Python 类型错误:输入';b';属于';马特穆尔';Op的float32类型与参数';a';
我试图遵循word2vec示例,但我遇到了以下错误:Python 类型错误:输入';b';属于';马特穆尔';Op的float32类型与参数';a';,python,python-2.7,tensorflow,Python,Python 2.7,Tensorflow,我试图遵循word2vec示例,但我遇到了以下错误: TypeError: Input 'b' of 'MatMul' Op has type float32 that does not match type int32 of argument 'a'. 在这条线上 相似性=tf.matmul( tf.cast(有效的_嵌入,tf.int32),tf.cast(规范化的_嵌入,tf.int32),transpose_b=True) 这是全部代码: graph = tf.Graph() wit
TypeError: Input 'b' of 'MatMul' Op has type float32 that does not match type int32 of argument 'a'.
在这条线上
相似性=tf.matmul(
tf.cast(有效的_嵌入,tf.int32),tf.cast(规范化的_嵌入,tf.int32),transpose_b=True)
这是全部代码:
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()
我如何解决这个问题?为什么要在整数空间中进行矩阵乘法?您可能希望将这两个tf.cast都转换为tf.float32。我在使用Tensorflow r1.4和Python 3.4时遇到了相同的问题 事实上,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))
进入
或
同时,您需要将代码更改回
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了
p、 美国
当您在使用tf.nn.sampled\u softmax\u loss()
时遇到问题时,该解决方案也很有用,因为sampled\u softmax\u loss()
的用法与nce\u loss()
非常类似
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))
similarity = tf.matmul(valid_embeddings, tf.transpose(normalized_embeddings))