def generate_h5py(data, h5_path, txt_path, augment=False):
'''
Get images and turn them into h5py files
Input:
- data: a tuple of [imgpath, bbox, landmark]
- h5_path: h5py file name
- txt_path: h5 txt name
'''
F_imgs = []
F_landmarks = []
for (imgpath, bbox, landmark) in data:
img = cv2.imread(imgpath, cv2.CV_LOAD_IMAGE_GRAYSCALE)
print("processing %s") % imgpath
if not check_bbox(img, bbox):
print 'BBox out of range.'
continue
face = img[bbox.top:bbox.bottom, bbox.left:bbox.right]
if augment:
face_flip, landmark_flip = flip(face, landmark)
face_flip = cv2.resize(face_flip, (39, 39)).reshape(1, 39, 39)
landmark_flip = landmark_flip.reshape(10)
F_imgs.append(face_flip)
F_landmarks.append(landmark_flip)
face = cv2.resize(face, (39, 39)).reshape(1, 39, 39)
landmark = landmark.reshape(10)
F_imgs.append(face)
F_landmarks.append(landmark)
F_imgs, F_landmarks = np.asarray(F_imgs), np.asarray(F_landmarks)
F_imgs = processImage(F_imgs)
F_imgs, F_landmarks = shuffle(F_imgs, F_landmarks, random_state=42)
with h5py.File(h5_path, 'w') as f:
f['data'] = F_imgs.astype(np.float32)
f['landmarks'] = F_landmarks.astype(np.float32)
with open(txt_path, 'w') as f:
f.write(h5_path)
def generate_h5py(data, h5_path, txt_path, augment=False):
'''
Get images and turn them into h5py files
Input:
- data: a tuple of [imgpath, bbox, landmark]
- h5_path: h5py file name
- txt_path: h5 txt name
'''
F_imgs = []
F_landmarks = []
img_size = 40
num_landmark = 68 * 2
num_sample = 0
for (imgpath, bbox, landmarkGt) in data:
img = cv2.imread(imgpath, cv2.CV_LOAD_IMAGE_GRAYSCALE)
print("processing %s") % imgpath
if not check_bbox(img, bbox):
print 'BBox out of range.'
continue
face = img[bbox.top:bbox.bottom, bbox.left:bbox.right]
if augment:
# flip the face
#face_flip, landmark_flip = flip(face, landmarkGt)
#face_flip = cv2.resize(face_flip, (img_size,img_size)).reshape(1,img_size,img_size)
#fit=0
#for i in range(0,num_landmark/2):
# if landmark_flip[i,0]<0 or landmark_flip[i,0]>1 or landmark_flip[i,1]<0 or landmark_flip[i,1]>1:
# fit=1
# break
#if fit==0:
#print landmark_flipped_alpha
# F_imgs.append(face_flip)
# F_landmarks.append(landmark_flip.reshape(num_landmark))
#print landmark_flip
#angles=[5,10,15,20,25,30,-5,-10,-15,-20,-25,-30]
#for alpha in angles:
# rotate the face
#face_rotated_by_alpha, landmark_rotated_alpha = rotate(img, bbox,bbox.reprojectLandmark(landmarkGt), alpha)
#landmark_rotated_alpha = bbox.projectLandmark(landmark_rotated_alpha)
#face_rotated_by_alpha = cv2.resize(face_rotated_by_alpha, (img_size,img_size))
#fit=0
#for i in range(0,num_landmark/2):
# if landmark_rotated_alpha[i,0]<0 or landmark_rotated_alpha[i,0]>1 or landmark_rotated_alpha[i,1]<0 or landmark_rotated_alpha[i,1]>1:
# fit=1
# break
#if fit==0:
#print landmark_rotated_alpha
# F_imgs.append(face_rotated_by_alpha.reshape((1, img_size,img_size)))
# F_landmarks.append(landmark_rotated_alpha.reshape(num_landmark))
#print landmark_rotated_5
# flip with the rotation
#face_flipped_alpha, landmark_flipped_alpha = flip(face_rotated_by_alpha, landmark_rotated_alpha)
#face_flipped_alpha = cv2.resize(face_flipped_alpha, (img_size,img_size))
#fit=0
#for i in range(0,num_landmark/2):
# if landmark_flipped_alpha[i,0]<0 or landmark_flipped_alpha[i,0]>1 or landmark_flipped_alpha[i,1]<0 or landmark_flipped_alpha[i,1]>1:
# fit=1
# break
#if fit==0:
#print landmark_flipped_alpha
# F_imgs.append(face_flipped_alpha.reshape((1, img_size,img_size)))
# F_landmarks.append(landmark_flipped_alpha.reshape(num_landmark))
# debug
#center = ((bbox.left+bbox.right)/2, (bbox.top+bbox.bottom)/2)
#rot_mat = cv2.getRotationMatrix2D(center, alpha, 1)
