model.py 文件源码

def get_train_model():
    # Has size [batch_size, max_stepsize, num_features], but the
    # batch_size and max_stepsize can vary along each step
    # features = convolutional_layers()
    # print features.get_shape()
    inputs = tf.placeholder(tf.float32, [None, None, common.OUTPUT_SHAPE[0]])

    # Here we use sparse_placeholder that will generate a
    # SparseTensor required by ctc_loss op.
    targets = tf.sparse_placeholder(tf.int32)

    # 1d array of size [batch_size]
    seq_len = tf.placeholder(tf.int32, [None])

    # Defining the cell
    # Can be:
    #   tf.nn.rnn_cell.RNNCell
    #   tf.nn.rnn_cell.GRUCell
    cell = tf.contrib.rnn.core_rnn_cell.LSTMCell(common.num_hidden, state_is_tuple=True)

    # Stacking rnn cells
    stack = tf.contrib.rnn.core_rnn_cell.MultiRNNCell([cell] * common.num_layers,
                                                      state_is_tuple=True)

    # The second output is the last state and we will no use that
    outputs, _ = tf.nn.dynamic_rnn(cell, inputs, seq_len, dtype=tf.float32)

    shape = tf.shape(inputs)
    batch_s, max_timesteps = shape[0], shape[1]

    # Reshaping to apply the same weights over the timesteps
    outputs = tf.reshape(outputs, [-1, common.num_hidden])

    # Truncated normal with mean 0 and stdev=0.1
    # Tip: Try another initialization
    # see https://www.tensorflow.org/versions/r0.9/api_docs/python/contrib.layers.html#initializers
    W = tf.Variable(tf.truncated_normal([common.num_hidden,
                                         common.num_classes],
                                        stddev=0.1), name="W")
    # Zero initialization
    # Tip: Is tf.zeros_initializer the same?
    b = tf.Variable(tf.constant(0., shape=[common.num_classes]), name="b")

    # Doing the affine projection
    logits = tf.matmul(outputs, W) + b

    # Reshaping back to the original shape
    logits = tf.reshape(logits, [batch_s, -1, common.num_classes])

    # Time major
    logits = tf.transpose(logits, (1, 0, 2))

    return logits, inputs, targets, seq_len, W, b