python程序小练
"""
Demo of HMR.
Note that HMR requires the bounding box of the person in the image. The best performance is obtained
when max length of the person in the image is roughly 150px.
When only the image path is supplied, it assumes that the image is centered on a person whose length
is roughly 150px.
Alternatively, you can supply output of the openpose to figure out the bbox and the right scale fact
or.
Sample usage:
# On images on a tightly cropped image around the person
python -m demo --img_path data/im1963.jpg
python -m demo --img_path data/coco1.png
# On images, with openpose output
python -m demo --img_path data/random.jpg --json_path data/random_keypoints.json
"""
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
import math
import sys
from absl import flags
import numpy as np
import skimage.io as io
import tensorflow as tf
from src.util import renderer as vis_util
from src.util import image as img_util
from src.util import openpose as op_util
import src.config
from src.RunModel import RunModel
flags.DEFINE_string('img_path', 'data/im1963.jpg', 'Image to run')
flags.DEFINE_string(
'json_path', None,
'If specified, uses the openpose output to crop the image.')
def visualize(img, proc_param, joints, verts, cam):
"""
Renders the result in original image coordinate frame.
"""
cam_for_render, vert_shifted, joints_orig = vis_util.get_original(
proc_param, verts, cam, joints, img_size=img.shape[:2])
# Render results
skel_img = vis_util.draw_skeleton(img, joints_orig)
rend_img_overlay = renderer(
vert_shifted, cam=cam_for_render, img=img, do_alpha=True)
rend_img = renderer(
vert_shifted, cam=cam_for_render, img_size=img.shape[:2])
rend_img_vp1 = renderer.rotated(
vert_shifted, 60, cam=cam_for_render, img_size=img.shape[:2])
rend_img_vp2 = renderer.rotated(
vert_shifted, -60, cam=cam_for_render, img_size=img.shape[:2])
import matplotlib.pyplot as plt
# plt.ion()
plt.figure(1)
plt.clf()
plt.subplot(231)
plt.imshow(img)
plt.title('input')
plt.axis('off')
plt.subplot(232)
plt.imshow(skel_img)
plt.title('joint projection')
plt.axis('off')
plt.subplot(233)
plt.imshow(rend_img_overlay)
plt.title('3D Mesh overlay')
plt.axis('off')
plt.subplot(234)
plt.imshow(rend_img)
plt.title('3D mesh')
plt.axis('off')
plt.subplot(235)
plt.imshow(rend_img_vp1)
plt.title('diff vp')
plt.axis('off')
plt.subplot(236)
plt.imshow(rend_img_vp2)
plt.title('diff vp')
plt.axis('off')
plt.draw()
plt.show()
# import ipdb
# ipdb.set_trace()
def get_angle1(p1,p2,p3):
x1,y1,z1 = p1[0],p1[1],p1[2]
x2,y2,z2 = p2[0],p2[1],p2[2]
x3,y3,z3 = p3[0],p3[1],p3[2]
a=math.sqrt((x2-x3)**2+(y2-y3)**2+(z2-z3)**2)
b=math.sqrt((x1-x3)**2+(y1-y3)**2+(z1-z3)**2)
c=math.sqrt((x2-x1)**2+(y2-y1)**2+(z2-z1)**2)
if c*b==0:
cosA=1
else:
cosA=(a**2-c**2-b**2)/(-2*c*b)
if cosA < -1.0:
cosA=-1.0
elif cosA>1.0:
cosA=1.0
A=math.acos(cosA)
deg=math.degrees(A)
return deg
def preprocess_image(img_path, json_path=None):
img = io.imread(img_path)
if img.shape[2] == 4:
img = img[:, :, :3]
if json_path is None:
if np.max(img.shape[:2]) != config.img_size:
print('Resizing so the max image size is %d..' % config.img_size)
scale = (float(config.img_size) / np.max(img.shape[:2]))
else:
scale = 1.
