def geneDataTxt(imgPath,landmarkREF,mode = 'test'):
imgTxt = 'dataset/data/testImageList.txt'
data = getDataFromTxt(imgTxt,False,False) #image_path,bbox
testData = defaultdict(lambda:dict(landmarks=[],patches=[],label=[]))
logger("generate 25 positive samples and 500 negative samples for per landmark")
testData = generateSamples(testData,data,landmarkREF)
for idx,name in types:
patches = np.asarray(testData[name]['patches'])
landmarks = np.asarray(testData[name]['landmarks'])
#label = np.asarray(testData[name]['label'])
patches = processImage(patches)
shuffle_in_unison_scary(patches,landmarks)
createDir('dataset/test/%s' % imgPath[-7:-4])
with h5py.File('dataset/test/%s/%s.h5' % (imgPath[-7:-4],name),'w') as h5:
h5['data'] = patches.astype(np.float32)
h5['landmark'] = landmarks.astype(np.float32)
#h5['label'] = label.astype(np.uint8)
with open('dataset/test/%s/%s.txt' % (imgPath[-7:-4],name),'w') as fd:
fd.write('dataset/test/%s/%s.h5'% (imgPath[-7:-4],name))
'''with open('dataset/test/%s.txt' % (name),'w') as fd:
def initMain(filename):
init(filename)
createDir(logfilename + "_log_all.log")
logging.basicConfig(filename=logfilename + "_log_all.log",
level=logging.INFO,
format=_FORMAT,
datefmt=_DATEFMT)
initProcess()
def initProcess():
if (os.getpid() not in process_ids):
process_ids.append(os.getpid())
filename = "{}_log_{}.log".format(logfilename, os.getpid())
createDir(filename)
formatter = logging.Formatter(fmt=_FORMAT, datefmt=_DATEFMT)
filehandler = logging.FileHandler(filename)
filehandler.setFormatter(formatter)
logger = logging.getLogger("subprocess_{}".format(os.getpid()))
logger.addHandler(filehandler)
types = [
(0, 'LE1', 0.11),
(0, 'LE2', 0.12),
(1, 'RE1', 0.11),
(1, 'RE2', 0.12),
(2, 'N1', 0.11),
(2, 'N2', 0.12),
(3, 'LM1', 0.11),
(3, 'LM2', 0.12),
(4, 'RM1', 0.11),
(4, 'RM2', 0.12),
]
for t in types:
d = '/home/tyd/下载/deep_landmark/mydataset/mytrain/3_%s' % t[1]
createDir(d)
def generate(ftxt, mode, argument=False):
"""
Generate Training Data for LEVEL-3
mode = train or test
"""
data = getDataFromTxt(ftxt)
trainData = defaultdict(lambda: dict(patches=[], landmarks=[]))
for (imgPath, bbox, landmarkGt) in data:
img = cv2.imread(imgPath, cv2.CV_LOAD_IMAGE_GRAYSCALE)
assert (img is not None)
logger("process %s" % imgPath)
def generate_hdf5(ftxt, output, fname, argument=False):
data = getDataFromTxt(ftxt)
F_imgs = []
F_landmarks = []
EN_imgs = []
EN_landmarks = []
NM_imgs = []
NM_landmarks = []
for (imgPath, bbox, landmarkGt) in data:
img = cv2.imread(imgPath, cv2.IMREAD_GRAYSCALE) #读取灰度图
assert (img is not None)
logger("process %s" % imgPath)
# F
f_bbox = bbox.subBBox(-0.05, 1.05, -0.05, 1.05)
f_face = img[f_bbox.top:f_bbox.bottom + 1,
f_bbox.left:f_bbox.right + 1] #截图
## data argument
if argument and np.random.rand() > -1:
### flip
face_flipped, landmark_flipped = flip(
f_face, landmarkGt) #图片翻转，数据增强，相应坐标也要发生变换
face_flipped = cv2.resize(face_flipped, (39, 39)) #固定图片大小
F_imgs.append(face_flipped.reshape((
1, 39,
39))) #caffe要求输入的格式 ['batch_size','channel','height','width']
F_landmarks.append(landmark_flipped.reshape(10)) #把10个关键坐标点值变成一维向量
