我正在尝试遵循word2vec示例，但是出现此错误：
TypeError: Input 'b' of 'MatMul' Op has type float32 that does not match type int32 of argument 'a'.
在这一行
相似性 = tf.matmul( tf.cast(valid_embeddings，tf.int32(， tf.cast(normalized_embeddings，tf.int32(， transpose_b=True(
这是整个代码：
graph = tf.Graph()
with graph.as_default():
# Input data.
train_inputs = tf.placeholder(tf.int32, shape=[batch_size])
train_labels = tf.placeholder(tf.int32, shape=[batch_size, 1])
valid_dataset = tf.constant(valid_examples, dtype=tf.int32)
# Ops and variables pinned to the CPU because of missing GPU implementation
with tf.device('/cpu:0'):
# Look up embeddings for inputs.
embeddings = tf.Variable(
tf.random_uniform([vocabulary_size, embedding_size], -1.0, 1.0))
embed = tf.nn.embedding_lookup(embeddings, train_inputs)
# Construct the variables for the NCE loss
nce_weights = tf.Variable(
tf.truncated_normal([vocabulary_size, embedding_size],
stddev=1.0 / math.sqrt(embedding_size)))
nce_biases = tf.Variable(tf.zeros([vocabulary_size]))
# Compute the average NCE loss for the batch.
# tf.nce_loss automatically draws a new sample of the negative labels each
# time we evaluate the loss.
loss = tf.reduce_mean(
tf.nn.nce_loss(nce_weights, nce_biases, embed, train_labels,
num_sampled, vocabulary_size))
# Construct the SGD optimizer using a learning rate of 1.0.
optimizer = tf.train.GradientDescentOptimizer(1.0).minimize(loss)
# Compute the cosine similarity between minibatch examples and all embeddings.
norm = tf.sqrt(tf.reduce_sum(tf.square(embeddings), 1, keep_dims=True))
normalized_embeddings = embeddings / norm
valid_embeddings = tf.nn.embedding_lookup(
normalized_embeddings, valid_dataset)
similarity = tf.matmul(
tf.cast(valid_embeddings,tf.int32), tf.cast(normalized_embeddings,tf.int32), transpose_b=True)
# Add variable initializer.
init = tf.initialize_all_variables()
我该如何解决这个问题？
我在使用 Python 3.4 的 Tensorflow r1.4 时遇到了同样的问题。
确实，我认为您需要更改代码
tf.nn.nce_loss(nce_weights, nce_biases, embed, train_labels,
num_sampled, vocabulary_size))
到
tf.nn.nce_loss(nce_weights, nce_biases, train_labels, embed,
num_sampled, vocabulary_size))
或
loss = tf.reduce_mean(tf.nn.nce_loss(
weights = softmax_weights,
biases = softmax_biases,
inputs = embed,
labels = train_labels,
num_sampled = num_sampled,
num_classes = vocabulary_size))
同时，您需要将代码改回
similarity = tf.matmul(valid_embeddings, tf.transpose(normalized_embeddings))
使用tf.cast(..., tf.int32)是错误的，实际上，没有必要使用tf.cast(..., tf.float32)因为它已经是tf.float32。
附言
当您在使用tf.nn.sampled_softmax_loss()时遇到问题时，该解决方案也很有用，因为sampled_softmax_loss()的用法与nce_loss()非常相似。
为什么要在整数空间中进行矩阵乘法？您可能希望这两个tf.cast都指向tf.float32。