def E(level=1):
if level == 0:
from common import level1 as P
P = partial(P, FOnly=True) # high order function, here we only test LEVEL-1 F CNN
elif level == 1:
from common import level1 as P
elif level == 2:
from common import level2 as P
else:
from common import level3 as P
data = getDataFromTxt(TXT)
error = np.zeros((len(data), 5))
for i in range(len(data)):
imgPath, bbox, landmarkGt = data[i]
img = cv2.imread(imgPath, cv2.CV_LOAD_IMAGE_GRAYSCALE)
assert(img is not None)
logger("process %s" % imgPath)
landmarkP = P(img, bbox)
# real landmark
landmarkP = bbox.reprojectLandmark(landmarkP)
landmarkGt = bbox.reprojectLandmark(landmarkGt)
error[i] = evaluateError(landmarkGt, landmarkP, bbox)
return error
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 E(level=1):
if level == 0:
from common import level1 as P
P = partial(P, FOnly=True) # high order function, here we only test LEVEL-1 F CNN
elif level == 1:
from common import level1 as P
elif level == 2:
from common import level2 as P
else:
from common import level3 as P
data = getDataFromTxt(TXT)
error = np.zeros((len(data), 5))
for i in range(len(data)):
imgPath, bbox, landmarkGt = data[i]
img = cv2.imread(imgPath, cv2.CV_LOAD_IMAGE_GRAYSCALE)
assert(img is not None)
logger("process %s" % imgPath)
landmarkP = P(img, bbox)
# real landmark
landmarkP = bbox.reprojectLandmark(landmarkP)
landmarkGt = bbox.reprojectLandmark(landmarkGt)
error[i] = evaluateError(landmarkGt, landmarkP, bbox)
return error
def geneDataTxt(imgPath, landmarks):
imgTxt = 'dataset/data/testImageList.txt'
data = getDataFromTxt(imgTxt, False, False) #image_path,bbox
trainData = defaultdict(lambda: dict(landmarks=[], patches=[], label=[]))
logger(
"generate 25 positive samples and 500 negative samples for per landmark"
)
trainData = generateSamples(trainData, data, landmarks)
arr = []
for idx, name in types:
patches = np.asarray(trainData[name]['patches'])
landmarks = np.asarray(trainData[name]['landmarks'])
label = np.asarray(trainData[name]['label'])
arr1 = landmarks.reshape(1, -1)
arr.append(arr1)
patches = processImage(patches)
shuffle_in_unison_scary(patches, landmarks, label)
with open('test/%s.txt' % (name), 'w') as fd:
fd.append(landmarks.astype(np.float32))
fd.append(patches.astype(np.float32))
fd.append(label.astype(np.uint8))
def generate_data(ftxt, fname):
data = getDataFromTxt(ftxt)
F_imgs = []
F_landmarks = []
F_genders = []
F_smiles = []
F_glasses = []
F_poses = []
F_all_attr = []
for (imgPath, bbox, landmarkGt, gender, smile, glasses, pose,
all_attr) in data:
img = cv2.imread(imgPath, cv2.IMREAD_GRAYSCALE)
print(imgPath)
assert (img is not None)
logger("process %s" % imgPath)
f_bbox = bbox
#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]
f_face = cv2.resize(f_face, (39, 39))
f_face = f_face.reshape((39, 39, 1))
f_face = f_face / 255.0
f_landmark = landmarkGt.reshape((10))
F_imgs.append(f_face)
F_landmarks.append(f_landmark)
F_genders.append(gender)
F_smiles.append(smile)
F_glasses.append(glasses)
F_poses.append(pose)
F_all_attr.append(all_attr)
F_imgs = np.asarray(F_imgs)
F_landmarks = np.asarray(F_landmarks)
F_genders = np.asarray(F_genders)
F_smiles = np.asarray(F_smiles)
F_glasses = np.asarray(F_glasses)
F_poses = np.asarray(F_poses)
F_all_attr = np.asarray(F_all_attr)
shuffle_in_unison_scary(F_imgs, F_landmarks, F_genders, F_smiles,
F_glasses, F_poses, F_all_attr)
logger("generate %s" % fname)
with h5py.File(fname, 'w') as h5:
h5['data'] = F_imgs.astype(np.float32)
h5['landmarks'] = F_landmarks.astype(np.float32)
h5['genders'] = F_genders.astype(np.float32)
h5['smiles'] = F_smiles.astype(np.float32)
h5['glasses'] = F_glasses.astype(np.float32)
h5['poses'] = F_poses.astype(np.float32)