### rotation
# if np.random.rand() > 0.5:
# face_rotated_by_alpha, landmark_rotated = rotate(img, f_bbox,
# bbox.reprojectLandmark(landmarkGt), 5)
# landmark_rotated = bbox.projectLandmark(landmark_rotated)
# face_rotated_by_alpha = cv2.resize(face_rotated_by_alpha, (39, 39))
# F_imgs.append(face_rotated_by_alpha.reshape((1, 39, 39)))
# F_landmarks.append(landmark_rotated.reshape(10))
# ### flip with rotation
# face_flipped, landmark_flipped = flip(face_rotated_by_alpha, landmark_rotated)
# face_flipped = cv2.resize(face_flipped, (39, 39))
# F_imgs.append(face_flipped.reshape((1, 39, 39)))
# F_landmarks.append(landmark_flipped.reshape(10))
# ### rotation
# if np.random.rand() > 0.5:
# face_rotated_by_alpha, landmark_rotated = rotate(img, f_bbox,
# bbox.reprojectLandmark(landmarkGt), -5)
# landmark_rotated = bbox.projectLandmark(landmark_rotated)
# face_rotated_by_alpha = cv2.resize(face_rotated_by_alpha, (39, 39))
# F_imgs.append(face_rotated_by_alpha.reshape((1, 39, 39)))
# F_landmarks.append(landmark_rotated.reshape(10))
# ### flip with rotation
# face_flipped, landmark_flipped = flip(face_rotated_by_alpha, landmark_rotated)
# face_flipped = cv2.resize(face_flipped, (39, 39))
# F_imgs.append(face_flipped.reshape((1, 39, 39)))
# F_landmarks.append(landmark_flipped.reshape(10))
f_face = cv2.resize(f_face, (39, 39))
en_face = f_face[:31, :]
nm_face = f_face[8:, :]
f_face = f_face.reshape((1, 39, 39))
f_landmark = landmarkGt.reshape((10))
F_imgs.append(f_face)
F_landmarks.append(f_landmark)
# EN
# en_bbox = bbox.subBBox(-0.05, 1.05, -0.04, 0.84)
# en_face = img[en_bbox.top:en_bbox.bottom+1,en_bbox.left:en_bbox.right+1]
## data argument
if argument and np.random.rand() > 0.5:
### flip
face_flipped, landmark_flipped = flip(en_face, landmarkGt)
face_flipped = cv2.resize(face_flipped, (31, 39)).reshape(
(1, 31, 39))
landmark_flipped = landmark_flipped[:3, :].reshape((6))
EN_imgs.append(face_flipped)
EN_landmarks.append(landmark_flipped)
en_face = cv2.resize(en_face, (31, 39)).reshape((1, 31, 39))
en_landmark = landmarkGt[:3, :].reshape((6))
EN_imgs.append(en_face)
EN_landmarks.append(en_landmark)
# NM
# nm_bbox = bbox.subBBox(-0.05, 1.05, 0.18, 1.05)
# nm_face = img[nm_bbox.top:nm_bbox.bottom+1,nm_bbox.left:nm_bbox.right+1]
## data argument
if argument and np.random.rand() > 0.5:
### flip
face_flipped, landmark_flipped = flip(nm_face, landmarkGt)
face_flipped = cv2.resize(face_flipped, (31, 39)).reshape(
(1, 31, 39))
landmark_flipped = landmark_flipped[2:, :].reshape((6))
NM_imgs.append(face_flipped)
NM_landmarks.append(landmark_flipped)
nm_face = cv2.resize(nm_face, (31, 39)).reshape((1, 31, 39))
nm_landmark = landmarkGt[2:, :].reshape((6))
NM_imgs.append(nm_face)
NM_landmarks.append(nm_landmark)
#imgs, landmarks = process_images(ftxt, output)
F_imgs, F_landmarks = np.asarray(F_imgs), np.asarray(F_landmarks)
EN_imgs, EN_landmarks = np.asarray(EN_imgs), np.asarray(EN_landmarks)
NM_imgs, NM_landmarks = np.asarray(NM_imgs), np.asarray(NM_landmarks)
F_imgs = processImage(F_imgs) #数据标准化
shuffle_in_unison_scary(F_imgs, F_landmarks) #随机打乱
EN_imgs = processImage(EN_imgs)
