深度学习实战4-卷积神经网络（DenseNet）数学图形识别+题目模式识别.zip

import tensorflow as tf # from keras import keras.layers import matplotlib.pyplot as plt from time import * # from tensorflow.keras.models import Sequential # from tensorflow.keras.layers import Dense,Dropout,MaxPooling2D,Flatten,Conv2D data_dir = "./data" batch_size = 12 img_height = 224 img_width = 224 train_ds = tf.keras.preprocessing.image_dataset_from_directory( data_dir, validation_split=0.2, subset="training", seed=12, image_size=(img_height, img_width), batch_size=batch_size) val_ds = tf.keras.preprocessing.image_dataset_from_directory( data_dir, validation_split=0.2, subset="validation", seed=12, image_size=(img_height, img_width), batch_size=batch_size) model = tf.keras.applications.DenseNet121(weights='imagenet') model.summary() # 设置初始学习率 initial_learning_rate = 1e-3 lr_schedule = tf.keras.optimizers.schedules.ExponentialDecay( initial_learning_rate, decay_steps=5, # 敲黑板！！！这里是指 steps，不是指epochs decay_rate=0.96, # lr经过一次衰减就会变成 decay_rate*lr staircase=True) # 将指数衰减学习率送入优化器 optimizer = tf.keras.optimizers.Adam(learning_rate=lr_schedule) model.compile(optimizer=optimizer, loss ='sparse_categorical_crossentropy', metrics =['accuracy']) def show_loss_acc(history): # 从history中提取模型训练集和验证集准确率信息和误差信息 acc = history.history['accuracy'] val_acc = history.history['val_accuracy'] loss = history.history['loss'] val_loss = history.history['val_loss'] # 按照上下结构将图画输出 plt.figure(figsize=(8, 8)) plt.subplot(2, 1, 1) plt.plot(acc, label='Training Accuracy') plt.plot(val_acc, label='Validation Accuracy') plt.legend(loc='lower right') plt.ylabel('Accuracy') plt.ylim([min(plt.ylim()), 1]) plt.title('Training and Validation Accuracy') plt.subplot(2, 1, 2) plt.plot(loss, label='Training Loss') plt.plot(val_loss, label='Validation Loss') plt.legend(loc='upper right') plt.ylabel('Cross Entropy') plt.title('Training and Validation Loss') plt.xlabel('epoch') plt.savefig('results/results_cnn.png', dpi=100) plt.show() def train(epochs): # 开始训练，记录开始时间 begin_time = time() AUTOTUNE = tf.data.AUTOTUNE train_ds1 = train_ds.cache().shuffle(1000).prefetch(buffer_size=AUTOTUNE) val_ds1 = val_ds.cache().prefetch(buffer_size=AUTOTUNE) # print(class_names) # 加载模型 # model = model_load(class_num=len(class_names)) # 指明训练的轮数epoch，开始训练 history = model.fit(train_ds1,validation_data=val_ds1,epochs=epochs) # todo 保存模型， 修改为你要保存的模型的名称 model.save("cnn_fv.h5") # 记录结束时间 end_time = time() run_time = end_time - begin_time print('该循环程序运行时间：', run_time, "s") # 该循环程序运行时间： 1.4201874732 # 绘制模型训练过程图 show_loss_acc(history) train(epochs=6)