left, bbox.top, bbox.right, bbox.bottom])
# get sub-image from bbox
f_face = img[bbox.top:bbox.bottom + 1, bbox.left:bbox.right + 1]
# resize the gt image to specified size
f_face = cv2.resize(f_face, (size, size))
# initialize the landmark
landmark = np.zeros((5, 2))
# normalize land mark by dividing the width and height of the ground truth bounding box
# landmakrGt is a list of tuples
for index, one in enumerate(landmarkGt):
# (( x - bbox.left)/ width of bounding box, (y - bbox.top)/ height of bounding box
rv = ((one[0] - gt_box[0]) / (gt_box[2] - gt_box[0]),
(one[1] - gt_box[1]) / (gt_box[3] - gt_box[1]))
landmark[index] = rv
F_imgs.append(f_face)
F_landmarks.append(landmark.reshape(10))
landmark = np.zeros((5, 2))
if argument:
idx = idx + 1
if idx % 100 == 0:
print(idx, "images done")
x1, y1, x2, y2 = gt_box
gt_w = x2 - x1 + 1
gt_h = y2 - y1 + 1
if max(gt_w, gt_h) < 40 or x1 < 0 or y1 < 0:
continue
#random shift
for i in range(10):
bbox_size = npr.randint(int(min(gt_w, gt_h) * 0.8),
np.ceil(1.25 * max(gt_w, gt_h)))
delta_x = npr.randint(-gt_w * 0.2, gt_w * 0.2)
delta_y = npr.randint(-gt_h * 0.2, gt_h * 0.2)
nx1 = int(max(x1 + gt_w / 2 - bbox_size / 2 + delta_x, 0))
ny1 = int(max(y1 + gt_h / 2 - bbox_size / 2 + delta_y, 0))
nx2 = nx1 + bbox_size
ny2 = ny1 + bbox_size
if nx2 > img_w or ny2 > img_h:
continue
crop_box = np.array([nx1, ny1, nx2, ny2])
cropped_im = img[ny1:ny2 + 1, nx1:nx2 + 1, :]
resized_im = cv2.resize(cropped_im, (size, size))
#cal iou
iou = IoU(crop_box, np.expand_dims(gt_box, 0))
if iou > 0.65:
F_imgs.append(resized_im)
#normalize
for index, one in enumerate(landmarkGt):
rv = ((one[0] - nx1) / bbox_size,
(one[1] - ny1) / bbox_size)
landmark[index] = rv
F_landmarks.append(landmark.reshape(10))
landmark = np.zeros((5, 2))
landmark_ = F_landmarks[-1].reshape(-1, 2)
bbox = BBox([nx1, ny1, nx2, ny2])
#mirror
if random.choice([0, 1]) > 0:
face_flipped, landmark_flipped = flip(
resized_im, landmark_)
face_flipped = cv2.resize(face_flipped, (size, size))
#c*h*w
F_imgs.append(face_flipped)
F_landmarks.append(landmark_flipped.reshape(10))
#rotate
if random.choice([0, 1]) > 0:
face_rotated_by_alpha, landmark_rotated = rotate(img, bbox, \
bbox.reprojectLandmark(landmark_), 5)#逆时针旋转
#landmark_offset
landmark_rotated = bbox.projectLandmark(
landmark_rotated)
face_rotated_by_alpha = cv2.resize(
face_rotated_by_alpha, (size, size))
F_imgs.append(face_rotated_by_alpha)
F_landmarks.append(landmark_rotated.reshape(10))
#flip
face_flipped, landmark_flipped = flip(
face_rotated_by_alpha, landmark_rotated)
face_flipped = cv2.resize(face_flipped, (size, size))
F_imgs.append(face_flipped)
F_landmarks.append(landmark_flipped.reshape(10))