shuffle_in_unison_scary(EN_imgs, EN_landmarks)
NM_imgs = processImage(NM_imgs)
shuffle_in_unison_scary(NM_imgs, NM_landmarks)
# full face
base = join(OUTPUT, '1_F')
createDir(base)
output = join(base, fname) #D:.\deep_landmark\dataset\train\1_F\train.h5
logger("generate %s" % output)
with h5py.File(output, 'w') as h5:
h5['data'] = F_imgs.astype(np.float32)
h5['landmark'] = F_landmarks.astype(np.float32)
# eye and nose
base = join(OUTPUT, '1_EN')
createDir(base)
output = join(base, fname)
logger("generate %s" % output)
with h5py.File(output, 'w') as h5:
h5['data'] = EN_imgs.astype(np.float32)
h5['landmark'] = EN_landmarks.astype(np.float32)
# nose and mouth
base = join(OUTPUT, '1_NM')
createDir(base)
output = join(base, fname)
logger("generate %s" % output)
with h5py.File(output, 'w') as h5:
h5['data'] = NM_imgs.astype(np.float32)
h5['landmark'] = NM_landmarks.astype(np.float32)
def downloadAll(serial_num, start, end, taskPool=None):
entryUrl = 'http://dp.pconline.com.cn/list/all_t%d_p%d.html'
entryUrls = [(entryUrl % (serial_num, ind))
for ind in range(start, end + 1)]
execDownloadTask(entryUrls, taskPool)
def execDownloadTask(entryUrls, taskPool=None):
if taskPool:
print 'using pool to download ...'
taskPool.map(downloadAllForAPage, entryUrls)
else:
map(downloadAllForAPage, entryUrls)
if __name__ == '__main__':
createDir(saveDir)
taskPool = Pool(processes=ncpus)
serial_num = 145
total = 4
nparts = divideNParts(total, 2)
for part in nparts:
start = part[0] + 1
end = part[1]
downloadAll(serial_num, start, end, taskPool=None)
taskPool.close()
taskPool.join()
from common import level1, level2, level3
TXT = 'dataset/test/lfpw_test_249_bbox.txt'
if __name__ == '__main__':
assert(len(sys.argv) == 2)
level = int(sys.argv[1])
if level == 0:
P = partial(level1, FOnly=True)
elif level == 1:
P = level1
elif level == 2:
P = level2
else:
P = level3
OUTPUT = 'dataset/test/out_{0}'.format(level)
createDir(OUTPUT)
data = getDataFromTxt(TXT, with_landmark=False)
for imgPath, bbox in data:
img = cv2.imread(imgPath)
assert(img is not None)
imgGray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
logger("process %s" % imgPath)
landmark = P(imgGray, bbox)
landmark = bbox.reprojectLandmark(landmark)
drawLandmark(img, bbox, landmark)
cv2.imwrite(os.path.join(OUTPUT, os.path.basename(imgPath)), img)
def generate_hdf5(ftxt, output, fname, argument=False):
data = getDataFromTxt(ftxt)
F_imgs = []
F_landmarks = []
EN_imgs = []
EN_landmarks = []
NM_imgs = []
NM_landmarks = []
for (imgPath, bbox, landmarkGt) in data:
img = cv2.imread(imgPath, cv2.CV_LOAD_IMAGE_GRAYSCALE)
assert (img is not None)
logger("process %s" % imgPath)
# F
f_bbox = bbox.subBBox(-0.05, 1.05, -0.05, 1.05)
f_face = img[f_bbox.top:f_bbox.bottom + 1,
f_bbox.left:f_bbox.right + 1]
## data argument
if argument and np.random.rand() > -1:
### flip
face_flipped, landmark_flipped = flip(f_face, landmarkGt)
face_flipped = cv2.resize(face_flipped, (39, 39))
F_imgs.append(face_flipped.reshape((1, 39, 39)))
F_landmarks.append(landmark_flipped.reshape(10))
### rotation
if np.random.rand() > 0.5:
face_rotated_by_alpha, landmark_rotated = rotate(img, f_bbox, \
bbox.reprojectLandmark(landmarkGt), 5)
landmark_rotated = bbox.projectLandmark(landmark_rotated)
face_rotated_by_alpha = cv2.resize(face_rotated_by_alpha,
(39, 39))
F_imgs.append(face_rotated_by_alpha.reshape((1, 39, 39)))
F_landmarks.append(landmark_rotated.reshape(10))
### flip with rotation
face_flipped, landmark_flipped = flip(face_rotated_by_alpha,
landmark_rotated)
face_flipped = cv2.resize(face_flipped, (39, 39))
F_imgs.append(face_flipped.reshape((1, 39, 39)))
F_landmarks.append(landmark_flipped.reshape(10))
### rotation
if np.random.rand() > 0.5:
face_rotated_by_alpha, landmark_rotated = rotate(img, f_bbox, \
bbox.reprojectLandmark(landmarkGt), -5)
landmark_rotated = bbox.projectLandmark(landmark_rotated)
face_rotated_by_alpha = cv2.resize(face_rotated_by_alpha,
(39, 39))
F_imgs.append(face_rotated_by_alpha.reshape((1, 39, 39)))
F_landmarks.append(landmark_rotated.reshape(10))
### flip with rotation
face_flipped, landmark_flipped = flip(face_rotated_by_alpha,
landmark_rotated)
face_flipped = cv2.resize(face_flipped, (39, 39))
F_imgs.append(face_flipped.reshape((1, 39, 39)))
F_landmarks.append(landmark_flipped.reshape(10))
f_face = cv2.resize(f_face, (39, 39))
en_face = f_face[:31, :]
nm_face = f_face[8:, :]
f_face = f_face.reshape((1, 39, 39))
f_landmark = landmarkGt.reshape((10))
F_imgs.append(f_face)
F_landmarks.append(f_landmark)
# EN
# en_bbox = bbox.subBBox(-0.05, 1.05, -0.04, 0.84)
# en_face = img[en_bbox.top:en_bbox.bottom+1,en_bbox.left:en_bbox.right+1]
## data argument
if argument and np.random.rand() > 0.5:
### flip
face_flipped, landmark_flipped = flip(en_face, landmarkGt)
face_flipped = cv2.resize(face_flipped, (31, 39)).reshape(
(1, 31, 39))
landmark_flipped = landmark_flipped[:3, :].reshape((6))
EN_imgs.append(face_flipped)
EN_landmarks.append(landmark_flipped)
en_face = cv2.resize(en_face, (31, 39)).reshape((1, 31, 39))
en_landmark = landmarkGt[:3, :].reshape((6))
EN_imgs.append(en_face)
EN_landmarks.append(en_landmark)
# NM
# nm_bbox = bbox.subBBox(-0.05, 1.05, 0.18, 1.05)
# nm_face = img[nm_bbox.top:nm_bbox.bottom+1,nm_bbox.left:nm_bbox.right+1]
## data argument
if argument and np.random.rand() > 0.5:
### flip
face_flipped, landmark_flipped = flip(nm_face, landmarkGt)
face_flipped = cv2.resize(face_flipped, (31, 39)).reshape(
(1, 31, 39))
landmark_flipped = landmark_flipped[2:, :].reshape((6))
NM_imgs.append(face_flipped)
NM_landmarks.append(landmark_flipped)
nm_face = cv2.resize(nm_face, (31, 39)).reshape((1, 31, 39))
nm_landmark = landmarkGt[2:, :].reshape((6))
NM_imgs.append(nm_face)
NM_landmarks.append(nm_landmark)
#imgs, landmarks = process_images(ftxt, output)
F_imgs, F_landmarks = np.asarray(F_imgs), np.asarray(F_landmarks)
EN_imgs, EN_landmarks = np.asarray(EN_imgs), np.asarray(EN_landmarks)
NM_imgs, NM_landmarks = np.asarray(NM_imgs), np.asarray(NM_landmarks)
F_imgs = processImage(F_imgs)
shuffle_in_unison_scary(F_imgs, F_landmarks)
EN_imgs = processImage(EN_imgs)
shuffle_in_unison_scary(EN_imgs, EN_landmarks)
NM_imgs = processImage(NM_imgs)
shuffle_in_unison_scary(NM_imgs, NM_landmarks)
