tensorflow history使用

import cv2
#正则匹配使用：
import re
import os
#此库用于拷贝，删除，移动，复制以及解压缩
import shutil
import numpy as np
import tensorflow as tf
from tensorflow.keras.preprocessing.image import ImageDataGenerator
from tensorflow.keras.applications import resnet
from tensorflow.keras.utils import plot_model
from tensorflow.keras.layers import Input,GlobalAvgPool2D,Dense,Dropout
from tensorflow.keras.models import Model
from tensorflow.keras.losses import SparseCategoricalCrossentropy
from tensorflow.keras.optimizers import Adam
from tensorflow.keras.callbacks import ModelCheckpoint,TensorBoard,EarlyStopping
import matplotlib.pyplot as plt
#如此读取图像，直接返回numpy.ndarray
#img=cv2.imdecode(np.fromfile(“C:/Users/104005162/Desktop/企业微信截图_20220212102256.png”,np.uint8),-1)
#print(img.shape)
##转换为bgr图片，注意此时是PNG图片，不能用矩阵直接转换！
##img=img[:,:,::-1]
##bgra
#img=cv2.cvtColor(img,cv2.COLOR_BGRA2RGB)
dataAll=ImageDataGenerator(validation_split=0.3)
genIteratorForTrain=dataAll.flow_from_directory("D:/17flowers",batch_size=32,subset="training",class_mode='sparse')
genIteratorForText=dataAll.flow_from_directory("D:/17flowers",batch_size=32,subset="validation",class_mode='sparse')
#17花朵分类的输入形状为(256, 256, 3)
shape_in=genIteratorForTrain.next()[0].shape[1:]
model=Dense(100)
#定义一个输入层：
inputs=Input(shape=shape_in)
#此处x形状为(None, 7, 7, 2048)
x=model(inputs)
#此处x形状为(None, 2048)
x=GlobalAvgPool2D()(x)
#此处x形状为(None, 2048)
x=Dense(units=17)(x)
#此处x形状为(None, 2048)
x=Dropout(rate=0.5)(x)
model2=Model(inputs = inputs, outputs = x)
#也可以通过此形式直接输出形状L:
plot_model(model2,to_file="text.png",show_shapes=True)
#min_delta=为有效性度量，patience为无效代数，baseline为基准值，只有当当前效果同时优于上一代及基准值，才归0。该值设定可以为，在patience内
#没有达到要求的baseline，也停止。
Ep = EarlyStopping(monitor='val_loss',min_delta=1, patience=5, restore_best_weights=True,baseline=5)
#monitor决定保存模型的因素是准确率还是损失大小
checkPoint=ModelCheckpoint(filepath='{epoch:02d}-{sparse_categorical_accuracy:.4f}.h5',
                    monitor='val_sparse_categorical_accuracy',
                    verbose=1,
                    save_best_only=True)
#未经概率分布直接输出,lr合适，不然导致不收敛，SparseCategoricalCrossentropy代表从0开始的输出，就是index，SparseCategoricalCrossentropy将y_true变成了one-hot编码
model2.compile(optimizer=Adam(lr=0.001),loss=SparseCategoricalCrossentropy(from_logits=True),metrics=['sparse_categorical_accuracy'])
history=model2.fit(x=genIteratorForTrain,validation_data=genIteratorForText,
                   callbacks=[checkPoint,Ep],validation_freq=1,epochs=2000)
plt.plot(history.history['sparse_categorical_accuracy'], label='sparse_categorical_accuracy')
#打印验证集上的准确率
plt.plot(history.history['val_sparse_categorical_accuracy'], label='val_sparse_categorical_accuracy')
#验证集上的损失函数
plt.plot(history.history['val_loss'], label='val_loss')
plt.show()