#img_rotated_by_alpha = cv2.warpAffine(img, rot_mat, img.shape)
#landmark_rotated_alpha = bbox.reprojectLandmark(landmark_rotated_alpha) # will affect the flip "landmark_rotated_alpha"
#img_rotated_by_alpha = drawLandmark(img_rotated_by_alpha, bbox, landmark_rotated_alpha)
#fp = 'debug_results/'+ str(num_sample)+'.jpg'
#cv2.imwrite(fp, img_rotated_by_alpha)
#num_sample=num_sample+1
# debug
#use bounding box perturbation
y = bbox.top
x = bbox.left
h = bbox.bottom - bbox.top
w = bbox.right - bbox.left
# original landmark position
landmarkGT_scale = bbox.reprojectLandmark(landmarkGt)
for cur_scale in [0.83, 0.91, 1.0, 1.10, 1.21]:
for cur_x in [-0.17, 0, 0.17]:
for cur_y in [-0.17, 0, 0.17]:
s_n = 1 / cur_scale
x_n = -cur_x / cur_scale
y_n = -cur_y / cur_scale
x_temp = int(x - (x_n * w / s_n))
y_temp = int(y - (y_n * h / s_n))
w_temp = int(w / s_n)
h_temp = int(h / s_n)
# generate new bounding box
bbox_left = x_temp
bbox_right = x_temp + w_temp
bbox_top = y_temp
bbox_bottom = y_temp + h_temp
new_bbox = map(
int,
[bbox_left, bbox_right, bbox_top, bbox_bottom])
new_bbox = BBox(new_bbox)
if not check_bbox(img, new_bbox):
print 'BBox out of range.'
continue
# project landmark onto the new bounding box
new_landmarkGT = new_bbox.projectLandmark(
landmarkGT_scale)
new_landmarkGT_org = new_landmarkGT.copy()
angles = [
5, 10, 15, 20, 25, 30, -5, -10, -15, -20, -25, -30
]
for alpha in angles:
# rotate the face
face_rotated_by_alpha, landmark_rotated_alpha = rotate(
img, new_bbox,
new_bbox.reprojectLandmark(new_landmarkGT),
alpha)
landmark_rotated_alpha = new_bbox.projectLandmark(
landmark_rotated_alpha)
face_rotated_by_alpha = cv2.resize(
face_rotated_by_alpha, (img_size, img_size))
fit = 0
for i in range(0, num_landmark / 2):
if landmark_rotated_alpha[
i, 0] < 0 or landmark_rotated_alpha[
i,
0] > 1 or landmark_rotated_alpha[
i,
1] < 0 or landmark_rotated_alpha[
i, 1] > 1:
fit = 1
break
if fit == 0:
#print landmark_rotated_alpha
F_imgs.append(
face_rotated_by_alpha.reshape(
(1, img_size, img_size)))
F_landmarks.append(
landmark_rotated_alpha.reshape(
num_landmark))
# debug
#center = ((new_bbox.left+new_bbox.right)/2, (new_bbox.top+new_bbox.bottom)/2)
#rot_mat = cv2.getRotationMatrix2D(center, alpha, 1)
#img_rotated_by_alpha = cv2.warpAffine(img, rot_mat, img.shape)
#landmark_rotated_alpha = new_bbox.reprojectLandmark(landmark_rotated_alpha) # will affect the flip "landmark_rotated_alpha"
#img_rotated_by_alpha = drawLandmark(img_rotated_by_alpha, new_bbox, landmark_rotated_alpha)
#fp = 'debug_results/'+ str(num_sample)+'.jpg'
#cv2.imwrite(fp, img_rotated_by_alpha)
#num_sample=num_sample+1
# debug
# project landmark onto the new bounding box
landmarkGT_project = new_landmarkGT_org.copy(
) # error is fixed here
#print landmarkGT_project
fit = 0
for i in range(0, num_landmark / 2):
if landmarkGT_project[
i, 0] < 0 or landmarkGT_project[
i, 0] > 1 or landmarkGT_project[
i, 1] < 0 or landmarkGT_project[
i, 1] > 1:
fit = 1
break
if fit == 0:
#print landmarkGT_project
#if landmarkGT_project[i,0]<0 or landmarkGT_project[i,0]>1 or landmarkGT_project[i,1]<0 or landmarkGT_project[i,1]>1:
# pdb.set_trace()
cropped_face = img[new_bbox.top:new_bbox.bottom,
new_bbox.left:new_bbox.right]
cropped_face = cv2.resize(
cropped_face, (img_size, img_size)).reshape(
1, img_size, img_size)
F_imgs.append(cropped_face)
F_landmarks.append(
landmarkGT_project.reshape(num_landmark))
# debug on the bounding box perturbation
#landmark_org = new_bbox.reprojectLandmark(landmarkGT_project) # will affect the flip "landmark_rotated_alpha"
