Question

RNN定义如下：

def RNN(X, weights_rnn, biases,n_inputs,n_steps,n_hidden_units,batch_size=None):
    # hidden layer for input to cell
    ########################################

    X = tf.reshape(X, [-1, n_inputs])

    # into hidden
    # X_in = (128 batch * 28 steps, 128 hidden)
    X_in = tf.matmul(X, weights_rnn['in']) + biases_rnn['in']

    # X_in ==> (128 batch, 28 steps, 128 hidden)
    X_in = tf.reshape(X_in, [-1, n_steps, n_hidden_units])

    # cell
    ##########################################

    # basic LSTM Cell.
    # if int((tf.__version__).split('.')[1]) < 12 and int((tf.__version__).split('.')[0]) < 1:
        # cell = tf.nn.rnn_cell.BasicLSTMCell(n_hidden_units, forget_bias=1.0, state_is_tuple=True)
    # else:
        # cell = tf.contrib.rnn.BasicLSTMCell(n_hidden_units)


    cell = tf.contrib.rnn.MultiRNNCell([attn_cell() for _ in range(1)], state_is_tuple=True)

    # lstm cell is divided into two parts (c_state, h_state)

    init_state = cell.zero_state(batch_size, dtype=tf.float32)


    # tf.nn.dynamic_rnn(cell, inputs).
    # unpack to list [(batch, outputs)..] * steps

    if int((tf.__version__).split('.')[1]) < 12 and int((tf.__version__).split('.')[0]) < 1:
        outputs = tf.unpack(tf.transpose(outputs, [1, 0, 2]))    # states is the last outputs
    else:
        outputs = tf.unstack(tf.transpose(outputs, [1,0,2]))

    results = tf.matmul(outputs[-1], weights_rnn['out']) + biases_rnn['out']    # shape = (128, 10)

    return results

以下是我调用函数RNN的方法。

x_rnn = tf.placeholder(tf.float32, [None, n_steps, n_inputs])
n_inputs =52
n_steps = 10    # time steps
n_hidden_units = 100   # neurons in hidden layer
n_classes = 22

weights_rnn = {
    'in': tf.Variable(tf.random_normal([n_inputs, n_hidden_units])),
    'out': tf.Variable(tf.random_normal([n_hidden_units, n_classes]))
}

biases_rnn = {
    'in': tf.Variable(tf.constant(0.1, shape=[n_hidden_units, ])),
    'out': tf.Variable(tf.constant(0.1, shape=[n_classes, ]))
}

y_rnn = RNN(x_rnn, weights_rnn, biases_rnn,n_inputs,n_steps,n_hidden_units,batch_size=x_rnn.shape[0])

使用张量来初始化带有张量而不是标量的batch_size是错误。

line 430, in RNN
init_state = cell.zero_state(batch_size, dtype=tf.float32)
ValueError: Provided a prefix or suffix of None: ? and 100

任何人都有这个想法吗？

Answer 1

我认为你需要获得x_rnn的动态形状而不是静态形状。您可以将x_rnn.shape[0]替换为tf.shape(x_rnn)[0]

TensorFlow RNN：如何用张量初始化RNN？

1 个答案: