【错误记录】train_function-＞train_function
⽂本（⽅便查）：InvalidArgumentError: 2 root error(s) found. (0) Invalid argument: indices[0,0] = 3479 is not in [0, 1785) [[node sequential/embedding/embedding_lookup (defined at <ipython-input-15-f68b96d3c625>:7) ]]
[[sequential/embedding/embedding_lookup/_24]] (1) Invalid argument: indices[0,0] = 3479 is not in [0, 1785) [[node sequential/embedding/embedding_lookup (defined at <ipython-input-15-f68b96d3c625>:7) ]] 0 successful operations. 0 derived errors ignored. [Op:__inference_train_function_4487] Errors may have originated from an input operation. Input Sourc
e operations connected to node sequential/embedding/embedding_lookup:
sequential/embedding/embedding_lookup/2796 (defined at /usr/lib/python3.7/contextlib.py:112) Input Source operations connected to node sequential/embedding/embedding_lookup: sequential/embedding/embedding_lookup/2796 (defined at /usr/lib/python3.7/contextlib.py:112) Function call stack: train_function -> train_function
问题翻译：InvalidArgumentError：到2个根错误。 （0）⽆效参数：indexs [0,0] = 3479不在[0，1785中] [[节点顺序/嵌⼊/嵌⼊_查（在<ipython-input-15-f68b96d3c625>：7处定义）]]] [[顺序 / embedding / embedding_lookup / _24]]（1）⽆效的参数：indexs [0,0] = 3479不在[0，1785中] [[节点顺序/ embeddding / embedding_lookup（定义在<ipython-input-15-
f68b96d3c625> ：7）]] 0成功操作。 忽略0个派⽣错误。 [Op：__ inference_train_function_4487]错误可能是由于输⼊操作引起的。 输⼊源操作连接到节点sequential / embeddding / embedding_lookup：顺序/ embeddding / embedding_lookup /
2796（在/usr/lib/python3.7/contextlib.py:112上定义）输⼊源操作连接到节点sequence / embeddding / embedding_lookup：顺序 / embedding / embedding_lookup / 2796（在/usr/lib/python3.7/contextlib.py:112中定义）函数调⽤堆栈：
train_function-> train_function
问题分析：
[0.1785]这个问题可以看出是词表的问题，我的chinese vocabulary size: 1784，English vocabulary size: 5232，所以词表⼤⼩要加到最⼤的那⼀个，修改代码为：english_vocab_size+1, chinese_vocab_size+3450
>function怎么记忆

版权声明：本站内容均来自互联网，仅供演示用，请勿用于商业和其他非法用途。如果侵犯了您的权益请与我们联系QQ:729038198，我们将在24小时内删除。