x = MaxPooling1D(pool_size=2048)(x)
x = Dense(512, activation='relu')(x)
x = BatchNormalization()(x)
x = Dense(256, activation='relu')(x)
x = BatchNormalization()(x)
x = Dense(9,
weights=[
np.zeros([256, 9]),
np.array([1, 0, 0, 0, 1, 0, 0, 0, 1]).astype(np.float32)
])(x)
input_T = Reshape((3, 3))(x)
# forward net
g = MatMul()([input_points, input_T])
g = Conv1D(64, 1, activation='relu')(g)
g = BatchNormalization()(g)
g = Conv1D(64, 1, activation='relu')(g)
g = BatchNormalization()(g)
# feature transform net
f = Conv1D(64, 1, activation='relu')(g)
f = BatchNormalization()(f)
f = Conv1D(128, 1, activation='relu')(f)
f = BatchNormalization()(f)
f = Conv1D(1024, 1, activation='relu')(f)
f = BatchNormalization()(f)
f = MaxPooling1D(pool_size=2048)(f)
f = Dense(512, activation='relu')(f)
f = BatchNormalization()(f)
x = BatchNormalization()(x)
x = MaxPooling1D(pool_size=2048)(x)
x = Dense(512, activation='relu')(x)
x = BatchNormalization()(x)
x = Dense(256, activation='relu')(x)
x = BatchNormalization()(x)
x = Dense(9,
weights=[
np.zeros([256, 9]),
np.array([1, 0, 0, 0, 1, 0, 0, 0, 1]).astype(np.float32)
])(x)
input_T = Reshape((3, 3))(x)
in_0 = MatMul()([input_points, input_T])
# forward net0
f_0 = Conv1D(64, 1, activation='relu')(in_0)
f_0 = BatchNormalization()(f_0)
f_0 = Conv1D(64, 1, activation='relu')(f_0)
c_0 = Conv1D(32, 1, activation='relu')(in_0)
c_0 = BatchNormalization()(c_0)
c_0 = Conv1D(32, 1, activation='relu')(c_0)
out_0 = GumbelSoftmax(1, hard=True)([f_0, c_0])
global_feature = MaxPooling1D(pool_size=2048)(c_0)
c = Dense(512, activation='relu')(global_feature)
c = BatchNormalization()(c)
c = Dropout(0.5)(c)
c = Dense(256, activation='relu')(c)
c = BatchNormalization()(c)
x = Conv1D(128, 1, activation='relu')(x) x = BatchNormalization()(x) x = Conv1D(1024, 1, activation='relu')(x) x = BatchNormalization()(x) x = MaxPooling1D(pool_size=2048)(x) x = Dense(512, activation='relu')(x) x = BatchNormalization()(x) x = Dense(256, activation='relu')(x) x = BatchNormalization()(x) x = Dense(9, weights=[np.zeros([256, 9]), np.array([1, 0, 0, 0, 1, 0, 0, 0, 1]).astype(np.float32)])(x) input_T = Reshape((3, 3))(x) # forward net g = MatMul()([input_points, input_T]) g = Conv1D(64, 1, activation='relu')(g) g = BatchNormalization()(g) g = Conv1D(64, 1, activation='relu')(g) g = BatchNormalization()(g) # feature transform net f = Conv1D(64, 1, activation='relu')(g) f = BatchNormalization()(f) f = Conv1D(128, 1, activation='relu')(f) f = BatchNormalization()(f) f = Conv1D(1024, 1, activation='relu')(f) f = BatchNormalization()(f) f = MaxPooling1D(pool_size=2048)(f) f = Dense(512, activation='relu')(f)