# full face
base = join(OUTPUT, '1_F')
createDir(base)
output = join(base, fname)
logger("generate %s" % output)
with h5py.File(output, 'w') as h5:
h5['data'] = F_imgs.astype(np.float32)
h5['landmark'] = F_landmarks.astype(np.float32)
# eye and nose
base = join(OUTPUT, '1_EN')
createDir(base)
output = join(base, fname)
logger("generate %s" % output)
with h5py.File(output, 'w') as h5:
h5['data'] = EN_imgs.astype(np.float32)
h5['landmark'] = EN_landmarks.astype(np.float32)
# nose and mouth
base = join(OUTPUT, '1_NM')
createDir(base)
output = join(base, fname)
logger("generate %s" % output)
with h5py.File(output, 'w') as h5:
h5['data'] = NM_imgs.astype(np.float32)
h5['landmark'] = NM_landmarks.astype(np.float32)
from utils import randomShift, randomShiftWithArgument
types = [(0, 'LE1', 0.11),
(0, 'LE2', 0.12),
(1, 'RE1', 0.11),
(1, 'RE2', 0.12),
(2, 'N1', 0.11),
(2, 'N2', 0.12),
(3, 'LM1', 0.11),
(3, 'LM2', 0.12),
(4, 'RM1', 0.11),
(4, 'RM2', 0.12),]
for t in types:
d = 'train/3_%s' % t[1]
createDir(d)
def generate(ftxt, mode, argument=False):
"""
Generate Training Data for LEVEL-3
mode = train or test
"""
data = getDataFromTxt(ftxt)
trainData = defaultdict(lambda: dict(patches=[], landmarks=[]))
for (imgPath, bbox, landmarkGt) in data:
img = cv2.imread(imgPath, cv2.CV_LOAD_IMAGE_GRAYSCALE)
assert(img is not None)
logger("process %s" % imgPath)
landmarkPs = randomShiftWithArgument(landmarkGt, 0.01)
from common import getDataFromTxt, createDir, logger, drawLandmark
from common import level1, level2, level3
TXT = 'dataset/test/lfpw_test_249_bbox.txt'
if __name__ == '__main__':
assert (len(sys.argv) == 2)
level = int(sys.argv[1])
if level == 0:
P = partial(level1, FOnly=True)
elif level == 1:
P = level1
elif level == 2:
P = level2
else:
P = level3
OUTPUT = 'dataset/test/out_{0}'.format(level)
createDir(OUTPUT)
data = getDataFromTxt(TXT, with_landmark=False)
for imgPath, bbox in data:
img = cv2.imread(imgPath)
assert (img is not None)
imgGray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
logger("process %s" % imgPath)
landmark = P(imgGray, bbox)
landmark = bbox.reprojectLandmark(landmark)
drawLandmark(img, bbox, landmark)
cv2.imwrite(os.path.join(OUTPUT, os.path.basename(imgPath)), img)
soup = getSoup(entryurl)
if soup is None:
return
#print soup.prettify()
picLinks = soup.find_all('a', class_='picLink')
if len(picLinks) == 0:
return
hrefs = map(lambda link: link.attrs['href'], picLinks)
print 'serials in a page: ', len(hrefs)
for serialHref in hrefs:
downloadForASerial(serialHref)
def downloadEntryUrl(serial_num, index):
entryUrl = 'http://dp.pconline.com.cn/list/all_t%d_p%d.html' % (serial_num, index)
print "entryUrl: ", entryUrl
downloadAllForAPage(entryUrl)
return 0
def downloadAll(serial_num):
start = 1
end = 2
return [downloadEntryUrl(serial_num, index) for index in range(start, end+1)]
serial_num = 145
if __name__ == '__main__':
createDir(saveDir)
downloadAll(serial_num)
def generate_hdf5(ftxt, output, fname, argument=False):
data = getDataFromTxt(ftxt)
F_imgs = []
F_landmarks = []
EN_imgs = []
EN_landmarks = []
NM_imgs = []
NM_landmarks = []
