Tensorflow:ValueError:形状必须为2级但为3级 [英] Tensorflow : ValueError: Shape must be rank 2 but is rank 3
问题描述
我是tensorflow的新手,我正在尝试将双向LSTM的一些代码从tensorflow的旧版本更新为最新版本(1.0),但出现此错误:
I'm new to tensorflow and I'm trying to update some code for a bidirectional LSTM from an old version of tensorflow to the newest (1.0), but I get this error:
对于"MatMul_3"(操作:"MatMul"),形状必须为2级,但其排名为3级,输入形状为[100,?,400],[400,2].
Shape must be rank 2 but is rank 3 for 'MatMul_3' (op: 'MatMul') with input shapes: [100,?,400], [400,2].
该错误发生在pred_mod上.
The error happens on pred_mod.
_weights = {
# Hidden layer weights => 2*n_hidden because of foward + backward cells
'w_emb' : tf.Variable(0.2 * tf.random_uniform([max_features,FLAGS.embedding_dim], minval=-1.0, maxval=1.0, dtype=tf.float32),name='w_emb',trainable=False),
'c_emb' : tf.Variable(0.2 * tf.random_uniform([3,FLAGS.embedding_dim],minval=-1.0, maxval=1.0, dtype=tf.float32),name='c_emb',trainable=True),
't_emb' : tf.Variable(0.2 * tf.random_uniform([tag_voc_size,FLAGS.embedding_dim], minval=-1.0, maxval=1.0, dtype=tf.float32),name='t_emb',trainable=False),
'hidden_w': tf.Variable(tf.random_normal([FLAGS.embedding_dim, 2*FLAGS.num_hidden])),
'hidden_c': tf.Variable(tf.random_normal([FLAGS.embedding_dim, 2*FLAGS.num_hidden])),
'hidden_t': tf.Variable(tf.random_normal([FLAGS.embedding_dim, 2*FLAGS.num_hidden])),
'out_w': tf.Variable(tf.random_normal([2*FLAGS.num_hidden, FLAGS.num_classes]))}
_biases = {
'hidden_b': tf.Variable(tf.random_normal([2*FLAGS.num_hidden])),
'out_b': tf.Variable(tf.random_normal([FLAGS.num_classes]))}
#~ input PlaceHolders
seq_len = tf.placeholder(tf.int64,name="input_lr")
_W = tf.placeholder(tf.int32,name="input_w")
_C = tf.placeholder(tf.int32,name="input_c")
_T = tf.placeholder(tf.int32,name="input_t")
mask = tf.placeholder("float",name="input_mask")
# Tensorflow LSTM cell requires 2x n_hidden length (state & cell)
istate_fw = tf.placeholder("float", shape=[None, 2*FLAGS.num_hidden])
istate_bw = tf.placeholder("float", shape=[None, 2*FLAGS.num_hidden])
_Y = tf.placeholder("float", [None, FLAGS.num_classes])
#~ transfortm into Embeddings
emb_x = tf.nn.embedding_lookup(_weights['w_emb'],_W)
emb_c = tf.nn.embedding_lookup(_weights['c_emb'],_C)
emb_t = tf.nn.embedding_lookup(_weights['t_emb'],_T)
_X = tf.matmul(emb_x, _weights['hidden_w']) + tf.matmul(emb_c, _weights['hidden_c']) + tf.matmul(emb_t, _weights['hidden_t']) + _biases['hidden_b']
inputs = tf.split(_X, FLAGS.max_sent_length, axis=0, num=None, name='split')
lstmcell = tf.contrib.rnn.BasicLSTMCell(FLAGS.num_hidden, forget_bias=1.0,
state_is_tuple=False)
bilstm = tf.contrib.rnn.static_bidirectional_rnn(lstmcell, lstmcell, inputs,
sequence_length=seq_len, initial_state_fw=istate_fw, initial_state_bw=istate_bw)
pred_mod = [tf.matmul(item, _weights['out_w']) + _biases['out_b'] for item in bilstm]
任何帮助表示赞赏.
推荐答案
对于以后遇到此问题的任何人,都不应使用上方的摘录.
For anyone encountering this issue in the future, the snippet above should not be used.
来自 tf.contrib.rnn.static_bidirectional_rnn
v1.1文档:
From tf.contrib.rnn.static_bidirectional_rnn
v1.1 documentation:
返回:
元组(outputs, output_state_fw, output_state_bw)
其中:输出是输出的长度T列表(每个输入一个),它们是深度连接的前向和后向输出. output_state_fw是前向rnn的最终状态. output_state_bw是向后rnn的最终状态.
A tuple (outputs, output_state_fw, output_state_bw)
where: outputs is a length T list of outputs (one for each input), which are depth-concatenated forward and backward outputs. output_state_fw is the final state of the forward rnn. output_state_bw is the final state of the backward rnn.
上面的列表理解是期望LSTM输出,而获得这些输出的正确方法是:
The list comprehension above is expecting LSTM outputs, and the correct way to get those is this:
outputs, _, _ = tf.contrib.rnn.static_bidirectional_rnn(lstmcell, lstmcell, ...)
pred_mod = [tf.matmul(item, _weights['out_w']) + _biases['out_b']
for item in outputs]
这将起作用,因为outputs
中的每个item
都具有形状[batch_size, 2 * num_hidden]
,并且可以将权重乘以tf.matmul()
.
This will work, because each item
in outputs
has the shape [batch_size, 2 * num_hidden]
and can be multiplied with the weights by tf.matmul()
.
附加组件:从tensorflow v1.2 +起,推荐使用的功能在另一个软件包中: tf.nn.static_bidirectional_rnn
.返回的张量相同,因此代码变化不大:
Add-on: from tensorflow v1.2+, the recommended function to use is in another package: tf.nn.static_bidirectional_rnn
. The returned tensors are the same, so the code doesn't change much:
outputs, _, _ = tf.nn.static_bidirectional_rnn(lstmcell, lstmcell, ...)
pred_mod = [tf.matmul(item, _weights['out_w']) + _biases['out_b']
for item in outputs]
这篇关于Tensorflow:ValueError:形状必须为2级但为3级的文章就介绍到这了,希望我们推荐的答案对大家有所帮助,也希望大家多多支持IT屋!