#anti-clockwise rotation
if random.choice([0, 1]) > 0:
face_rotated_by_alpha, landmark_rotated = rotate(img, bbox, \
bbox.reprojectLandmark(landmark_), -5)#顺时针旋转
landmark_rotated = bbox.projectLandmark(
landmark_rotated)
face_rotated_by_alpha = cv2.resize(
face_rotated_by_alpha, (size, size))
F_imgs.append(face_rotated_by_alpha)
F_landmarks.append(landmark_rotated.reshape(10))
face_flipped, landmark_flipped = flip(
face_rotated_by_alpha, landmark_rotated)
face_flipped = cv2.resize(face_flipped, (size, size))
F_imgs.append(face_flipped)
F_landmarks.append(landmark_flipped.reshape(10))
F_imgs, F_landmarks = np.asarray(F_imgs), np.asarray(F_landmarks)
for i in range(len(F_imgs)):
if np.sum(np.where(F_landmarks[i] <= 0, 1, 0)) > 0:
continue
if np.sum(np.where(F_landmarks[i] >= 1, 1, 0)) > 0:
continue
cv2.imwrite(join(dstdir, "%d.jpg" % (image_id)), F_imgs[i])
landmarks = map(str, list(F_landmarks[i]))
f.write(dstdir + "/%d.jpg" % (image_id) + " -2 " +
" ".join(landmarks) + "\n")
image_id = image_id + 1
f.close()
return F_imgs, F_landmarks
def GenerateData(ftxt,
data_path,
output_path,
img_output_path,
net,
argument=False):
'''
参数
------------
ftxt: path of anno file
data_path: 数据集所在目录
output_path: 文本文件输出目录地址
img_output_path: 图片输出地址
net: String 三个网络之一的名字
argument: 是否使用数据增强
返回值
-------------
images and related landmarks
'''
if net == "PNet":
size = 12
elif net == "RNet":
size = 24
elif net == "ONet":
size = 48
else:
print('Net type error')
return
image_id = 0
#
f = open(join(output_path, "landmark_%s_aug.txt" % (size)), 'w')
#img_output_path = "train_landmark_few"
# get image path , bounding box, and landmarks from file 'ftxt'
data = getDataFromTxt(ftxt, data_path=data_path)
idx = 0
#image_path bbox landmark(5*2)
for (imgPath, bbox, landmarkGt) in data:
#print imgPath
F_imgs = []
F_landmarks = []
#print(imgPath)
img = cv2.imread(imgPath)
assert (img is not None)
img_h, img_w, img_c = img.shape
gt_box = np.array([bbox.left, bbox.top, bbox.right, bbox.bottom])
#get sub-image from bbox
f_face = img[bbox.top:bbox.bottom + 1, bbox.left:bbox.right + 1]
# resize the gt image to specified size
f_face = cv2.resize(f_face, (size, size))
#initialize the landmark
landmark = np.zeros((5, 2))
#normalize land mark by dividing the width and height of the ground truth bounding box
# landmakrGt is a list of tuples
for index, one in enumerate(landmarkGt):
# 重新计算因裁剪过后而改变的landmark的坐标，并且进行归一化
# (x - bbox.left) / width of bbox, (y - bbox.top) / height of bbox
rv = ((one[0] - gt_box[0]) / (gt_box[2] - gt_box[0]),
(one[1] - gt_box[1]) / (gt_box[3] - gt_box[1]))
landmark[index] = rv
F_imgs.append(f_face)
F_landmarks.append(landmark.reshape(10)) #[x1, y1, x2, y2, ...]
