基于yolo_v3的水印检测

基于yolo_v3的水印检测

(adsbygoogle = window.adsbygoogle || []).push({}); 背景 近年来版权意识的提高,在使用别人图片的时候(尤其是商业领域),需要检测图片是否有别的公司的水印( 主要针对人眼可见的水印,除去数
Keras多标签分类网络实现

Keras多标签分类网络实现

(adsbygoogle = window.adsbygoogle || []).push({}); 简谈多分类与多标签分类 简单的说,输入一张图片进行分类: * 这张图片里面的物体(通常认为只有一个物体)属于某一个类,各个类别之间的概率
Keras数据集加载小结

Keras数据集加载小结

(adsbygoogle = window.adsbygoogle || []).push({}); 对于keras加载训练数据,官方上没有详说。然而网上查各种资料,写法太多,通过自己跑代码测试总结以下几条,方便自己以后使用。 总的来
基于Keras图像相似度计算孪生网络

基于Keras图像相似度计算孪生网络

(adsbygoogle = window.adsbygoogle || []).push({}); import keras from keras.layers import Input,Dense,Conv2D from keras.layers import MaxPooling2D,Flatten,Convolution2D from keras.models import Model import os import numpy as np from PIL import Image from keras.optimizers import SGD from scipy import misc root_path = os.getcwd() train_names = ['bear','blackswan','bus','camel','car','cows','dance','dog','hike','hoc','kite','lucia','mallerd','pigs','soapbox','stro','surf','swing','train','walking'] test_names = ['boat','dance-jump','drift-turn','elephant','libby'] def load_data(seq_names,data_number,seq_len): #生成图片对 print('loading data.....') frame_num = 51 train_data1 = [] train_data2 = [] train_lab = [] count =
Keras 猫狗二分类

Keras 猫狗二分类

(adsbygoogle = window.adsbygoogle || []).push({}); import keras from keras.models import Sequential from keras.layers import Dense,MaxPooling2D,Input,Flatten,Convolution2D,Dropout,GlobalAveragePooling2D from keras.optimizers import SGD from keras.callbacks import TensorBoard,ModelCheckpoint from PIL import Image import os import numpy as np from scipy import misc root_path = os.getcwd() def load_data(): tran_imags = [] labels = [] seq_names = ['cat','dog'] for seq_name in seq_names: frames = sorted(os.listdir(os.path.join(root_path,'data','train_data', seq_name))) for frame in frames: imgs = [os.path.join(root_path, 'data', 'train_data', seq_name, frame)]