Open normanheckscher opened 7 years ago
Need to refactor with state_is_tuple=True for TF 0.11?
cell = cell_fn(args.rnn_size, state_is_tuple=True) self.cell = cell = rnn_cell.MultiRNNCell([cell] * args.num_layers, state_is_tuple=True)
feed = {model.input_data: x, model.targets: y} for i, (c, h) in enumerate(model.initial_state): feed[c] = state[I].c feed[h] = state[I].h
https://github.com/sherjilozair/char-rnn-tensorflow/commit/991704e68632b57c1591651ce8183e5a374ca44a
Need to refactor with state_is_tuple=True for TF 0.11?
https://github.com/sherjilozair/char-rnn-tensorflow/commit/991704e68632b57c1591651ce8183e5a374ca44a