def predict_68pts(param, roi_box):
pts68 = reconstruct_vertex(param, dense=False)
pts68 = pts68[:2, :]
sx, sy, ex, ey = roi_box
scale_x = (ex - sx) / 120
scale_y = (ey - sy) / 120
pts68[0, :] = pts68[0, :] * scale_x + sx
pts68[1, :] = pts68[1, :] * scale_y + sy
return pts68
def _predict_vertices(param, roi_box, dense):
vertex = reconstruct_vertex(param, dense=dense)
sx, sy, ex, ey = roi_box
scale_x = (ex - sx) / 120
scale_y = (ey - sy) / 120
vertex[0, :] = vertex[0, :] * scale_x + sx
vertex[1, :] = vertex[1, :] * scale_y + sy
s = (scale_x + scale_y) / 2
vertex[2, :] *= s
return vertex
def gen_3d_vertex():
filelists = 'test.data/AFLW2000-3D_crop.list'
root = 'test.data/AFLW-2000-3D/'
fns = open(filelists).read().strip().split('\n')
params = _load('results/params_aflw2000_xgtu.npy')
for i in range(100):
fn = fns[i]
vertex = reconstruct_vertex(params[i], dense=True)
wfp = osp.join('results/AFLW-2000-3D_vertex/',
fn.replace('.jpg', '.mat'))
print(wfp)
sio.savemat(wfp, {'vertex': vertex})
def draw_landmarks():
root_ori = 'test.data/AFLW-2000-3D'
root = 'test.data/AFLW2000-3D_crop'
filelists = 'test.data/AFLW2000-3D_crop.list'
fns = open(filelists).read().strip().split('\n')
params = _load('results/params_aflw2000_xgtu.npy')
for i in range(len(fns)):
plt.close()
img_fp = osp.join(root_ori, fns[i])
img = io.imread(img_fp)
lms = reconstruct_vertex(params[i], dense=False)
lms = convert_to_ori(lms, i)
# lms = convert_to_ori_frmMat(lms, [root + fns[i]])
# print(lms.shape)
fig = plt.figure(figsize=plt.figaspect(.5))
# fig = plt.figure(figsize=(8, 4))
ax = fig.add_subplot(1, 2, 1)
ax.imshow(img)
alpha = 0.8
markersize = 1.5
lw = 1.2
color = 'w'
markeredgecolor = 'b'
nums = [0, 17, 22, 27, 31, 36, 42, 48, 60, 68]
for ind in range(len(nums) - 1):
l, r = nums[ind], nums[ind + 1]
ax.plot(lms[0, l:r],
lms[1, l:r],
color=color,
lw=lw,
alpha=alpha - 0.1)
ax.plot(lms[0, l:r],
lms[1, l:r],
marker='o',
linestyle='None',
markersize=markersize,
color=color,
markeredgecolor=markeredgecolor,
alpha=alpha)
ax.axis('off')
plt.savefig('results/3dLandmarks_proj_resnet50_4chls/' +
img_fp.split('/')[-1])
def gen_3d_vertex():
filelists = 'test.data/AFLW2000-3D_crop.list'
root = 'AFLW-2000-3D/'
fns = open(filelists).read().strip().split('\n')
params = _load('res/params_aflw2000.npy')
sel = [
'00427', '00439', '00475', '00477', '00497', '00514', '00562', '00623',
'01045', '01095', '01104', '01506', '01621', '02214', '02244', '03906',
'04157'
]
sel = list(map(lambda x: f'image{x}.jpg', sel))
for i in range(2000):
fn = fns[i]
if fn in sel:
vertex = reconstruct_vertex(params[i], dense=True)
wfp = osp.join('res/AFLW-2000-3D_vertex/',
fn.replace('.jpg', '.mat'))
print(wfp)
sio.savemat(wfp, {'vertex': vertex})
def benchmark_aflw2000_params(params):
outputs = []
for i in range(params.shape[0]):
lm = reconstruct_vertex(params[i])
outputs.append(lm[:2, :])
return _benchmark_aflw2000(outputs)
def main(args):
# 1. load pretained model
checkpoint_fp = 'models/phase1_wpdc_vdc_v2.pth.tar'
arch = 'mobilenet_1'
checkpoint = torch.load(
checkpoint_fp, map_location=lambda storage, loc: storage)['state_dict']
model = getattr(mobilenet_v1, arch)(num_classes=62)
model_dict = model.state_dict()
for k in checkpoint.keys():
model_dict[k.replace('module.', '')] = checkpoint[k]
model.load_state_dict(model_dict)
if args.mode == 'gpu':
cudnn.benchmark = True
model = model.cuda()
model.eval()
# 2. load dlib model
dlib_landmark_model = 'models/shape_predictor_68_face_landmarks.dat'
face_detector = dlib.get_frontal_face_detector()
