tensorflow 中的embedding 報錯問題解決

 

問題如圖:

解決參照如下：

今天TensorFlow中的tf.contrib.layers.embed_sequence來對輸入進行embedding時候，發現報瞭如下的錯誤：

InvalidArgumentError (see above for traceback): indices[1,2] = 6 is not in [0, 6)
	 [[Node: EmbedSequence_8/embedding_lookup = Gather[Tindices=DT_INT32, Tparams=DT_FLOAT, _class=["loc:@EmbedSequence_8/embeddings"], validate_indices=true, _dev
ice="/job:localhost/replica:0/task:0/cpu:0"](EmbedSequence_8/embeddings/read, EmbedSequence_8/embedding_lookup/indices)]]

後來就找了一些資料，尋求解決方法，發現是vocab_size要加1纔可以，因爲vocab_to_int是從1開始編碼的，0留作評論單詞不足的補全位，代碼如下：

       
    import tensorflow as tf
     
    features = [[1,2,3],[4,5,6]]
    n_words=6
    outputs = tf.contrib.layers.embed_sequence(features, vocab_size=n_words+1, embed_dim=4)
     
    with tf.Session(config=config) as sess:
        sess.run(tf.global_variables_initializer())
        a=sess.run(outputs)
        print(a)


詞向量結果如下：

[[[ 0.42639822 -0.45257723  0.44895023  0.17683214]
  [ 0.68834776  0.25755352  0.18518716 -0.36953419]
  [-0.20138246 -0.35034212  0.44844049  0.3326121 ]]

 [[-0.55106479 -0.64119202 -0.06463015 -0.68032914]
  [ 0.58467633  0.58155423  0.63106912  0.17282218]
  [ 0.46636218 -0.73744893  0.38337153  0.64258808]]]