center = np.round(np.array(img.shape[:2]) / 2).astype(int)
# image center in (x,y)
center = center[::-1]
else:
scale, center = op_util.get_bbox(json_path)
crop, proc_param = img_util.scale_and_crop(img, scale, center,
config.img_size)
# Normalize image to [-1, 1]
crop = 2 * ((crop / 255.) - 0.5)
return crop, proc_param, img
def main(img_path, json_path=None):
sess = tf.Session()
model = RunModel(config, sess=sess)
input_img, proc_param, img = preprocess_image(img_path, json_path)
# Add batch dimension: 1 x D x D x 3
input_img = np.expand_dims(input_img, 0)
# Theta is the 85D vector holding [camera, pose, shape]
# where camera is 3D [s, tx, ty]
# pose is 72D vector holding the rotation of 24 joints of SMPL in axis angle format
# shape is 10D shape coefficients of SMPL
joints, verts, cams, joints3d, theta = model.predict(
input_img, get_theta=True)
import matplotlib.pyplot as plt
from mpl_toolkits import mplot3d
ax = plt.axes(projection="3d")
xdata = joints3d[0][:,:1].reshape(1,19)[0]
ydata = joints3d[0][:,1:2].reshape(1,19)[0]
zdata = joints3d[0][:,2:3].reshape(1,19)[0]
#右抬臂角度
print(joints3d[0][2])
c1 = get_angle1(joints3d[0][12],joints3d[0][2],joints3d[0][13])
c2 = get_angle1(joints3d[0][12],joints3d[0][3],joints3d[0][13])
c3 = get_angle1(joints3d[0][8],joints3d[0][2],joints3d[0][7])
c4 = get_angle1(joints3d[0][9],joints3d[0][3],joints3d[0][10])
c5 = get_angle1(joints3d[0][7],joints3d[0][6],joints3d[0][8])
c6 = get_angle1(joints3d[0][10],joints3d[0][9],joints3d[0][11])
c7 = get_angle1(joints3d[0][2],joints3d[0][1],joints3d[0][3])
c8 = get_angle1(joints3d[0][3],joints3d[0][2],joints3d[0][4])
c9 = get_angle1(joints3d[0][1],joints3d[0][0],joints3d[0][2])
c10 = get_angle1(joints3d[0][4],joints3d[0][3],joints3d[0][5])
ax.scatter3D(xdata,ydata,zdata,cmap="Greens")
plt.show()
print(xdata)
print(ydata)
print(zdata)
print("2D坐标:",joints)
print("3D坐标:",joints3d)
print("cams",cams)
visualize(img, proc_param, joints[0], verts[0], cams[0])
if __name__ == '__main__':
config = flags.FLAGS
config(sys.argv)
# Using pre-trained model, change this to use your own.
config.load_path = src.config.PRETRAINED_MODEL
config.batch_size = 1
renderer = vis_util.SMPLRenderer(face_path=config.smpl_face_path)
main(config.img_path, config.json_path)
Demo of HMR.
Note that HMR requires the bounding box of the person in the image. The best performance is obtained
when max length of the person in the image is roughly 150px.
When only the image path is supplied, it assumes that the image is centered on a person whose length
is roughly 150px.
Alternatively, you can supply output of the openpose to figure out the bbox and the right scale fact
or.
Sample usage:
# On images on a tightly cropped image around the person
python -m demo --img_path data/im1963.jpg
python -m demo --img_path data/coco1.png
# On images, with openpose output
python -m demo --img_path data/random.jpg --json_path data/random_keypoints.json
"""
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
import math
import sys
from absl import flags
import numpy as np
import skimage.io as io
import tensorflow as tf
from src.util import renderer as vis_util
from src.util import image as img_util
from src.util import openpose as op_util
import src.config
from src.RunModel import RunModel
flags.DEFINE_string('img_path', 'data/im1963.jpg', 'Image to run')
flags.DEFINE_string(
'json_path', None,
'If specified, uses the openpose output to crop the image.')
def visualize(img, proc_param, joints, verts, cam):
"""
Renders the result in original image coordinate frame.
"""
cam_for_render, vert_shifted, joints_orig = vis_util.get_original(
proc_param, verts, cam, joints, img_size=img.shape[:2])
# Render results
skel_img = vis_util.draw_skeleton(img, joints_orig)
rend_img_overlay = renderer(
vert_shifted, cam=cam_for_render, img=img, do_alpha=True)
rend_img = renderer(
vert_shifted, cam=cam_for_render, img_size=img.shape[:2])
rend_img_vp1 = renderer.rotated(
vert_shifted, 60, cam=cam_for_render, img_size=img.shape[:2])
rend_img_vp2 = renderer.rotated(
vert_shifted, -60, cam=cam_for_render, img_size=img.shape[:2])
import matplotlib.pyplot as plt
# plt.ion()
plt.figure(1)
plt.clf()
plt.subplot(231)
plt.imshow(img)
plt.title('input')
plt.axis('off')
plt.subplot(232)
plt.imshow(skel_img)
plt.title('joint projection')
plt.axis('off')
plt.subplot(233)
plt.imshow(rend_img_overlay)
plt.title('3D Mesh overlay')
plt.axis('off')
plt.subplot(234)
plt.imshow(rend_img)
plt.title('3D mesh')
plt.axis('off')
plt.subplot(235)
plt.imshow(rend_img_vp1)
plt.title('diff vp')
plt.axis('off')
plt.subplot(236)
plt.imshow(rend_img_vp2)
plt.title('diff vp')
plt.axis('off')
plt.draw()
plt.show()
# import ipdb
# ipdb.set_trace()
def get_angle1(p1,p2,p3):
x1,y1,z1 = p1[0],p1[1],p1[2]
x2,y2,z2 = p2[0],p2[1],p2[2]
x3,y3,z3 = p3[0],p3[1],p3[2]
a=math.sqrt((x2-x3)**2+(y2-y3)**2+(z2-z3)**2)
b=math.sqrt((x1-x3)**2+(y1-y3)**2+(z1-z3)**2)
c=math.sqrt((x2-x1)**2+(y2-y1)**2+(z2-z1)**2)
if c*b==0:
cosA=1
else:
cosA=(a**2-c**2-b**2)/(-2*c*b)
if cosA < -1.0:
cosA=-1.0
elif cosA>1.0:
cosA=1.0
A=math.acos(cosA)
deg=math.degrees(A)
return deg
def preprocess_image(img_path, json_path=None):
img = io.imread(img_path)
if img.shape[2] == 4:
img = img[:, :, :3]
if json_path is None:
if np.max(img.shape[:2]) != config.img_size:
print('Resizing so the max image size is %d..' % config.img_size)
scale = (float(config.img_size) / np.max(img.shape[:2]))
else:
scale = 1.
