迁移学习之VGG16和VGG19

文章目录

1.输出效果：
2.主文件TransorVGG16AndVGG19.py:

1.输出效果：

实际的图片——Dog：

预测的结果有误。但是没关系，自己可以找一些数据集，在此模型的基础上进行微调达到更好的效果。

关于InceptionV3（159层）,Xception（126层）,Inception_ResNet_V2（572层）：
https://mydreamambitious.blog.csdn.net/article/details/123907490
关于ResNet50和ResNet101：
https://mydreamambitious.blog.csdn.net/article/details/123906833
关于MobileNet（88层）和MobileNetV2（88层）：
https://mydreamambitious.blog.csdn.net/article/details/123907955
关于DenseNet121(121层）,DenseNet169(169层),DenseNet201(201层)：
https://mydreamambitious.blog.csdn.net/article/details/123908742
EfficientNetBX
https://mydreamambitious.blog.csdn.net/article/details/123929264

2.主文件TransorVGG16AndVGG19.py:

import os
import cv2
import numpy as np
import tensorflow.keras.applications.vgg16
from PIL import Image
from tensorflow import keras
from tensorflow.keras.preprocessing import image
from tensorflow.keras.preprocessing.image import img_to_array
from keras.applications.vgg16 import preprocess_input,decode_predictionsdef load_VGG_16():#加载VGG16模型,并且保留顶层model_VGG16=tensorflow.keras.applications.vgg16.VGG16(weights='imagenet')img_path='images/train/dog/1.jpg'# 将图像转换为网络需要的大小，因为我们这里加载的模型都是固定输入大小224*224img=image.load_img(img_path,target_size=(224,224))##首先需要转换为向量的形式img=image.img_to_array(img)# 扩充维度img=np.expand_dims(img,axis=0)# 对输入的图像进行处理img_out=preprocess_input(img)## decode the results into a list of tuples (class, description, probability)# (one such list for each sample in the batch)#上面这段话的意思是输出包括（类别，图像描述，输出概率）preds=model_VGG16.predict(img_out)# 输出前三个结果的可能性print('Predicted: ', decode_predictions(preds, top=3)[0])print('Predicted: ', decode_predictions(preds, top=3))def load_VGG_19():#加载VGG16模型,并且保留顶层model_VGG19=tensorflow.keras.applications.vgg19.VGG19(weights='imagenet')img_path='images/train/dog/1.jpg'# 将图像转换为网络需要的大小，因为我们这里加载的模型都是固定输入大小224*224img=image.load_img(img_path,target_size=(224,224))##首先需要转换为向量的形式img=image.img_to_array(img)# 扩充维度img=np.expand_dims(img,axis=0)# 对输入的图像进行处理img_out=preprocess_input(img)## decode the results into a list of tuples (class, description, probability)# (one such list for each sample in the batch)#上面这段话的意思是输出包括（类别，图像描述，输出概率）preds=model_VGG19.predict(img_out)# 输出前三个结果的可能性print('Predicted: ', decode_predictions(preds, top=3)[0])print('Predicted: ', decode_predictions(preds, top=3))if __name__ == '__main__':print('Pycharm')print('VGG16: Predict:\\n')load_VGG_16()print('VGG19: Predict:\\n')load_VGG_19()