Ricky Han

Given the current implementation of recuurentshop. This would be an undertaking if not outright impossible. Look elsewhere

1. You will need to convert to one hot encoded vector then use an embedding layer. 2. Variable length input can be solved by bucketing.

I have figured it out: ``` enc_cells_fw = [] for i in range(0, encoder_depth): with tf.variable_scope('enc_RNN_{}'.format(i)): cell = tf.contrib.rnn.LSTMCell(hidden_dim) # Or LSTMCell(hidden_dim) cell = tf.contrib.rnn.DropoutWrapper(cell, output_keep_prob=1.0-dropout) enc_cells_fw.append(cell) enc_cell_fw = tf.contrib.rnn.MultiRNNCell(enc_cells_fw,...

Same here. Please remove me from the mailing list please. On Wed, Mar 5, 2025 at 10:46 Chioke Aarhus ***@***.***> wrote: > Can confirm I was also set to get...