face_regressor = dlib.shape_predictor(dlib_landmark_model)
# 3. forward pass: one step strategy
tri = sio.loadmat('visualize/tri.mat')['tri']
for img_fp in args.files:
img_ori = cv2.imread(img_fp)
if args.dlib_bbox:
rects = face_detector(img_ori, 1)
else:
rects = []
if len(rects) == 0:
rects = dlib.rectangles()
rect_fp = img_fp + '.bbox'
lines = open(rect_fp).read().strip().split('\n')[1:]
for l in lines:
l, r, t, b = [int(_) for _ in l.split(' ')[1:]]
rect = dlib.rectangle(l, r, t, b)
rects.append(rect)
pts_dlib = []
pts_res = []
ind = 0
suffix = get_suffix(img_fp)
for rect in rects:
# landmark & crop
pts = face_regressor(img_ori, rect).parts()
pts = np.array([[pt.x, pt.y] for pt in pts]).T
pts_dlib.append(pts)
roi_box = calc_roi_box(pts)
img = crop_img(img_ori, roi_box)
# forward: one step
img = cv2.resize(img,
dsize=(120, 120),
interpolation=cv2.INTER_LINEAR)
transform = transforms.Compose(
[ToTensorGjz(),
NormalizeGjz(mean=127.5, std=128)])
input = transform(img).unsqueeze(0)
with torch.no_grad():
if args.mode == 'gpu':
input = input.cuda()
param = model(input)
param = param.squeeze().cpu().numpy().flatten().astype(
np.float32)
# 68 pts
pts68 = predict_68pts(param, roi_box)
if args.box_init == 'two':
roi_box_step2 = calc_roi_box(pts68)
img_step2 = crop_img(img_ori, roi_box_step2)
img_step2 = cv2.resize(img_step2,
dsize=(120, 120),
interpolation=cv2.INTER_LINEAR)
input = transform(img_step2).unsqueeze(0)
with torch.no_grad():
if args.mode == 'gpu':
input = input.cuda()
param = model(input)
param = param.squeeze().cpu().numpy().flatten().astype(
np.float32)
pts68 = predict_68pts(param, roi_box_step2)
pts_res.append(pts68)
# dense face vertices
if args.dump_ply or args.dump_vertex:
vertices = reconstruct_vertex(param, dense=True)
if args.dump_ply:
dump_to_ply(
vertices, tri,
'{}_{}.ply'.format(img_fp.replace(suffix, ''), ind))
if args.dump_vertex:
dump_vertex(
vertices, '{}_{}.mat'.format(img_fp.replace(suffix, ''),
ind))
ind += 1
draw_landmarks(img_ori,
pts_res,
wfp=img_fp.replace(suffix, '_3DDFA.jpg'),
show_flg=args.show_flg)
def draw_landmarks():
filelists = 'test.data/AFLW2000-3D_crop.list'
root = 'AFLW-2000-3D/'
fns = open(filelists).read().strip().split('\n')
params = _load('res/params_aflw2000.npy')
for i in range(2000):
plt.close()
img_fp = osp.join(root, fns[i])
img = io.imread(img_fp)
lms = reconstruct_vertex(params[i], dense=False)
lms = convert_to_ori(lms, i)
# print(lms.shape)
fig = plt.figure(figsize=plt.figaspect(.5))
# fig = plt.figure(figsize=(8, 4))
ax = fig.add_subplot(1, 2, 1)
ax.imshow(img)
alpha = 0.8
markersize = 4
lw = 1.5
color = 'w'
markeredgecolor = 'black'
nums = [0, 17, 22, 27, 31, 36, 42, 48, 60, 68]
for ind in range(len(nums) - 1):
l, r = nums[ind], nums[ind + 1]
ax.plot(lms[0, l:r],
lms[1, l:r],
color=color,
lw=lw,
alpha=alpha - 0.1)
ax.plot(lms[0, l:r],
lms[1, l:r],
marker='o',
linestyle='None',
markersize=markersize,
color=color,
markeredgecolor=markeredgecolor,
alpha=alpha)
ax.axis('off')
# 3D
ax = fig.add_subplot(1, 2, 2, projection='3d')
lms[1] = img.shape[1] - lms[1]
lms[2] = -lms[2]
# print(lms)
ax.scatter(lms[0], lms[2], lms[1], c="cyan", alpha=1.0, edgecolor='b')
for ind in range(len(nums) - 1):
l, r = nums[ind], nums[ind + 1]
ax.plot3D(lms[0, l:r], lms[2, l:r], lms[1, l:r], color='blue')
ax.view_init(elev=5., azim=-95)
# ax.set_xlabel('x')
# ax.set_ylabel('y')
# ax.set_zlabel('z')
ax.set_xticklabels([])
ax.set_yticklabels([])
ax.set_zticklabels([])
plt.tight_layout()
# plt.show()
wfp = f'res/AFLW-2000-3D/{osp.basename(img_fp)}'
plt.savefig(wfp, dpi=200)