batchsize = 1
window = X.shape[2]
X = theano.shared(X, borrow=True)
network = create_core(batchsize=batchsize, window=window, dropout=0.0, depooler=lambda x,**kw: x/2)
network.load(np.load('network_core.npz'))
from AnimationPlot import animation_plot
for _ in range(10):
index = rng.randint(X.shape[0].eval())
Xorgi = np.array(X[index:index+1].eval())
Xnois = Xorgi.copy()
Xnois[:,16*3-1:17*3] = 0.0
Xrecn = np.array(network(Xnois).eval())
Xorgi = (Xorgi * preprocess['Xstd']) + preprocess['Xmean']
Xnois = (Xnois * preprocess['Xstd']) + preprocess['Xmean']
Xrecn = (Xrecn * preprocess['Xstd']) + preprocess['Xmean']
Xrecn = constrain(Xrecn, network[0], network[1], preprocess, multiconstraint(
foot_sliding(Xorgi[:,-4:].copy()),
joint_lengths(),
trajectory(Xorgi[:,-7:-4])), alpha=0.01, iterations=50)
Xrecn[:,-7:-4] = Xorgi[:,-7:-4]
animation_plot([Xnois, Xrecn, Xorgi], interval=15.15)
dtype=theano.config.floatX) * preprocess['Xstd']) + preprocess['Xmean']
def style_transfer(H, V):
s, c = style_amount, 1.0
s, c = s / (s + c), c / (s + c)
return s * T.mean((gram_matrix(H) - G)**2) + c * T.mean((H - network_C[0](C))**2)
Xstyl = (S * preprocess['Xstd']) + preprocess['Xmean']
Xcntn = (C * preprocess['Xstd']) + preprocess['Xmean']
Xtrsf = N
Xtrsf = constrain(Xtrsf, network_C[0], network_C[1], preprocess, style_transfer, iterations=250, alpha=0.01)
Xtrsfvel = np.mean(np.sqrt(Xtrsf[:,-7:-6]**2 + Xtrsf[:,-6:-5]**2), axis=2)[:,:,np.newaxis]
Xcntnvel = np.mean(np.sqrt(Xcntn[:,-7:-6]**2 + Xcntn[:,-6:-5]**2), axis=2)[:,:,np.newaxis]
Xtail = Xtrsfvel * (Xcntn[:,-7:] / Xcntnvel)
Xtail[:,-5:] = Xcntn[:,-5:]
Xtrsf = constrain(Xtrsf, network_C[0], network_C[1], preprocess, multiconstraint(
foot_sliding(Xtail[:,-4:]),
joint_lengths(),
trajectory(Xtail[:,:3])), alpha=0.01, iterations=100)
Xtrsf[:,-7:] = Xtail
Xstyl = np.concatenate([Xstyl, Xstyl], axis=2)
from AnimationPlot import animation_plot
animation_plot([Xstyl, Xcntn, Xtrsf], interval=15.15)
# 2021
# 13283
for _ in range(10):
index = rng.randint(X.shape[0].eval())
print(index)
Xorgi = np.array(X[index:index + 1].eval())
Xnois = ((Xorgi * rng.binomial(size=Xorgi.shape, n=1, p=0.5)) /
0.5).astype(theano.config.floatX)
Xrecn = np.array(network(Xnois).eval())
Xorgi = (Xorgi * preprocess['Xstd']) + preprocess['Xmean']
Xnois = (Xnois * preprocess['Xstd']) + preprocess['Xmean']
Xrecn = (Xrecn * preprocess['Xstd']) + preprocess['Xmean']
Xrecn = constrain(Xrecn,
network[0],
network[1],
preprocess,
multiconstraint(foot_sliding(Xorgi[:, -4:].copy()),
joint_lengths(),
trajectory(Xorgi[:, -7:-4])),
alpha=0.01,
iterations=50)
Xrecn[:, -7:-4] = Xorgi[:, -7:-4]
animation_plot([Xnois, Xrecn, Xorgi], interval=15.15)
network_first, network_second, network = create_network(
batchsize=T.shape[0], window=T.shape[2], hidden=T.shape[1])
network_func = theano.function([input],
network(input),
allow_input_downcast=True)
start = time.clock()
X = network_func(T)
X = (X * preprocess['Xstd']) + preprocess['Xmean']
Xtail = (T * preprocess['Xstd'][:, -7:]) + preprocess['Xmean'][:, -7:]
X = constrain(X,
network_second[0],
network_second[1],
preprocess,
multiconstraint(foot_sliding(Xtail[:, -4:]), joint_lengths(),
trajectory(Xtail[:, :3])),
alpha=0.01,
iterations=10)
X[:, -7:] = Xtail
#############
animation_plot([X[0:1, :, :200], X[10:11, :, :200], X[20:21, :, :200]],
interval=15.15)
X = np.swapaxes(X, 1, 2)
joints = X[:, :, :-7].reshape((X.shape[0], X.shape[1], -1, 3))
