我想尝试使用编码器和注意解码器替换此github code（即dcrnn_model.py第83行中）中编码和解码器的内容。
这些是编码器-解码器之前的代码：
max_diffusion_step = int(model_kwargs.get('max_diffusion_step', 2))
cl_decay_steps = int(model_kwargs.get('cl_decay_steps', 1000))
filter_type = model_kwargs.get('filter_type', 'laplacian')
horizon = int(model_kwargs.get('horizon', 1))
max_grad_norm = float(model_kwargs.get('max_grad_norm', 5.0))
num_nodes = int(model_kwargs.get('num_nodes', 1))
num_rnn_layers = int(model_kwargs.get('num_rnn_layers', 1))
rnn_units = int(model_kwargs.get('rnn_units'))
seq_len = int(model_kwargs.get('seq_len'))
use_curriculum_learning = bool(model_kwargs.get('use_curriculum_learning', False))
input_dim = int(model_kwargs.get('input_dim', 1))
output_dim = int(model_kwargs.get('output_dim', 1))
aux_dim = input_dim - output_dim
# Input (batch_size, timesteps, num_sensor, input_dim)
self._inputs = tf.placeholder(tf.float32, shape=(batch_size, seq_len, num_nodes, input_dim), name='inputs')
# Labels: (batch_size, timesteps, num_sensor, input_dim), same format with input except the temporal dimension.
self._labels = tf.placeholder(tf.float32, shape=(batch_size, horizon, num_nodes, input_dim), name='labels')
# GO_SYMBOL = tf.zeros(shape=(batch_size, num_nodes * input_dim))
GO_SYMBOL = tf.zeros(shape=(batch_size, num_nodes * output_dim))
cell = DCGRUCell(rnn_units, adj_mx, max_diffusion_step=max_diffusion_step, num_nodes=num_nodes,
filter_type=filter_type)
cell_with_projection = DCGRUCell(rnn_units, adj_mx, max_diffusion_step=max_diffusion_step, num_nodes=num_nodes,
num_proj=output_dim, filter_type=filter_type)
encoding_cells = [cell] * num_rnn_layers
decoding_cells = [cell] * (num_rnn_layers - 1) + [cell_with_projection]
encoding_cells = tf.contrib.rnn.MultiRNNCell(encoding_cells, state_is_tuple=True)
decoding_cells = tf.contrib.rnn.MultiRNNCell(decoding_cells, state_is_tuple=True)
global_step = tf.train.get_or_create_global_step()
# Outputs: (batch_size, timesteps, num_nodes, output_dim)
with tf.variable_scope('DCRNN_SEQ'):
inputs = tf.unstack(tf.reshape(self._inputs, (batch_size, seq_len, num_nodes * input_dim)), axis=1)
labels = tf.unstack(
tf.reshape(self._labels[..., :output_dim], (batch_size, horizon, num_nodes * output_dim)), axis=1)
if aux_dim > 0:
aux_info = tf.unstack(self._labels[..., output_dim:], axis=1)
aux_info.insert(0, None)
labels.insert(0, GO_SYMBOL)
def _loop_function(prev, i):
if is_training:
# Return either the model's prediction or the previous ground truth in training.
if use_curriculum_learning:
c = tf.random_uniform((), minval=0, maxval=1.)
threshold = self._compute_sampling_threshold(global_step, cl_decay_steps)
result = tf.cond(tf.less(c, threshold), lambda: labels[i], lambda: prev)
else:
result = labels[i]
else:
# Return the prediction of the model in testing.
result = prev
if False and aux_dim > 0:
result = tf.reshape(result, (batch_size, num_nodes, output_dim))
result = tf.concat([result, aux_info[i]], axis=-1)
result = tf.reshape(result, (batch_size, num_nodes * input_dim))
return result
这是编码器-解码器的原始代码：
#DCRNN-encoder-decoder
_, enc_state = tf.contrib.rnn.static_rnn(encoding_cells, inputs, dtype=tf.float32)#encoder
outputs, final_state = legacy_seq2seq.rnn_decoder(labels, enc_state, decoding_cells,
loop_function=_loop_function)#decoder
我的代码如下：
# Encoder and Attention_decoder
encoder_outputs, enc_state = tf.contrib.rnn.static_rnn(encoding_cells, inputs, dtype=tf.float32)#encoder
# First calculate a concatenation of encoder outputs to put attention on.
top_states = [tf.reshape(encoder_outputs,[-1, 1, decoding_cells.output_size])]
attention_states = tf.concat(top_states,1)
outputs, final_state = legacy_seq2seq.attention_decoder(labels, enc_state,attention_states, decoding_cells,loop_function=_loop_function)#attention_decoder
但是，发生了这样的尺寸错误：
值错误：尺寸必须相等，但对于输入形状为[49152,1,1,207]的“火车/ DCRNN / DCRNN_SEQ / attention_decoder / Attention_0 / add”（op：“ Add”），尺寸必须为49152和64 ，[64,1,1,207]。