TypeError: Input 'b' of 'MatMul' Op has type float32 that does not match type int32 of argument 'a'.

tensorflow 

word embedding

代码：

loss = tf.reduce_mean(  tf.nn.nce_loss(nce_weights, nce_biases, embed, train_labels,                 num_sampled, vocabulary_size))

报错：

TypeError: Input 'b' of 'MatMul' Op has type float32 that does not match type int32 of argument 'a'.

解决办法：

loss = tf.reduce_mean(
        tf.nn.nce_loss(nce_weights, nce_biases, train_labels,embed,
                 num_sampled, vocabulary_size))