model1 = np.zeros((10, 16, 16), dtype=np.float)
model2 = np.zeros((10, 16, 16, 16), dtype=np.float)
model3 = np.zeros((10, 16, 16, 16, 16), dtype=np.float)
for i in range(10):
rule1 = np.zeros((16, 16), dtype=np.float)
rule2 = np.zeros((16, 16, 16), dtype=np.float)
rule3 = np.zeros((16, 16, 16, 16), dtype=np.float)
idxes = check_data(i, training_size)
size = len(idxes)
d = prep_training_data(idxes)
for img in d:
btb = BTB(2, img)
btb.perception()
rule1 = rule1 + btb.lvl1
rule2 = rule2 + btb.lvl2
rule3 = rule3 + btb.lvl3
rule1 = rule1 / size
rule2 = rule2 / size
rule3 = rule3 / size
model1[i, :, :] = rule1
model2[i, :, :, :] = rule2
model3[i, :, :, :, :] = rule3
"""
for i in range(10):
print(i)
for j in range(10):
model1 = np.zeros((10, 16, 16), dtype=np.float)
model2 = np.zeros((10, 16, 16, 16), dtype=np.float)
model3 = np.zeros((10, 16, 16, 16, 16), dtype=np.float)
for i in range(10):
rule1 = np.zeros((16, 16), dtype=np.float)
rule2 = np.zeros((16, 16, 16), dtype=np.float)
rule3 = np.zeros((16, 16, 16, 16), dtype=np.float)
idxes = check_data(i, training_size)
size = len(idxes)
d = prep_training_data(idxes)
for img in d:
btb = BTB(2, img)
btb.perception()
rule1 = rule1 + btb.lvl1
rule2 = rule2 + btb.lvl2
rule3 = rule3 + btb.lvl3
rule1 = rule1 / size
rule2 = rule2 / size
rule3 = rule3 / size
model1[i, :, :] = rule1
model2[i, :, :, :] = rule2
model3[i, :, :, :, :] = rule3
"""
for i in range(10):
print(i)
for j in range(10):