for (imgPath, bbox, landmarkGt) in data:
img = cv2.imread(imgPath, cv2.CV_LOAD_IMAGE_GRAYSCALE)
assert(img is not None)
logger("process %s" % imgPath)
# F
f_bbox = bbox.subBBox(-0.05, 1.05, -0.05, 1.05)
f_face = img[f_bbox.top:f_bbox.bottom+1,f_bbox.left:f_bbox.right+1]
## data argument
if argument and np.random.rand() > -1:
### flip
face_flipped, landmark_flipped = flip(f_face, landmarkGt)
face_flipped = cv2.resize(face_flipped, (39, 39))
F_imgs.append(face_flipped.reshape((1, 39, 39)))
F_landmarks.append(landmark_flipped.reshape(10))
### rotation
if np.random.rand() > 0.5:
face_rotated_by_alpha, landmark_rotated = rotate(img, f_bbox, \
bbox.reprojectLandmark(landmarkGt), 5)
landmark_rotated = bbox.projectLandmark(landmark_rotated)
face_rotated_by_alpha = cv2.resize(face_rotated_by_alpha, (39, 39))
F_imgs.append(face_rotated_by_alpha.reshape((1, 39, 39)))
F_landmarks.append(landmark_rotated.reshape(10))
### flip with rotation
face_flipped, landmark_flipped = flip(face_rotated_by_alpha, landmark_rotated)
face_flipped = cv2.resize(face_flipped, (39, 39))
F_imgs.append(face_flipped.reshape((1, 39, 39)))
F_landmarks.append(landmark_flipped.reshape(10))
### rotation
if np.random.rand() > 0.5:
face_rotated_by_alpha, landmark_rotated = rotate(img, f_bbox, \
bbox.reprojectLandmark(landmarkGt), -5)
landmark_rotated = bbox.projectLandmark(landmark_rotated)
face_rotated_by_alpha = cv2.resize(face_rotated_by_alpha, (39, 39))
F_imgs.append(face_rotated_by_alpha.reshape((1, 39, 39)))
F_landmarks.append(landmark_rotated.reshape(10))
### flip with rotation
face_flipped, landmark_flipped = flip(face_rotated_by_alpha, landmark_rotated)
face_flipped = cv2.resize(face_flipped, (39, 39))
F_imgs.append(face_flipped.reshape((1, 39, 39)))
F_landmarks.append(landmark_flipped.reshape(10))
f_face = cv2.resize(f_face, (39, 39))
en_face = f_face[:31, :]
nm_face = f_face[8:, :]
f_face = f_face.reshape((1, 39, 39))
f_landmark = landmarkGt.reshape((10))
F_imgs.append(f_face)
F_landmarks.append(f_landmark)
# EN
# en_bbox = bbox.subBBox(-0.05, 1.05, -0.04, 0.84)
# en_face = img[en_bbox.top:en_bbox.bottom+1,en_bbox.left:en_bbox.right+1]
## data argument
if argument and np.random.rand() > 0.5:
### flip
face_flipped, landmark_flipped = flip(en_face, landmarkGt)
face_flipped = cv2.resize(face_flipped, (31, 39)).reshape((1, 31, 39))
landmark_flipped = landmark_flipped[:3, :].reshape((6))
EN_imgs.append(face_flipped)
EN_landmarks.append(landmark_flipped)
en_face = cv2.resize(en_face, (31, 39)).reshape((1, 31, 39))
en_landmark = landmarkGt[:3, :].reshape((6))
EN_imgs.append(en_face)
EN_landmarks.append(en_landmark)
# NM
# nm_bbox = bbox.subBBox(-0.05, 1.05, 0.18, 1.05)
# nm_face = img[nm_bbox.top:nm_bbox.bottom+1,nm_bbox.left:nm_bbox.right+1]
## data argument
if argument and np.random.rand() > 0.5:
### flip
face_flipped, landmark_flipped = flip(nm_face, landmarkGt)
face_flipped = cv2.resize(face_flipped, (31, 39)).reshape((1, 31, 39))
landmark_flipped = landmark_flipped[2:, :].reshape((6))
NM_imgs.append(face_flipped)
NM_landmarks.append(landmark_flipped)
nm_face = cv2.resize(nm_face, (31, 39)).reshape((1, 31, 39))
nm_landmark = landmarkGt[2:, :].reshape((6))
NM_imgs.append(nm_face)
NM_landmarks.append(nm_landmark)
#imgs, landmarks = process_images(ftxt, output)
F_imgs, F_landmarks = np.asarray(F_imgs), np.asarray(F_landmarks)
EN_imgs, EN_landmarks = np.asarray(EN_imgs), np.asarray(EN_landmarks)
NM_imgs, NM_landmarks = np.asarray(NM_imgs),np.asarray(NM_landmarks)
F_imgs = processImage(F_imgs)
shuffle_in_unison_scary(F_imgs, F_landmarks)
EN_imgs = processImage(EN_imgs)
shuffle_in_unison_scary(EN_imgs, EN_landmarks)
NM_imgs = processImage(NM_imgs)
shuffle_in_unison_scary(NM_imgs, NM_landmarks)
# full face
base = join(OUTPUT, '1_F')
createDir(base)
output = join(base, fname)
logger("generate %s" % output)
with h5py.File(output, 'w') as h5:
h5['data'] = F_imgs.astype(np.float32)
h5['landmark'] = F_landmarks.astype(np.float32)
# eye and nose
base = join(OUTPUT, '1_EN')
createDir(base)
output = join(base, fname)
logger("generate %s" % output)
with h5py.File(output, 'w') as h5:
h5['data'] = EN_imgs.astype(np.float32)
h5['landmark'] = EN_landmarks.astype(np.float32)
# nose and mouth
base = join(OUTPUT, '1_NM')
createDir(base)
output = join(base, fname)
logger("generate %s" % output)
with h5py.File(output, 'w') as h5:
h5['data'] = NM_imgs.astype(np.float32)
h5['landmark'] = NM_landmarks.astype(np.float32)
def generate_hdf5(ftxt, output, fname, argument=False):
'''
生成hdf5
:param ftxt: 图片路径对应人脸框和左眼睛、右眼睛、鼻子、左嘴角、右嘴角对应坐标
:param output: hdf5存放位置
:param fname: 保存名称
:param argument:
:return:
'''
data = getDataFromTxt(ftxt)
# 全局图片
F_imgs = []
# 全局坐标
F_landmarks = []
# 只包含了eye nose的图片
EN_imgs = []
# 只包含了eye nose的坐标
EN_landmarks = []
# 只包含nose mouth的图片
NM_imgs = []
# 只包含了nose mouth的坐标
NM_landmarks = []
for (imgPath, bbox, landmarkGt) in data:
img = cv2.imread(imgPath, cv2.IMREAD_GRAYSCALE)
assert(img is not None)
logger("process %s" % imgPath)
# 人脸框有点小，扩大一点
f_bbox = bbox.subBBox(-0.05, 1.05, -0.05, 1.05)
# 人脸框里面的图像
f_face = img[int(f_bbox.top):int(f_bbox.bottom+1),int(f_bbox.left):int(f_bbox.right+1)]
## data argument
if argument and np.random.rand() > -1:
### flip 图片水平翻转，数据增强
face_flipped, landmark_flipped = flip(f_face, landmarkGt)
face_flipped = cv2.resize(face_flipped, (39, 39))
# 1表示通道
F_imgs.append(face_flipped.reshape((1, 39, 39)))
# 5*2的关键点转换为一位数组
F_landmarks.append(landmark_flipped.reshape(10))
### rotation
if np.random.rand() > 0.5:
face_rotated_by_alpha, landmark_rotated = rotate(img, f_bbox, \
bbox.reprojectLandmark(landmarkGt), 5)
landmark_rotated = bbox.projectLandmark(landmark_rotated)
face_rotated_by_alpha = cv2.resize(face_rotated_by_alpha, (39, 39))
F_imgs.append(face_rotated_by_alpha.reshape((1, 39, 39)))
F_landmarks.append(landmark_rotated.reshape(10))
### flip with rotation
face_flipped, landmark_flipped = flip(face_rotated_by_alpha, landmark_rotated)
face_flipped = cv2.resize(face_flipped, (39, 39))
F_imgs.append(face_flipped.reshape((1, 39, 39)))
F_landmarks.append(landmark_flipped.reshape(10))
### rotation
if np.random.rand() > 0.5:
face_rotated_by_alpha, landmark_rotated = rotate(img, f_bbox, \
bbox.reprojectLandmark(landmarkGt), -5)
landmark_rotated = bbox.projectLandmark(landmark_rotated)
face_rotated_by_alpha = cv2.resize(face_rotated_by_alpha, (39, 39))
F_imgs.append(face_rotated_by_alpha.reshape((1, 39, 39)))
F_landmarks.append(landmark_rotated.reshape(10))
### flip with rotation
face_flipped, landmark_flipped = flip(face_rotated_by_alpha, landmark_rotated)
face_flipped = cv2.resize(face_flipped, (39, 39))
F_imgs.append(face_flipped.reshape((1, 39, 39)))
F_landmarks.append(landmark_flipped.reshape(10))
f_face = cv2.resize(f_face, (39, 39))
# 眼睛和鼻子
en_face = f_face[:31, :]
# 鼻子和嘴巴
nm_face = f_face[8:, :]
f_face = f_face.reshape((1, 39, 39))
f_landmark = landmarkGt.reshape((10))
F_imgs.append(f_face)
F_landmarks.append(f_landmark)
# EN
# en_bbox = bbox.subBBox(-0.05, 1.05, -0.04, 0.84)
# en_face = img[en_bbox.top:en_bbox.bottom+1,en_bbox.left:en_bbox.right+1]
## data argument
if argument and np.random.rand() > 0.5:
### flip
face_flipped, landmark_flipped = flip(en_face, landmarkGt)
face_flipped = cv2.resize(face_flipped, (31, 39)).reshape((1, 31, 39))
landmark_flipped = landmark_flipped[:3, :].reshape((6))
EN_imgs.append(face_flipped)
EN_landmarks.append(landmark_flipped)
en_face = cv2.resize(en_face, (31, 39)).reshape((1, 31, 39))
en_landmark = landmarkGt[:3, :].reshape((6))
EN_imgs.append(en_face)
EN_landmarks.append(en_landmark)
# NM
# nm_bbox = bbox.subBBox(-0.05, 1.05, 0.18, 1.05)
# nm_face = img[nm_bbox.top:nm_bbox.bottom+1,nm_bbox.left:nm_bbox.right+1]
## data argument
if argument and np.random.rand() > 0.5:
### flip
face_flipped, landmark_flipped = flip(nm_face, landmarkGt)
face_flipped = cv2.resize(face_flipped, (31, 39)).reshape((1, 31, 39))
landmark_flipped = landmark_flipped[2:, :].reshape((6))
NM_imgs.append(face_flipped)
NM_landmarks.append(landmark_flipped)
nm_face = cv2.resize(nm_face, (31, 39)).reshape((1, 31, 39))
nm_landmark = landmarkGt[2:, :].reshape((6))
NM_imgs.append(nm_face)
NM_landmarks.append(nm_landmark)
#imgs, landmarks = process_images(ftxt, output)
F_imgs, F_landmarks = np.asarray(F_imgs), np.asarray(F_landmarks)
EN_imgs, EN_landmarks = np.asarray(EN_imgs), np.asarray(EN_landmarks)
NM_imgs, NM_landmarks = np.asarray(NM_imgs),np.asarray(NM_landmarks)
F_imgs = processImage(F_imgs)
shuffle_in_unison_scary(F_imgs, F_landmarks)
EN_imgs = processImage(EN_imgs)
shuffle_in_unison_scary(EN_imgs, EN_landmarks)
NM_imgs = processImage(NM_imgs)
shuffle_in_unison_scary(NM_imgs, NM_landmarks)
# full face
base = join(OUTPUT, '1_F')
createDir(base)
output = join(base, fname)
logger("generate %s" % output)
with h5py.File(output, 'w') as h5:
h5['data'] = F_imgs.astype(np.float32)
h5['landmark'] = F_landmarks.astype(np.float32)
# eye and nose
base = join(OUTPUT, '1_EN')
createDir(base)
output = join(base, fname)
logger("generate %s" % output)
with h5py.File(output, 'w') as h5:
h5['data'] = EN_imgs.astype(np.float32)
h5['landmark'] = EN_landmarks.astype(np.float32)
# nose and mouth
base = join(OUTPUT, '1_NM')
createDir(base)
output = join(base, fname)
logger("generate %s" % output)
with h5py.File(output, 'w') as h5:
h5['data'] = NM_imgs.astype(np.float32)
h5['landmark'] = NM_landmarks.astype(np.float32)