center = np.round(np.array(img.shape[:2]) / 2).astype(int)
# image center in (x,y)
center = center[::-1]
else:
scale, center = op_util.get_bbox(json_path)
crop, proc_param = img_util.scale_and_crop(img, scale, center,
config.img_size)
# Normalize image to [-1, 1]
crop = 2 * ((crop / 255.) - 0.5)
return crop, proc_param, img
def main(img_path, json_path=None):
sess = tf.Session()
model = RunModel(config, sess=sess)
input_img, proc_param, img = preprocess_image(img_path, json_path)
# Add batch dimension: 1 x D x D x 3
input_img = np.expand_dims(input_img, 0)
# Theta is the 85D vector holding [camera, pose, shape]
# where camera is 3D [s, tx, ty]
# pose is 72D vector holding the rotation of 24 joints of SMPL in axis angle format
# shape is 10D shape coefficients of SMPL
joints, verts, cams, joints3d, theta = model.predict(
input_img, get_theta=True)
import matplotlib.pyplot as plt
from mpl_toolkits import mplot3d
ax = plt.axes(projection="3d")
xdata = joints3d[0][:,:1].reshape(1,19)[0]
ydata = joints3d[0][:,1:2].reshape(1,19)[0]
zdata = joints3d[0][:,2:3].reshape(1,19)[0]
#右抬臂角度
print(joints3d[0][2])
c1 = get_angle1(joints3d[0][12],joints3d[0][2],joints3d[0][13])
c2 = get_angle1(joints3d[0][12],joints3d[0][3],joints3d[0][13])
c3 = get_angle1(joints3d[0][8],joints3d[0][2],joints3d[0][7])
c4 = get_angle1(joints3d[0][9],joints3d[0][3],joints3d[0][10])
c5 = get_angle1(joints3d[0][7],joints3d[0][6],joints3d[0][8])
c6 = get_angle1(joints3d[0][10],joints3d[0][9],joints3d[0][11])
c7 = get_angle1(joints3d[0][2],joints3d[0][1],joints3d[0][3])
c8 = get_angle1(joints3d[0][3],joints3d[0][2],joints3d[0][4])
c9 = get_angle1(joints3d[0][1],joints3d[0][0],joints3d[0][2])
c10 = get_angle1(joints3d[0][4],joints3d[0][3],joints3d[0][5])
ax.scatter3D(xdata,ydata,zdata,cmap="Greens")
plt.show()
print(xdata)
print(ydata)
print(zdata)
print("2D坐标:",joints)
print("3D坐标:",joints3d)
print("cams",cams)
visualize(img, proc_param, joints[0], verts[0], cams[0])
if __name__ == '__main__':
config = flags.FLAGS
config(sys.argv)
# Using pre-trained model, change this to use your own.
config.load_path = src.config.PRETRAINED_MODEL
config.batch_size = 1
renderer = vis_util.SMPLRenderer(face_path=config.smpl_face_path)
main(config.img_path, config.json_path)
Last one:世界末日·周杰伦
Next one:《瓦尔登湖》经典语句
声明:以上文章均为用户自行添加,仅供打字交流使用,不代表本站观点,本站不承担任何法律责任,特此声明!如果有侵犯到您的权利,请及时联系我们删除。
Hot degree:★★★☆☆
Difficulty:★★★★☆
quality:☆☆☆☆☆
Description: the system according to the heat, the difficulty, the quality of automatic certification, the certification of the article will be involved in typing!
This paper typing ranking TOP20
登录后可见