landmark = np.zeros((5, 2))
# data augment
if argument:
idx = idx + 1
if idx % 100 == 0:
print(idx, "images done")
x1, y1, x2, y2 = gt_box
#gt's width
gt_w = x2 - x1 + 1
#gt's height
gt_h = y2 - y1 + 1
if max(gt_w, gt_h) < 40 or x1 < 0 or y1 < 0:
continue
#random shift
for i in range(10):
bbox_size = npr.randint(int(min(gt_w, gt_h) * 0.8),
np.ceil(1.25 * max(gt_w, gt_h)))
delta_x = npr.randint(-gt_w * 0.2, gt_w * 0.2)
delta_y = npr.randint(-gt_h * 0.2, gt_h * 0.2)
nx1 = int(max(x1 + gt_w / 2 - bbox_size / 2 + delta_x, 0))
ny1 = int(max(y1 + gt_h / 2 - bbox_size / 2 + delta_y, 0))
nx2 = nx1 + bbox_size
ny2 = ny1 + bbox_size
if nx2 > img_w or ny2 > img_h:
continue
crop_box = np.array([nx1, ny1, nx2, ny2])
cropped_im = img[ny1:ny2 + 1, nx1:nx2 + 1, :]
resized_im = cv2.resize(cropped_im, (size, size))
#calculate iou
iou = IoU(crop_box, np.expand_dims(gt_box, 0))
if iou > 0.65:
F_imgs.append(resized_im)
#normalize
for index, one in enumerate(landmarkGt):
rv = ((one[0] - nx1) / bbox_size,
(one[1] - ny1) / bbox_size)
landmark[index] = rv
F_landmarks.append(landmark.reshape(10))
landmark = np.zeros((5, 2))
landmark_ = F_landmarks[-1].reshape(-1, 2)
bbox = BBox([nx1, ny1, nx2, ny2])
#mirror
if random.choice([0, 1]) > 0:
face_flipped, landmark_flipped = flip(
resized_im, landmark_)
face_flipped = cv2.resize(face_flipped, (size, size))
#c*h*w
F_imgs.append(face_flipped)
F_landmarks.append(landmark_flipped.reshape(10))
#rotate
if random.choice([0, 1]) > 0:
face_rotated_by_alpha, landmark_rotated = rotate(img, bbox, \
bbox.reprojectLandmark(landmark_), 5)#逆时针旋转
#landmark_offset
landmark_rotated = bbox.projectLandmark(
landmark_rotated)
face_rotated_by_alpha = cv2.resize(
face_rotated_by_alpha, (size, size))
F_imgs.append(face_rotated_by_alpha)
F_landmarks.append(landmark_rotated.reshape(10))
#flip
face_flipped, landmark_flipped = flip(
face_rotated_by_alpha, landmark_rotated)
face_flipped = cv2.resize(face_flipped, (size, size))
F_imgs.append(face_flipped)
F_landmarks.append(landmark_flipped.reshape(10))
#anti-clockwise rotation
if random.choice([0, 1]) > 0:
face_rotated_by_alpha, landmark_rotated = rotate(img, bbox, \
bbox.reprojectLandmark(landmark_), -5)#顺时针旋转
landmark_rotated = bbox.projectLandmark(
landmark_rotated)
face_rotated_by_alpha = cv2.resize(
face_rotated_by_alpha, (size, size))
F_imgs.append(face_rotated_by_alpha)
F_landmarks.append(landmark_rotated.reshape(10))
face_flipped, landmark_flipped = flip(
face_rotated_by_alpha, landmark_rotated)
face_flipped = cv2.resize(face_flipped, (size, size))
F_imgs.append(face_flipped)
F_landmarks.append(landmark_flipped.reshape(10))
F_imgs, F_landmarks = np.asarray(F_imgs), np.asarray(F_landmarks)
#print F_imgs.shape
#print F_landmarks.shape
for i in range(len(F_imgs)):
# 只要有一个坐标小于0或大于1就舍弃
if np.sum(np.where(F_landmarks[i] <= 0, 1, 0)) > 0:
continue
if np.sum(np.where(F_landmarks[i] >= 1, 1, 0)) > 0:
continue
cv2.imwrite(join(img_output_path, "%d.jpg" % (image_id)),
F_imgs[i])
landmarks = map(str, list(F_landmarks[i]))
f.write(
join(dstdir, "%d.jpg" % (image_id)) + " -2 " +
" ".join(landmarks) + "\n")
image_id = image_id + 1
#print F_imgs.shape
#print F_landmarks.shape
#F_imgs = processImage(F_imgs)
#shuffle_in_unison_scary(F_imgs, F_landmarks)