joints = -Quaternions(
data[scene + '_rot'][:, cstart:cend])[:, :, np.newaxis] * joints
joints[:, :, :,
#Y shape:(1,12,240)
network_func = theano.function([], network(Y[i:i + 1]))
Y_pad_ori = np.array(Y_pad[i:i + 1])
Xorig = np.array(X[i:i + 1])
print('X shape: ', X.shape)
#X shape: 121,73,240
print('Xorig shape: ', Xorig.shape)
#Xorig shape : 1,73,240
start = time.clock()
print('before network_func')
Xrecn = network_func()
# meaning that Y is inserted into network function then output will be Xrecn
print('Xrecn shape: ', Xrecn.shape)
#Xrecn shape: (1,73,240)
Xorig = (Xorig * preprocess['Xstd']) + preprocess['Xmean']
Xrecn = (Xrecn * preprocess['Xstd']) + preprocess['Xmean']
Y_pad_ori = (Y_pad_ori * preprocess['Xstd']) + preprocess['Xmean']
print
print('before constrain')
#here Xrecn already same as Xorig, but next is add constraint
Xrecn = constrain(Xrecn,
network_second[0],
network_second[1],
preprocess,
multiconstraint(foot_sliding(Xrecn[:, -4:].copy()),
joint_lengths()),
alpha=0.01,
iterations=50)
#print(data_kicking_cmu[i])
animation_plot([Xorig], interval=15.15)
feet = np.array([9,10,11,12,13,14,21,22,23,24,25,26])
Y = X[:,feet]
batchsize = 1
window = X.shape[2]
network_first = create_regressor(batchsize=batchsize, window=window, input=Y.shape[1], dropout=0.0)
network_second = create_core(batchsize=batchsize, window=window, dropout=0.0, depooler=lambda x,**kw:x/2)
network_second.load(np.load('network_core.npz'))
network = Network(network_first, network_second[1], params=network_first.params)
network.load(np.load('network_regression_kick.npz'))
from AnimationPlot import animation_plot
for i in range(len(X)):
network_func = theano.function([], network(Y[i:i+1]))
Xorig = np.array(X[i:i+1])
start = time.clock()
Xrecn = network_func()
Xorig = (Xorig * preprocess['Xstd']) + preprocess['Xmean']
Xrecn = (Xrecn * preprocess['Xstd']) + preprocess['Xmean']
Xrecn = constrain(Xrecn, network_second[0], network_second[1], preprocess, multiconstraint(
foot_sliding(Xrecn[:,-4:].copy()),
joint_lengths()), alpha=0.01, iterations=50)
animation_plot([Xorig, Xrecn], interval=15.15)
Xnois = np.concatenate([Xnois_Torso[:,0:3,:], Xnois_Leftleg, Xnois_Rightleg, Xnois_Torso[:,3:15,:], Xnois_Leftarm, Xnois_Rightarm, Xorgi[:,63:73,:]],axis=1)
print(Xnois.shape)
Xrecn = np.concatenate([Xrecn_Torso[:,0:3,:], Xrecn_Leftleg, Xrecn_Rightleg, Xrecn_Torso[:,3:15,:], Xrecn_Leftarm, Xrecn_Rightarm, Xorgi[:,63:73,:]], axis=1)
Xorgi = (Xorgi * preprocess['Xstd']) + preprocess['Xmean']
Xnois = (Xnois * preprocess['Xstd']) + preprocess['Xmean']
Xrecn = (Xrecn * preprocess['Xstd']) + preprocess['Xmean']
np.save("./denoise/Xorgi.npy",Xorgi)
np.save("./denoise/Xnois.npy",Xnois)
print(Xorgi[:,-7:-4].shape)
# H'=argmin[Pos(H)+Bone(H)+Traj(H)]
Xrecn = constrain(Xrecn, network[0], network[1], preprocess, multiconstraint(
foot_sliding(Xorgi[:,-4:].copy()),#foot sliding information(-4,-3,-2,-1)
joint_lengths(),
trajectory(Xorgi[:,-7:-4])), alpha=0.01, iterations=50)#input trajectory(-7,-6,-5)
Xrecn[:,-7:-4] = Xorgi[:,-7:-4]
np.save("./denoise/Xrecn.npy",Xrecn)
print("construction done")
animation_plot([Xnois, Xrecn, Xorgi], interval=15.15)
"""
Xnois = ((Xorgi * rng.binomial(size=Xorgi.shape, n=1, p=0.5)) / 0.5).astype(theano.config.floatX)
#Xnois = (Xorgi + 0.05*np.random.randn(1,73,240)+0.1).astype(theano.config.floatX)
Xrecn = np.array(network(Xnois).eval())
#print(Xrecn.shape)
"""