#img_debug = drawLandmark(img, new_bbox, landmark_org)
#fp = 'debug_results/'+ str(num_sample)+'_bbox.jpg'
#cv2.imwrite(fp, img_debug)
#num_sample=num_sample+1
face = cv2.resize(face,
(img_size, img_size)).reshape(1, img_size, img_size)
fit = 0
for i in range(0, num_landmark / 2):
if landmarkGt[i, 0] < 0 or landmarkGt[i, 0] > 1 or landmarkGt[
i, 1] < 0 or landmarkGt[i, 1] > 1:
fit = 1
break
if fit == 0:
#print landmark_flipped_alpha
F_imgs.append(face)
F_landmarks.append(landmarkGt.reshape(num_landmark))
F_imgs, F_landmarks = np.asarray(F_imgs), np.asarray(F_landmarks)
F_imgs = processImage(F_imgs)
F_imgs, F_landmarks = shuffle(F_imgs, F_landmarks, random_state=42)
with h5py.File(h5_path, 'w') as f:
f['data'] = F_imgs.astype(np.float32)
f['landmarks'] = F_landmarks.astype(np.float32)
with open(txt_path, 'w') as f:
f.write(h5_path)
f.write(str(len(F_landmarks)))
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
print 'predicting %s' % img_path
face = load_test_img(gray, bbox)
landmark = net.forward(face, 'fc2')
landmark = bbox.reprojectLandmark(landmark)
img = drawLandmark(img, bbox, landmark)
fp = os.path.join(test_dir_out, os.path.basename(img_path))
cv2.imwrite(fp, img)
# Test for celeba dataset
elif len(sys.argv) == 3 and sys.argv[2] == 'celeba':
data = load_celeba_data()
train, val, test = get_train_val_test_list()
test_data = [data[i - 1] for i in test]
for (img_path, bbox, landmark_ground) in test_data:
img = cv2.imread(img_path)
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
print 'predicting %s' % img_path
if not check_bbox(gray, bbox):
print 'BBox out of range...'
continue
face = load_test_img(gray, bbox)
landmark = net.forward(face, 'fc2')
landmark = bbox.reprojectLandmark(landmark)
img = drawLandmark(img, bbox, landmark)
fp = os.path.join(test_dir_out, os.path.basename(img_path))
cv2.imwrite(fp, img)
#y_min=face[1]
#x_max=face[0] + face[2]
#y_max=face[1]+face[3]
# used by dlib
x_min = face.left()
y_min = face.top()
x_max = face.right()
y_max = face.bottom()
w, h = x_max - x_min, y_max - y_min
w = h = min(w, h)
x_new = x_min - w * ratio
y_new = y_min - h * ratio
w_new = w * (1 + 2 * ratio)
h_new = h * (1 + 2 * ratio)
new_bbox = map(int, [x_new, x_new + w_new, y_new, y_new + h_new])
new_bbox = BBox(new_bbox)
#print bbox_left,bbox_top,bbox_right,bbox_bottom
if not check_bbox(gray.transpose(), new_bbox):
print 'BBox out of range.'
continue
face = load_test_img(gray, new_bbox)
#landmark = net.forward(face, 'Dense2')
#print landmark
#landmark = new_bbox.reprojectLandmark(landmark)
gender = net.forward_gender(face, 'prob_gender')
age = net.forward_age(face, 'prob_age')
img = drawAttribute(img, new_bbox, gender, age)
#img = drawLandmark_multiple(img, new_bbox, landmark)
cv2.imwrite('demo_result.jpg', img)
landmark = net.forward(face, 'fc2') landmark = bbox.reprojectLandmark(landmark) img = drawLandmark(img, bbox, landmark) fp = os.path.join(test_dir_out, os.path.basename(img_path)) cv2.imwrite(fp, img) # Test for celeba dataset elif len(sys.argv) == 3 and sys.argv[2] == 'celeba': data = load_celeba_data() train, val, test = get_train_val_test_list() test_data = [data[i-1] for i in test] for (img_path, bbox, landmark_ground) in test_data: img = cv2.imread(img_path) gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY) print 'predicting %s' % img_path if not check_bbox(gray, bbox): print 'BBox out of range...' continue face = load_test_img(gray, bbox) landmark = net.forward(face, 'fc2') landmark = bbox.reprojectLandmark(landmark) img = drawLandmark(img, bbox, landmark) fp = os.path.join(test_dir_out, os.path.basename(img_path)) cv2.imwrite(fp, img)