BUG: chapter 6
zhan4402 opened this issue · 1 comments
zhan4402 commented
loss = tf.reduce_mean(
tf.nn.nce_loss(nce_weights, nce_biases, embed, train_labels,
negative_samples, vocabulary_size))
This line returns the following error.
ValueError: Tensor conversion requested dtype int32 for Tensor with dtype float32: 'Tensor("nce_loss/Reshape_1:0", shape=(?, 1, ?), dtype=float32)'