h5['all_attr'] = F_all_attr.astype(np.float32)
def generate(ftxt, mode, argument=False):
'''
第二阶段数据源制作
:param ftxt: 数据源文件位置和label
:param mode: 训练或测试
:param argument:
:return:
'''
data = getDataFromTxt(ftxt)
trainData = defaultdict(lambda: dict(patches=[], landmarks=[]))
for (imgPath, bbox, landmarkGt) in data:
img = cv2.imread(imgPath, cv2.IMREAD_GRAYSCALE)
assert (img is not None)
logger("process %s" % imgPath)
landmarkPs = randomShiftWithArgument(landmarkGt, 0.05)
if not argument:
landmarkPs = [landmarkPs[0]]
for landmarkP in landmarkPs:
for idx, name, padding in types:
patch, patch_bbox = getPatch(img, bbox, landmarkP[idx],
padding)
patch = cv2.resize(patch, (15, 15))
patch = patch.reshape((1, 15, 15))
trainData[name]['patches'].append(patch)
_ = patch_bbox.project(bbox.reproject(landmarkGt[idx]))
trainData[name]['landmarks'].append(_)
for idx, name, padding in types:
logger('writing training data of %s' % name)
patches = np.asarray(trainData[name]['patches'])
landmarks = np.asarray(trainData[name]['landmarks'])
patches = processImage(patches)
shuffle_in_unison_scary(patches, landmarks)
with h5py.File(
'/python/face_key_point/data_hdf5/train/2_%s/%s.h5' %
(name, mode), 'w') as h5:
h5['data'] = patches.astype(np.float32)
h5['landmark'] = landmarks.astype(np.float32)
with open(
'/python/face_key_point/data_hdf5/train/2_%s/%s.txt' %
(name, mode), 'w') as fd:
fd.write('/python/face_key_point/data_hdf5/train/2_%s/%s.h5' %
(name, mode))
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)
if not argument:
landmarkPs = [landmarkPs[0]]
for landmarkP in landmarkPs:
for idx, name, padding in types:
patch, patch_bbox = getPatch(img, bbox, landmarkP[idx],
padding)
patch = cv2.resize(patch, (15, 15))
patch = patch.reshape((1, 15, 15))
trainData[name]['patches'].append(patch)
_ = patch_bbox.project(bbox.reproject(landmarkGt[idx]))
trainData[name]['landmarks'].append(_)
for idx, name, padding in types:
logger('writing training data of %s' % name)
patches = np.asarray(trainData[name]['patches'])
landmarks = np.asarray(trainData[name]['landmarks'])
patches = processImage(patches)
shuffle_in_unison_scary(patches, landmarks)
with h5py.File(
'/home/tyd/下载/deep_landmark/mydataset/mytrain/3_%s/%s.h5' %
(name, mode), 'w') as h5:
h5['data'] = patches.astype(np.float32)
h5['landmark'] = landmarks.astype(np.float32)
with open(
'/home/tyd/下载/deep_landmark/mydataset/mytrain/3_%s/%s.txt' %
(name, mode), 'w') as fd:
fd.write(
'/home/tyd/下载/deep_landmark/mydataset/mytrain/3_%s/%s.h5' %
(name, mode))
def E():
data = getDataFromTxt(TXT)
error = np.zeros((len(data), 3))
for i in range(len(data)):
imgPath, bbox, landmarkGt = data[i]
landmarkGt = landmarkGt[2:, :]
img = cv2.imread(imgPath, cv2.CV_LOAD_IMAGE_GRAYSCALE)
assert (img is not None)
logger("process %s" % imgPath)
landmarkP = NM(img, bbox)
# real landmark
landmarkP = bbox.reprojectLandmark(landmarkP)
landmarkGt = bbox.reprojectLandmark(landmarkGt)
error[i] = evaluateError(landmarkGt, landmarkP, bbox)
return error
def E():
data = getDataFromTxt(TXT)
error = np.zeros((len(data), 3))
for i in range(len(data)):
imgPath, bbox, landmarkGt = data[i]
landmarkGt = landmarkGt[2:, :]
img = cv2.imread(imgPath, cv2.CV_LOAD_IMAGE_GRAYSCALE)
assert(img is not None)
logger("process %s" % imgPath)
landmarkP = NM(img, bbox)
# real landmark
landmarkP = bbox.reprojectLandmark(landmarkP)
landmarkGt = bbox.reprojectLandmark(landmarkGt)
error[i] = evaluateError(landmarkGt, landmarkP, bbox)
return error
def generate(txt, mode, N):
"""
generate Training Data for LEVEL-2: patches around landmarks
mode: train or validate
"""
assert (mode == 'train')
#从txt文件中获取数据
data = getDataFromTxt(txt, True,
