python - Tensorflow:使用 sparse_placeholder 恢复模型

Question

我需要保存和恢复使用 sparse_placeholder 的模型，但是我收到一条错误消息:KeyError:“名称‘w1:0’指的是一个不存在的张量。运算‘w1’在图中不存在。”

这里有一个简单的方法来重现我在需要恢复包含 sparse_tensor 的模型时遇到的错误:

import tensorflow as tf
import numpy as np


def train_sparse():
    w1 = tf.sparse_placeholder(tf.float64, shape=None, name="w1")
    b1 = tf.Variable(np.ones((2, 2)) * 1.0, name="bias")
    operation = tf.sparse_tensor_dense_matmul(w1, b1, name="op1")

    with tf.Session() as sess:
        sess.run(tf.global_variables_initializer())
        saver = tf.train.Saver()
        w1_value = tf.SparseTensorValue([[1, 1]], [5], [2, 2])
        print sess.run(operation, {w1: w1_value})
        saver.save(sess, 'my_test_model')


def test_sparse():
    with tf.Session() as sess:
        saver = tf.train.import_meta_graph('my_test_model.meta')
        saver.restore(sess, tf.train.latest_checkpoint('./'))
        print(sess.run('bias:0'))
        graph = tf.get_default_graph()
        op_to_restore = graph.get_tensor_by_name("op1/SparseTensorDenseMatMul:0")
        w1 = graph.get_tensor_by_name("w1:0")
        w1_value = tf.SparseTensorValue([[1, 1]], [5], [2, 2])

        print sess.run(op_to_restore, {w1: w1_value})

if __name__ == "__main__":
    train_sparse()
    test_sparse()

这里我们可以看到一个类似的图，其中使用了正态张量:

import tensorflow as tf
import numpy as np

def train():
    w1 = tf.placeholder(tf.float64, shape=None, name="w1")
    b1 = tf.Variable(np.ones((2, 2)) * 1.0, name="bias")
    operation = tf.matmul(w1, b1, name="op1")

    with tf.Session() as sess:
        sess.run(tf.global_variables_initializer())
        saver = tf.train.Saver()
        w1_value = [[0, 0], [0, 5]]
        print sess.run(operation, {w1: w1_value})
        saver.save(sess, 'my_test_model')


def test():
    with tf.Session() as sess:
        saver = tf.train.import_meta_graph('my_test_model.meta')
        saver.restore(sess, tf.train.latest_checkpoint('./'))
        print(sess.run('bias:0'))
        graph = tf.get_default_graph()
        op_to_restore = graph.get_tensor_by_name("op1:0")
        w1 = graph.get_tensor_by_name("w1:0")
        w1_value = [[0, 0], [0, 5]]

        print sess.run(op_to_restore, {w1: w1_value})


if __name__ == "__main__":
    train()
    test()

有没有人知道如何修复它？

作为解决方法，我可以将数据作为普通张量传递，并在图中更改为 sparse_tensor。但是，它需要进行不必要的转换。

Answer 1

Tensorflow 单独保存稀疏占位符的索引、值和形状。它相应地为它们添加后缀，因此名为 w1 的 SparsePlaceholder 变成了 3 个名为 w1/indices、w1/values 和 w1/shape< 的占位符 在保存的图表中。

我稍微修改了你的例子，让它变得更清晰:

import tensorflow as tf
import numpy as np


def train_sparse():
    w1 = tf.sparse_placeholder(tf.float64, shape=None, name="w1")
    b1 = tf.Variable(np.ones((2, 2)) * 1.0, name="bias")
    operation = tf.sparse_tensor_dense_matmul(w1, b1, name="op1")

    with tf.Session() as sess:
        sess.run(tf.global_variables_initializer())
        saver = tf.train.Saver()
        w1_value = tf.SparseTensorValue([[1, 1]], [5], [2, 2])
        print sess.run(operation, {w1: w1_value})
        saver.save(sess, 'my_test_model')

def test_sparse():
    with tf.Session() as sess:
        saver = tf.train.import_meta_graph('my_test_model.meta')
        saver.restore(sess, tf.train.latest_checkpoint('./'))
        print(sess.run('bias:0'))
        graph = tf.get_default_graph()
        op_to_restore = graph.get_tensor_by_name("op1/SparseTensorDenseMatMul:0")

        # NEW PART 

        w1_indices = graph.get_tensor_by_name("w1/indices:0")
        w1_indices_value = [[1,1]]

        w1_size = graph.get_tensor_by_name("w1/indices:0")
        w1_size_value = [5]

        w1_values = graph.get_tensor_by_name("w1/values:0")
        w1_values_value = [5]

        w1_shape = graph.get_tensor_by_name("w1/shape:0")
        w1_shape_value = [2,2]

        print sess.run(op_to_restore, {w1_indices: w1_indices_value,
                                       w1_values: w1_values_value,
                                       w1_shape: w1_shape_value})

if __name__ == "__main__":
    train_sparse()
    test_sparse()