def __init__(self,
config,
latent_code_garms_sz=1024,
garmparams_sz=config.PCA_,
name=None):
super(PoseShapeOffsetModel, self).__init__(name=name)
self.config = config
self.latent_code_garms_sz = latent_code_garms_sz
self.garmparams_sz = garmparams_sz
self.latent_code_betas_sz = 128
# ToDo: Minor: Remove hard coded colors. Should be same as rendered colors in input
self.colormap = tf.cast([
np.array([255, 255, 255]),
np.array([65, 0, 65]),
np.array([0, 65, 65]),
np.array([145, 65, 0]),
np.array([145, 0, 65]),
np.array([0, 145, 65])
], tf.float32) / 255.
with open('assets/hresMapping.pkl', 'rb') as f:
_, self.faces = pkl.load(f, encoding="latin1")
self.faces = np.int32(self.faces)
# Define network layers
self.top_ = SingleImageNet(self.latent_code_garms_sz,
self.latent_code_betas_sz)
for n in self.config.garmentKeys:
gn = GarmentNet(self.config.PCA_, n, self.garmparams_sz)
self.garmentModels.append(gn)
self.smpl = SMPL('assets/neutral_smpl.pkl',
theta_in_rodrigues=False,
theta_is_perfect_rotmtx=False,
isHres=True,
scale=True)
self.smpl_J = SmplBody25Layer(theta_in_rodrigues=False,
theta_is_perfect_rotmtx=False,
isHres=True)
self.J_layers = [NameLayer('J_{}'.format(i)) for i in range(NUM)]
self.lat_betas = Dense(self.latent_code_betas_sz,
kernel_initializer=initializers.RandomNormal(
0, 0.00005),
activation='relu')
self.betas = Dense(10,
kernel_initializer=initializers.RandomNormal(
0, 0.000005),
name='betas')
init_trans = np.array([0, 0.2, -2.])
init_pose = np.load('assets/mean_a_pose.npy')
init_pose[:3] = 0
init_pose = tf.reshape(
batch_rodrigues(init_pose.reshape(-1, 3).astype(np.float32)),
(-1, ))
self.pose_trans = tf.concat((init_pose, init_trans), axis=0)
self.lat_pose = Dense(self.latent_code_betas_sz,
kernel_initializer=initializers.RandomNormal(
0, 0.000005),
activation='relu')
self.lat_pose_layer = Dense(
24 * 3 * 3 + 3,
kernel_initializer=initializers.RandomNormal(0, 0.000005),
name='pose_trans')
self.cut_trans = Lambda(lambda z: z[:, -3:])
self.trans_layers = [
NameLayer('trans_{}'.format(i)) for i in range(NUM)
]
self.cut_poses = Lambda(lambda z: z[:, :-3])
self.reshape_pose = Reshape((24, 3, 3))
self.pose_layers = [NameLayer('pose_{}'.format(i)) for i in range(NUM)]
# Optional: Condition garment on betas, probably not
self.latent_code_offset_ShapeMerged = Dense(self.latent_code_garms_sz +
self.latent_code_betas_sz,
activation='relu')
self.latent_code_offset_ShapeMerged_2 = Dense(
self.latent_code_garms_sz + self.latent_code_betas_sz,
activation='relu',
name='latent_code_offset_ShapeMerged')
self.avg = Average()
self.flatten = Flatten()
self.concat = Concatenate()
self.scatters = []
for vs in self.vertSpread:
self.scatters.append(Scatter_(vs, self.config.NVERTS))
import os
import pickle
import numpy as np
import torch
from block_timer.timer import Timer
from smpl.batch_smpl import SMPL
with open('../mpi/data/mano/MANO_RIGHT_py3.pkl', 'rb') as f:
mano_data = pickle.load(f, encoding='latin1')
mano = SMPL(mano_data).cuda() # not good
def get_mano_vertices(shape, pose, device=torch.device('cpu')):
"""
:param shape: mano shape params [batch_size, 10]
:param pose: mano pose params including global rotation (joint axis-angle representation) [batch_size, 45+3]
:return:
"""
# check if not tensor: wrap
if not isinstance(shape, torch.Tensor):
shape = torch.tensor(shape, dtype=torch.float).cuda()
if not isinstance(pose, torch.Tensor):
pose = torch.tensor(pose, dtype=torch.float).cuda()
verts, joints, Rs = mano(shape, pose, get_skin=True)
return verts.cpu().detach().numpy()