Python Deep Learning Projects

Defining our LSTM model

Again, most of the code will remain same—the only the major change will be to use tf.nn.rnn_cell.LSTMCell(), instead of tf.nn.rnn_cell.BasicRNNCell(). While initializing the LSTM cell, we are using an orthogonal initializer that will generate a random orthogonal matrix, which is an effective way of combating exploding and vanishing gradients:

class Model:    def __init__(self, size_layer, num_layers, embedded_size,                 dict_size, dimension_output, learning_rate):                def cells(reuse=False):            return tf.nn.rnn_cell.LSTMCell(size_layer,initializer=tf.orthogonal_initializer(),reuse=reuse)                self.X = tf.placeholder(tf.int32, [None, None])        self.Y = tf.placeholder(tf.float32, [None, dimension_output]) encoder_embeddings = tf.Variable(tf.random_uniform([dict_size, ...