True) #return [(image_path,landmarks,bbox)]
#用defaultdict存储数据
trainData = defaultdict(lambda: dict(landmarks=[], patches=[], label=[]))
logger(
"generate 25 positive samples and 500 negative samples for per landmark"
)
#产生正负训练样本
trainData = generateSamples(trainData, data)
print 'All data:' + str(len(trainData))
#print trainData['L1']
#arr = []
for idx, name in types: #19个点
logger('writing training data of %s' % name)
patches = np.asarray(trainData[name]['patches'])
landmarks = np.asarray(trainData[name]['landmarks'])
label = np.asarray(trainData[name]['label'])
#arr1 = landmarks.reshape(1,-1)
#arr.append(arr1)
patches = processImage(patches)
shuffle_in_unison_scary(patches, landmarks, label)
#将训练数据保存为hdf5格式
with h5py.File('train/2_%s/%s.h5' % (name, mode), 'w') as h5:
h5['data'] = patches.astype(np.float32)
h5['landmark'] = landmarks.astype(np.float32)
h5['label'] = label.astype(np.uint8)
with open('train/2_%s/%s.txt' % (name, mode), 'w') as fd:
fd.write('train/2_%s/%s.h5' % (name, mode))
#暂时只产生一个点的数据
if idx == 1:
break
def E(level=1):
if level == 1:
from common import level1 as P
elif level == 2:
from common import level2 as P
data = getDataFromTxt(TXT)
error = np.zeros((len(data), 19))
for i in range(len(data)):
imgPath, bbox, landmarkGt = data[i]
img = cv2.imread(imgPath, cv2.CV_LOAD_IMAGE_GRAYSCALE)
assert (img is not None)
logger("process %s" % imgPath)
landmarkP = P(img, bbox)
#real landmark
landmarkP = bbox.reprojectLandmark(landmarkP)
landmarkGt = bbox.reprojectLandmark(landmarkGt)
error[i] = evaluateError(landmarkGt, landmarkP, bbox)
return error
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)
if not argument:
landmarkPs = [landmarkPs[0]]
for landmarkP in landmarkPs:
for idx, name, padding in types:
patch, patch_bbox = getPatch(img, bbox, landmarkP[idx], padding)
patch = cv2.resize(patch, (15, 15))
patch = patch.reshape((1, 15, 15))
trainData[name]['patches'].append(patch)
_ = patch_bbox.project(bbox.reproject(landmarkGt[idx]))
trainData[name]['landmarks'].append(_)
for idx, name, padding in types:
logger('writing training data of %s'%name)
patches = np.asarray(trainData[name]['patches'])
landmarks = np.asarray(trainData[name]['landmarks'])
patches = processImage(patches)
shuffle_in_unison_scary(patches, landmarks)
with h5py.File('train/3_%s/%s.h5'%(name, mode), 'w') as h5:
h5['data'] = patches.astype(np.float32)
h5['landmark'] = landmarks.astype(np.float32)
with open('train/3_%s/%s.txt'%(name, mode), 'w') as fd:
fd.write('train/3_%s/%s.h5'%(name, mode))
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)
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:
fd.write(landmarks.astype(np.float32))
fd.write(patches.astype(np.float32))
fd.write(label.astype(np.uint8))'''
TXT = 'dataset/data/'
if __name__ == '__main__':
txtFile = os.path.join(TXT,'testImageList.txt')
data = getDataFromTxt(txtFile,with_landmark=False) #imgPath,bbox
for imgPath,bbox in data:
print imgPath
img = cv2.imread(imgPath,cv2.CV_LOAD_IMAGE_GRAYSCALE)
assert(img is not None)
#landmarks = level1(img,bbox) #正常情况下，应该用level1学习出来的坐标作为初始化
landmarkREF = [[835,996],[1473,1029],[1289,1279],[604,1228],[1375,1654],
[1386,2019],[1333,2200],[1263,2272],[1305,2252],[694,1805],
[1460,1870],[1450,1864],[1588,1753],[1569,2013],[1514,1620],
[1382,2310],[944,1506],[1436,1569],[664,1340]]#随机选取的坐标,这里用了第一张作为初始化
landmarkREF = np.array(landmarkREF,dtype=int)
drawBBoxLandmark(img,bbox,landmarkREF,color=(0,255,0))
geneDataTxt(imgPath,landmarkREF)#test/L1.txt
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 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)
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)
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)