f.close()
return F_imgs, F_landmarks
def generate_landmark_data(landmark_truth_txt_path,
images_dir,
net,
argument=False):
""" 为特定网络类型生成关键点训练样本，label=-2
:param landmark_truth_txt_path: 包含image path, bounding box, and landmarks的txt路径
:param images_dir: 图片文件夹路径
:param net: 网络类型,('PNet', 'RNet', 'ONet')
:param argument: 是否进行数据增强
:return: images and related landmarks
"""
if net == "PNet":
size = 12
landmark_dir = path_config.pnet_landmark_dir
net_data_root_dir = path_config.pnet_dir
landmark_file = open(path_config.pnet_landmark_txt_path, 'w')
elif net == "RNet":
size = 24
landmark_dir = path_config.rnet_landmark_dir
net_data_root_dir = path_config.rnet_dir
landmark_file = open(path_config.rnet_landmark_txt_path, 'w')
elif net == "ONet":
size = 48
landmark_dir = path_config.onet_landmark_dir
net_data_root_dir = path_config.onet_dir
landmark_file = open(path_config.onet_landmark_txt_path, 'w')
else:
raise ValueError('网络类型(--net)错误！')
if not os.path.exists(net_data_root_dir):
os.mkdir(net_data_root_dir)
if not os.path.exists(landmark_dir):
os.mkdir(landmark_dir)
# 读取关键点信息文件：image path , bounding box, and landmarks
data = get_landmark_data(landmark_truth_txt_path, images_dir)
# 针对每张图片，生成关键点训练数据
landmark_idx = 0
image_id = 0
for (imgPath, bbox, landmarkGt) in data:
# 截取的图片数据和图片中关键点位置数据
cropped_images = []
cropped_landmarks = []
img = cv2.imread(imgPath)
assert (img is not None)
image_height, image_width, _ = img.shape
gt_box = np.array([[bbox.left, bbox.top, bbox.right, bbox.bottom]])
square_gt_box = np.squeeze(convert_to_square(gt_box))
# 防止越界，同时保持方形
if square_gt_box[0] < 0:
square_gt_box[2] -= square_gt_box[0]
square_gt_box[0] = 0
if square_gt_box[1] < 0:
square_gt_box[3] -= square_gt_box[1]
square_gt_box[1] = 0
if square_gt_box[2] > image_width:
square_gt_box[0] -= (square_gt_box[2] - image_width)
square_gt_box[2] = image_width
if square_gt_box[3] > image_height:
square_gt_box[1] -= (square_gt_box[3] - image_height)
square_gt_box[3] = image_height
gt_box = np.squeeze(gt_box)
# 计算标准化的关键点坐标
landmark = np.zeros((5, 2))
for index, one in enumerate(landmarkGt):
# (( x - bbox.left)/ width of bounding box, (y - bbox.top)/ height of bounding box
landmark[index] = ((one[0] - square_gt_box[0]) /
(square_gt_box[2] - square_gt_box[0]),
(one[1] - square_gt_box[1]) /
(square_gt_box[3] - square_gt_box[1]))
cropped_landmarks.append(landmark.reshape(10))
# 截取目标区域图片
cropped_object_image = img[square_gt_box[1]:square_gt_box[3] + 1,
square_gt_box[0]:square_gt_box[2] + 1]
cropped_object_image = cv2.resize(cropped_object_image, (size, size))
cropped_images.append(cropped_object_image)
landmark = np.zeros((5, 2))
if argument:
landmark_idx = landmark_idx + 1
if landmark_idx % 100 == 0:
sys.stdout.write("\r{}/{} images done ...".format(
landmark_idx, len(data)))
# ground truth的坐标、宽和高
x_truth_left, y_truth_top, x_truth_right, y_truth_bottom = gt_box
width_truth = x_truth_right - x_truth_left + 1
height_truth = y_truth_bottom - y_truth_top + 1
if max(width_truth,
height_truth) < 20 or x_truth_left < 0 or y_truth_top < 0:
continue
# 随机偏移
shift_num = 0
shift_try = 0
while shift_num < 10 and shift_try < 100:
bbox_size = npr.randint(
int(min(width_truth, height_truth) * 0.8),
np.ceil(1.25 * max(width_truth, height_truth)))
