The final line:
output = slim.fully_connected(
last_layer,
num_outputs,
weights_initializer=normc_initializer(0.01),
activation_fn=None,
scope="fc_out")
embeds the inputs into num_outputs, but the last hidden_dim should actually go into the LSTM, not into this final hidden layer
The final line: output = slim.fully_connected( last_layer, num_outputs, weights_initializer=normc_initializer(0.01), activation_fn=None, scope="fc_out") embeds the inputs into num_outputs, but the last hidden_dim should actually go into the LSTM, not into this final hidden layer