Question

目前我有以下代码：

init_state = tf.Variable(tf.zeros([batch_partition_length, state_size]))    # -> [16, 1024].
final_state = tf.Variable(tf.zeros([batch_partition_length, state_size]))

And inside my inference method that is responsible producing the output, I have the following:

def inference(frames):
    # Note that I write the final_state as a global valriable to avoid the shadowing issue, since it is referenced at the dynamic_rnn line. 
    global final_state
    # ....  Here we have some conv layers and so on... 

    # Now the RNN cell
    with tf.variable_scope('local1') as scope:

        # Move everything into depth so we can perform a single matrix multiply.
        shape_d = pool3.get_shape()
        shape = shape_d[1] * shape_d[2] * shape_d[3]
        # tf_shape = tf.stack(shape)
        tf_shape = 1024

        print("shape:", shape, shape_d[1], shape_d[2], shape_d[3])

        # So note that tf_shape = 1024, this means that we have 1024 features are fed into the network. And
        # the batch size = 1024. Therefore, the aim is to divide the batch_size into num_steps so that
        reshape = tf.reshape(pool3, [-1, tf_shape])
        # Now we need to reshape/divide the batch_size into num_steps so that we would be feeding a sequence
        rnn_inputs = tf.reshape(reshape, [batch_partition_length, step_size, tf_shape])

        print('RNN inputs shape: ', rnn_inputs.get_shape()) # -> (16, 64, 1024).

        cell = tf.contrib.rnn.BasicRNNCell(state_size)
        # note that rnn_outputs are the outputs but not multiplied by W.
        rnn_outputs, final_state = tf.nn.dynamic_rnn(cell, rnn_inputs, initial_state=init_state)

    # linear Wx + b
    with tf.variable_scope('softmax_linear') as scope:
        weight_softmax = \
            tf.Variable(
                tf.truncated_normal([state_size, n_classes], stddev=1 / state_size, dtype=tf.float32, name='weight_softmax'))
        bias_softmax = tf.constant(0.0, tf.float32, [n_classes], name='bias_softmax')

        softmax_linear = tf.reshape(
            tf.matmul(tf.reshape(rnn_outputs, [-1, state_size]), weight_softmax) + bias_softmax,
            [batch_size, n_classes])

        print('Output shape:', softmax_linear.get_shape())

    return softmax_linear

# Here we define the loss, accuracy and the optimzer. 
# now run the graph:

with tf.Session() as sess:
    _, accuracy_train, loss_train, summary = \
            sess.run([optimizer, accuracy, cost_scalar, merged], feed_dict={x: image_batch,
                                                                            y_valence: valences,
                                                                            confidence_holder: confidences})

    ....

问题：我如何能够为initial_state分配存储在final_state中的值？也就是说，如何更多地更新给定的另一个变量值？

我使用了以下内容：

tf.assign(init_state, final_state.eval())

运行sess.run命令后，在会话中

。但是，这是一个错误：您必须为占位符张量输入＆＃39;提供一个值。与dtype浮动其中tf.Variable：＆＃34;输入＆＃34;声明如下：

x = tf.placeholder(tf.float32, [None, 112, 112, 3], name='inputs')

通过以下命令从tfRecords读取图像后完成进纸：

example = tf.train.Example()
example.ParseFromString(string_record)

height = int(example.features.feature['height']
             .int64_list
             .value[0])

width = int(example.features.feature['width']
            .int64_list
            .value[0])

img_string = (example.features.feature['image_raw']
              .bytes_list
              .value[0])

img_1d = np.fromstring(img_string, dtype=np.uint8)
reconstructed_img = img_1d.reshape((height, width, -1)) # Where this is added to the image_batch list, which is fed into the placeholder.

如果尝试以下内容：

img_1d = np.fromstring(img_string, dtype=np.float32)

这将产生以下错误：

ValueError：无法将9408大小的数组重塑为形状（112,112，newaxis）

非常感谢任何帮助!!

Answer 1

所以这是我到目前为止所犯的错误。做了一些修改后，我想出了以下内容：

我不应该将final_state创建为tf.Variable。由于tf.nn.dynamic_rnn将张量作为ndarray返回，因此，我不应该在开头实例化final_state int。我不应该在函数定义下使用全局final_state。
为了将初始状态指定为final_state，我使用了：
```
tf.assign(intial_state, final_state)
```

事情顺利进行。注意：在tensorflow中，一个操作在python中将数据返回为numpy数组，在C和C ++中返回tensorflow :: Tensor。

请查看https://www.tensorflow.org/versions/r0.10/get_started/basic_usage以获取更多信息。

在张量流中更新递归神经网络的初始状态

1 个答案: