运行出错出错: TypeError: Input 'y' of 'AddV2' Op has type int32 that does not match type float32 of argument 'x'.
检查发现是损失函数的数据 类型不一致
解决办法:用loss_pi=tf.cast(loss_pi,tf.float32)转换成统一的float类型
运行出错出错: TypeError: Input 'y' of 'AddV2' Op has type int32 that does not match type float32 of argument 'x'.
检查发现是损失函数的数据 类型不一致
解决办法:用loss_pi=tf.cast(loss_pi,tf.float32)转换成统一的float类型