delta_x = npr.randint(int(-width_truth * 0.2),
np.ceil(width_truth * 0.2))
delta_y = npr.randint(int(-height_truth * 0.2),
np.ceil(height_truth * 0.2))
x_left_shift = int(
max(
x_truth_left + width_truth / 2 - bbox_size / 2 +
delta_x, 0))
y_top_shift = int(
max(
y_truth_top + height_truth / 2 - bbox_size / 2 +
delta_y, 0))
x_right_shift = x_left_shift + bbox_size
y_bottom_shift = y_top_shift + bbox_size
if x_right_shift > image_width or y_bottom_shift > image_height:
shift_try += 1
continue
crop_box = np.array(
[x_left_shift, y_top_shift, x_right_shift, y_bottom_shift])
# 计算数据增强后的偏移区域和ground truth的方形校正IoU
iou = square_IoU(crop_box, np.expand_dims(gt_box, 0))
if iou > 0.65:
shift_num += 1
cropped_im = img[y_top_shift:y_bottom_shift + 1,
x_left_shift:x_right_shift + 1, :]
resized_im = cv2.resize(cropped_im, (size, size))
cropped_images.append(resized_im)
# 标准化
for index, one in enumerate(landmarkGt):
landmark[index] = ((one[0] - x_left_shift) / bbox_size,
(one[1] - y_top_shift) / bbox_size)
cropped_landmarks.append(landmark.reshape(10))
# 进行其他类型的数据增强
landmark = np.zeros((5, 2))
landmark_ = cropped_landmarks[-1].reshape(-1, 2)
bbox = BBox([
x_left_shift, y_top_shift, x_right_shift,
y_bottom_shift
])
# 镜像
if random.choice([0, 1]) > 0:
face_flipped, landmark_flipped = flip(
resized_im, landmark_)
face_flipped = cv2.resize(face_flipped, (size, size))
cropped_images.append(face_flipped)
cropped_landmarks.append(landmark_flipped.reshape(10))
# 顺时针旋转
if random.choice([0, 1]) > 0:
face_rotated_by_alpha, landmark_rotated = \
rotate(img, bbox, bbox.reprojectLandmark(landmark_), 5)
# landmark_offset
landmark_rotated = bbox.projectLandmark(
landmark_rotated)
face_rotated_by_alpha = cv2.resize(
face_rotated_by_alpha, (size, size))
cropped_images.append(face_rotated_by_alpha)
cropped_landmarks.append(landmark_rotated.reshape(10))
# 上下翻转
face_flipped, landmark_flipped = flip(
face_rotated_by_alpha, landmark_rotated)
face_flipped = cv2.resize(face_flipped, (size, size))
cropped_images.append(face_flipped)
cropped_landmarks.append(landmark_flipped.reshape(10))
# 逆时针旋转
if random.choice([0, 1]) > 0:
face_rotated_by_alpha, landmark_rotated = \
rotate(img, bbox, bbox.reprojectLandmark(landmark_), -5)
landmark_rotated = bbox.projectLandmark(
landmark_rotated)
face_rotated_by_alpha = cv2.resize(
face_rotated_by_alpha, (size, size))
cropped_images.append(face_rotated_by_alpha)
cropped_landmarks.append(landmark_rotated.reshape(10))
# 上下翻转
face_flipped, landmark_flipped = flip(
face_rotated_by_alpha, landmark_rotated)
face_flipped = cv2.resize(face_flipped, (size, size))
cropped_images.append(face_flipped)
cropped_landmarks.append(landmark_flipped.reshape(10))
else:
shift_try += 1
# 保存关键点训练图片及坐标信息
cropped_images, cropped_landmarks = np.asarray(
cropped_images), np.asarray(cropped_landmarks)
for i in range(len(cropped_images)):
if np.any(cropped_landmarks[i] < 0):
continue
if np.any(cropped_landmarks[i] > 1):
continue
cv2.imwrite(os.path.join(landmark_dir, "%d.jpg" % image_id),
cropped_images[i])
landmarks = map(str, list(cropped_landmarks[i]))
landmark_file.write(
os.path.join(landmark_dir, "%d.jpg" % image_id) + " -2 " +
" ".join(landmarks) + "\n")
image_id = image_id + 1
landmark_file.close()
return
