写代码时遇到的问题（tensorflow相关）

1. 喂数据时报错：InvalidArgumentError (see above for traceback): logits and labels must have the same first dimension, got logits shape [3,9] and labels shape [123]
     [[node loss/SparseSoftmaxCrossEntropyWithLogits/SparseSoftmaxCrossEntropyWithLogits (defined at D:\workspace\RL\reinforcementLearning\RL_brain.py:82) ]]

错误截图：te_acts报错了

错误原因：计算交叉熵时，loggits和label的第一维维数不一致

修改：将二者维度改为一样，又出错

 Rank mismatch: Rank of labels (received 2) should equal rank of logits minus 1 (received 2).

原因：求损失函数时，labels应比logits少一个维度

后续修改：换了损失函数

 

2.画图时出错：The number of derivatives at boundaries does not match: expected 1, got 0+0

发现问题是x和y的元素个数少于3就会报错，多加点数据就可以了