python 3.x - La entrada no es invertible.

git clone https github com tensorflow tensorflow git

Question

Estoy tratando de implementar el Modelo de Mezcla Gaussiana usando tf.learn (skflow) de Tensorflow, pero recibo el siguiente error.

from tensorflow.contrib.factorization.python.ops import gmm as gmm_lib
import random
import numpy as np
x = np.array([[random.random() for i in range(198)] for j in range(2384)], dtype=np.float32)
gmm = gmm_lib.GMM(128,random_seed=0)
gmm.fit(x)

Error StackTrace: -

InvalidArgumentError (see above for traceback): Input is not invertible.
[[Node: MatrixInverse_2 = MatrixInverse[T=DT_FLOAT, adjoint=false, _device="/job:localhost/replica:0/task:0/cpu:0"](add_138)]]