tensorflow2+dataset+multi loss 多输出任务 匹配 多loss_tf的多输出loss

 之前提过在model的fit中使用 dataset

参考链接：https://blog.csdn.net/qq_24677259/article/details/108166601

 现在继续熟悉一下multi output和multi loss，多输出多损失函数

keras的函数式模型主要用于多输入多输出任务，输出按顺序对应损失函数list，在dataset构建时也要分为一个tuple含两个元素，分别对应输入和输出

dataset = tf.data.Dataset.from_tensor_slices((x_train, (y_train,y_train))).batch(32)

例子如下

from tensorflow.keras.datasets import cifar10
from tensorflow.keras import Model
from tensorflow.keras.layers import Conv2D,MaxPool2D,Flatten,Dense,Input
from tensorflow.keras.utils import to_categorical
from tensorflow.keras.optimizers import Adam
from tensorflow.keras.losses import mean_squared_error,categorical_crossentropy
import numpy as np
import tensorflow as tf
gpus = tf.config.experimental.list_physical_devices('GPU')
tf.config.experime