1.ValueError: Tensor conversion requested dtype int64 for Tensor with dtype float32: 'Tensor("loss/mul:0", shape=(), dtype=float32)'
解决方法:将报错项进行格式转换tf.to_float(self.predictions))
1.ValueError: Tensor conversion requested dtype int64 for Tensor with dtype float32: 'Tensor("loss/mul:0", shape=(), dtype=float32)'
解决方法:将报错项进行格式转换tf.to_float(self.predictions))