def param_recon_3d_vertex(param_path,
reference_img_names_list,
method='',
dense=True):
# load 62d param
param_62d = _load(param_path)
# reconstruct 3d face shape, include pose information, and save 3d vertex info
benchmark_3d_vertex_save(param_62d,
reference_img_names_list,
method,
dense=True)
def gen_3d_vertex(filelists, params_path,
save_path): # dense 3d face rather than 68 keypoints
fns = open(filelists).read().strip().split('\n')
params = _load(params_path) #jia zai 2000 ge yang ben de 3d data
for i in range(2000):
fn = fns[i]
vertex = reconstruct_vertex(params[i], dense=True) #dense 3d face
wfp = osp.join(save_path, fn.replace('.jpg', '.mat'))
print(wfp)
sio.savemat(wfp, {'vertex': 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 load_bfm(model_path):
suffix = _get_suffix(model_path)
if suffix == 'mat':
C = sio.loadmat(model_path)
model = C['model_refine']
model = model[0, 0]
model_new = {}
w_shp = model['w'].astype(np.float32)
model_new['w_shp_sim'] = w_shp[:, :40]
w_exp = model['w_exp'].astype(np.float32)
model_new['w_exp_sim'] = w_exp[:, :10]
u_shp = model['mu_shape']
u_exp = model['mu_exp']
u = (u_shp + u_exp).astype(np.float32)
model_new['mu'] = u
model_new['tri'] = model['tri'].astype(np.int32) - 1
# flatten it, pay attention to index value
keypoints = model['keypoints'].astype(np.int32) - 1
keypoints = np.concatenate(
(3 * keypoints, 3 * keypoints + 1, 3 * keypoints + 2), axis=0)
model_new['keypoints'] = keypoints.T.flatten()
#
w = np.concatenate((w_shp, w_exp), axis=1)
w_base = w[keypoints]
w_norm = np.linalg.norm(w, axis=0)
w_base_norm = np.linalg.norm(w_base, axis=0)
dim = w_shp.shape[0] // 3
u_base = u[keypoints].reshape(-1, 1)
w_shp_base = w_shp[keypoints]
w_exp_base = w_exp[keypoints]
model_new['w_norm'] = w_norm
model_new['w_base_norm'] = w_base_norm
model_new['dim'] = dim
model_new['u_base'] = u_base
model_new['w_shp_base'] = w_shp_base
model_new['w_exp_base'] = w_exp_base
_dump(model_path.replace('.mat', '.pkl'), model_new)
return model_new
else:
return _load(model_path)
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 _load_gpu(fp):
return torch.from_numpy(_load(fp)).cuda()
def _load_tensor(fp, mode='cpu'):
if mode.lower() == 'cpu':
return torch.from_numpy(_load(fp))
elif mode.lower() == 'gpu':
return torch.from_numpy(_load(fp)).cuda()
#!/usr/bin/env python3
# coding: utf-8
import os.path as osp
import numpy as np
from io_utils import _load, _numpy_to_cuda, _numpy_to_tensor, _load_gpu
def make_abs_path(d):
return osp.join(osp.dirname(osp.realpath(__file__)), d)
d = make_abs_path('train.configs')
keypoints = _load(osp.join(d, 'keypoints_sim.npy'))
w_shp = _load(osp.join(d, 'w_shp_sim.npy'))
w_exp = _load(osp.join(d, 'w_exp_sim.npy')) # simplified version
meta = _load(osp.join(d, 'param_whitening.pkl'))
param_mean = meta.get('param_mean')
param_std = meta.get('param_std')
u_shp = _load(osp.join(d, 'u_shp.npy'))
u_exp = _load(osp.join(d, 'u_exp.npy'))
u = u_shp + u_exp
w = np.concatenate((w_shp, w_exp), axis=1)
w_base = w[keypoints]
w_norm = np.linalg.norm(w, axis=0)
w_base_norm = np.linalg.norm(w_base, axis=0)
# for test
dim = w_shp.shape[0] // 3
u_base = u[keypoints].reshape(-1, 1)
#from benchmark_aflw1998 import ana as ana_alfw1998
from benchmark_aflw import calc_nme as calc_nme_alfw
from benchmark_aflw import ana as ana_aflw
from resnet_xgtu_4chls import resnet50
from ddfa_utils2 import ToTensorGjz, NormalizeGjz, DDFATestDataset, reconstruct_vertex
import argparse
from io_utils import _load, _numpy_to_cuda, _numpy_to_tensor
import os.path as osp
import numpy as np
from math import sqrt
from io_utils import _load
d = 'test.configs'
fail_detect = [1082 - 1, 1799 - 1]
yaws_list = _load(osp.join(d, 'AFLW2000-3D.pose.npy'))
yaws_list = [
yaws_list[idx] for idx in range(len(yaws_list)) if idx not in fail_detect
]
# pts21 = _load(osp.join(d, 'AFLW2000-3D.pts21.npy'))
# origin
pts68_all_ori = _load(osp.join(d, 'AFLW2000-3D.pts68.npy'))
pts68_all_ori = [
pts68_all_ori[idx] for idx in range(len(pts68_all_ori))
if idx not in fail_detect
]
# reannonated
pts68_all_re = _load(osp.join(d, 'AFLW2000-3D-Reannotated.pts68.npy'))
pts68_all_re = [
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)
#!/usr/bin/env python3
# coding: utf-8
import os
import os.path as osp
import numpy as np
import sys
from glob import glob
from math import sqrt
from io_utils import _load
d = 'test.configs'
yaw_list = _load(osp.join(d, 'AFLW_GT_crop_yaws.npy'))
roi_boxs = _load(osp.join(d, 'AFLW_GT_crop_roi_box.npy'))
pts68_all = _load(osp.join(d, 'AFLW_GT_pts68.npy'))
pts21_all = _load(osp.join(d, 'AFLW_GT_pts21.npy'))
def ana(nme_list):
yaw_list_abs = np.abs(yaw_list)
ind_yaw_1 = yaw_list_abs <= 30
ind_yaw_2 = np.bitwise_and(yaw_list_abs > 30, yaw_list_abs <= 60)
ind_yaw_3 = yaw_list_abs > 60
nme_1 = nme_list[ind_yaw_1]
nme_2 = nme_list[ind_yaw_2]
nme_3 = nme_list[ind_yaw_3]
mean_nme_1 = np.mean(nme_1) * 100
mean_nme_2 = np.mean(nme_2) * 100
mean_nme_3 = np.mean(nme_3) * 100