tensorflow2.0使用自带的函数求精准率和召回率（解决Shapes (None, 10) and (None, 1) are incompatible）

本代码使用的是cifar10数据集，所以有十个类别
废话不多说，直接给代码吧

import tensorflow as tf
from tensorflow.keras import datasets, Sequential, layers,metrics
(x_train, y_train), _ = datasets.cifar10.load_data()

def procession(x, y):
    x = tf.cast(x, dtype=tf.float32)