Tensorflow 稀疏张量问题

Question

我试图运行以下 TensorFlow 代码。它包括稀疏矩阵，但似乎不起作用。我修改了 tensorflow 文档（链接）中给出的示例。我正在使用 tensorflow 1.12.0 版。

代码：

import tensorflow as tf

import numpy as np

x = tf.sparse.placeholder(shape=[-1,8,8], dtype=np.float32)

x_reshaped = tf.sparse.reshape(x, shape=[-1,64],name='flow_sizes_reshaped')

layer = tf.Variable(initial_value=tf.random_normal(shape=[64, 32],stddev=.05), name='hidden_layer_0', dtype=np.float32)

x_final = tf.sparse.matmul(x_reshaped, layer)

with tf.Session() as sess:

  indices = np.array([[0, 2, 0], [0, 5, 1]], dtype=np.int64)

  values = np.array([1.0, 2.0], dtype=np.float32)

  shape = np.array([1, 8, 8], dtype=np.int64)

  print(sess.run(x_final, feed_dict={

    x: (indices, values, shape)}))

错误：

2018-12-11 13:24:39.039224: I tensorflow/core/platform/cpu_feature_guard.cc:141] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA

Traceback (most recent call last):

  File "Test_Sparse.py", line 15, in <module>

    x: (indices, values, shape)}))

  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.py", line 929, in run

    run_metadata_ptr)

  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.py", line 1132, in _run

    raise ValueError('Tensor %s may not be fed.' % subfeed_t)

ValueError: Tensor Tensor("Const:0", shape=(3,), dtype=int64) may not be fed.

我不认为这是一个尺寸不匹配问题，因为如果我在代码中进行这个更改：

indices = np.array([[2, 0], [5, 1]], dtype=np.int64)

我收到以下错误：

2018-12-11 13:30:01.538664: I tensorflow/core/platform/cpu_feature_guard.cc:141] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA

Traceback (most recent call last):

  File "Test_Sparse.py", line 15, in <module>

    x: (indices, values, shape)}))

我试过做很多事情，但我最终每次都会遇到这个问题。我现在正在考虑转到 TF 源代码并检查为什么会引发此错误。