问题
I'm facing this error when running my code with 3 lstm layers. Not sure how to fix it. Can anyone help. Here MAX_SEQUENCE_LENGTH=250. After running the cost function, i get the error 'ValueError: Shapes (?, 1) and (?,) are incompatible'
# Generate a Tensorflow Graph
tf.reset_default_graph()
batch_size = 25
embedding_size = 50
lstmUnits = 64
max_label = 2
x = tf.placeholder(tf.int32, [None, MAX_SEQUENCE_LENGTH])
y = tf.placeholder(tf.int32, [None])
number_of_layers=3
# Embeddings to represent words
saved_embeddings = np.load('wordVectors.npy')
embeddings = tf.nn.embedding_lookup(saved_embeddings, x)
def lstm_cell():
return tf.contrib.rnn.BasicLSTMCell(lstmUnits,reuse=tf.get_variable_scope().reuse)
lstmCell = tf.contrib.rnn.MultiRNNCell([lstm_cell() for _ in range(number_of_layers)])
lstmCell = tf.contrib.rnn.DropoutWrapper(cell=lstmCell, output_keep_prob=0.75)
outputs, final_state = tf.nn.dynamic_rnn(lstmCell, embeddings, dtype=tf.float32)
predictions = tf.contrib.layers.fully_connected(outputs[:, -1], 1, activation_fn=tf.sigmoid)
cost = tf.losses.mean_squared_error(y, predictions)
ValueError: Shapes (?, 1) and (?,) are incompatible full error message as below.
---------------------------------------------------------------------------
ValueError Traceback (most recent call last)
<ipython-input-19-f261b46a6f62> in <module>()
1 # Try 3
----> 2 cost = tf.losses.mean_squared_error(y, predictions)
3 cost
4 #y.shape
5 #y.reshape[]
/home/lavared/anaconda3/lib/python3.5/site-packages/tensorflow/python/ops/losses/losses_impl.py in mean_squared_error(labels, predictions, weights, scope, loss_collection, reduction)
564 predictions = math_ops.to_float(predictions)
565 labels = math_ops.to_float(labels)
--> 566 predictions.get_shape().assert_is_compatible_with(labels.get_shape())
567 losses = math_ops.squared_difference(predictions, labels)
568 return compute_weighted_loss(
/home/lavared/anaconda3/lib/python3.5/site-packages/tensorflow/python/framework/tensor_shape.py in assert_is_compatible_with(self, other)
751 """
752 if not self.is_compatible_with(other):
--> 753 raise ValueError("Shapes %s and %s are incompatible" % (self, other))
754
755 def most_specific_compatible_shape(self, other):
ValueError: Shapes (?, 1) and (?,) are incompatible
回答1:
I know this question is a month-old.
I was facing this issue some days ago. It was a well-known bug even though they solved only for that specific case.
In your case, the only working solution I found is to modify:
y = tf.placeholder(tf.int32, [None])
in:
y = tf.placeholder(tf.int32, [None, 1])
来源:https://stackoverflow.com/questions/49703387/tensorflow-valueerror-shapes-1-and-are-incompatible