def main():
obs1 = srk.Observation(np.loadtxt("data000.txt"))
obs2 = srk.Observation(np.loadtxt("data001.txt"))
obs3 = srk.Observation(np.loadtxt("data002.txt"))
obs4 = srk.Observation(np.loadtxt("data003.txt"))
obs5 = srk.Observation(np.loadtxt("data004.txt"))
category = np.loadtxt("data_category.txt")
mlda1 = mlda.MLDA(10, [100], category=category)
mlda2 = mlda.MLDA(10, [100, 100], category=category)
mlda3 = mlda.MLDA(10, [100, 100], category=category)
mlda4 = mlda.MLDA(10, [100, 100], category=category)
mlda5 = mlda.MLDA(10, [100, 100], category=category)
mlda1.connect(obs1)
mlda2.connect(mlda1, obs2)
mlda3.connect(mlda2, obs3)
mlda4.connect(mlda3, obs4)
mlda5.connect(mlda4, obs5)
for it in range(5):
mlda1.update()
mlda2.update()
mlda3.update()
mlda4.update()
mlda5.update()
def main():
obs1 = srk.Observation(np.loadtxt("data1.txt"))
obs2 = srk.Observation(np.loadtxt("data2.txt"))
category = np.loadtxt("category.txt")
vae1 = vae_model(10, epoch=200, batch_size=500)
gmm1 = gmm.GMM(10, category=category)
nn1 = NN_model(itr1=500, itr2=2000, batch_size1=500, batch_size2=500)
vae1.connect(obs1)
gmm1.connect(vae1)
nn1.connect(gmm1, obs2)
for i in range(10):
print(i)
vae1.update()
gmm1.update()
nn1.update()
def main():
obs1 = srk.Observation(np.loadtxt("data1.txt"))
obs2 = srk.Observation(np.loadtxt("data2.txt"))
data_category = np.loadtxt("category.txt")
vae1 = vae_model(18, epoch=200, batch_size=500)
gmm1 = gmm.GMM(10, category=data_category)
mlda1 = mlda.MLDA(10, [200, 200], category=data_category)
vae1.connect(obs1)
gmm1.connect(vae1)
mlda1.connect(obs2, gmm1)
for i in range(5):
print(i)
vae1.update()
gmm1.update()
mlda1.update()
def main():
obs1 = srk.Observation(np.loadtxt("dsift.txt")) # 視覚
obs2 = srk.Observation(np.loadtxt("mfcc.txt")) # 聴覚
obs3 = srk.Observation(np.loadtxt("tactile.txt")) # 触覚
obs4 = srk.Observation(np.loadtxt("angle.txt")) # 関節角
object_category = np.loadtxt("object_category.txt")
motion_category = np.loadtxt("motion_category.txt")
mlda1 = mlda.MLDA(10, [200, 200, 200], category=object_category)
mlda2 = mlda.MLDA(10, [200], category=motion_category)
mlda3 = mlda.MLDA(10, [100, 100])
mlda1.connect(obs1, obs2, obs3)
mlda2.connect(obs4)
mlda3.connect(mlda1, mlda2)
for it in range(5):
print(it)
mlda1.update()
mlda2.update()
mlda3.update()
def main():
obs = srk.Observation(np.loadtxt("data.txt"))
data_category = np.loadtxt("category.txt")
vae1 = vae_model(18, epoch=200, batch_size=500)
gmm1 = gmm.GMM(10, category=data_category)
vae1.connect(obs)
gmm1.connect(vae1)
for i in range(5):
print(i)
vae1.update()
gmm1.update()
def main():
obs1 = CNN.CNNFeatureExtractor( ["images/%03d.png"%i for i in range(6)] )
obs2 = srk.Observation( np.loadtxt("histogram_w.txt") )
mlda1 = mlda.MLDA(3, [1000])
mlda2 = mlda.MLDA(3, [50])
mlda3 = mlda.MLDA(3, [50,50])
mlda1.connect( obs1 )
mlda2.connect( obs2 )
mlda3.connect( mlda1, mlda2 )
for it in range(5):
mlda1.update()
mlda2.update()
mlda3.update()
def main():
obs = srk.Observation(np.loadtxt("data.txt"))
data_category = np.loadtxt("category.txt")
vae1 = vae.VAE(18, itr=200, batch_size=500)
gmm1 = gmm.GMM(10, category=data_category)
mm1 = mm.MarkovModel()
vae1.connect(obs)
gmm1.connect(vae1)
mm1.connect(gmm1)
for i in range(5):
print(i)
vae1.update()
gmm1.update()
mm1.update()
def main():
obs = srk.Observation(np.loadtxt("data.txt"))
correct_classes = np.loadtxt("correct.txt")
# GMM単体
g = gmm.GMM(4, category=correct_classes)
g.connect(obs)
g.update()
# GMMとマルコフモデルを結合したモデル
g = gmm.GMM(4, category=correct_classes)
m = mm.MarkovModel()
g.connect(obs)
m.connect(g)
for itr in range(5):
g.update()
m.update()
