Dogs vs. Cats

本文主要是介绍Dogs vs. Cats，希望对大家解决编程问题提供一定的参考价值，需要的开发者们随着小编来一起学习吧！

二分类问题
我的方案：

import os
import sys
import cv2
import random
import pandas as pdimport matplotlib.pyplot as plt
import matplotlib.image as mpimg
import seaborn as sns
import itertools
from sklearn.model_selection import train_test_split
from sklearn.metrics import confusion_matrixfrom keras.utils.np_utils import to_categorical # convert to one-hot-encoding
from keras.models import Sequential
from keras.models import load_model
from keras.layers import Dense, Dropout, Flatten, Conv2D, MaxPool2D
from keras.optimizers import RMSprop
from keras.preprocessing.image import ImageDataGenerator
from keras.callbacks import ReduceLROnPlateau
from keras.callbacks import EarlyStopping
from keras.preprocessing.image import load_img,img_to_arrayimport numpy as np
root_path=sys.path[0]
train_path=r'./input/train/'
test_path=r'./input/test/'
train_list=next(os.walk(root_path+r'\input\train'))[2]
test_list=next(os.walk(root_path+r'\input\test'))[2]IMAGE_WIDTH=224
IMAGE_HEIGHT=224# train_path="../input/train/"
# test_path="../input/test/"
# train_list=next(os.walk(train_path))[2]
# test_list=next(os.walk(test_path))[2]# 根据图片路径获取图片标签
def get_img_label(img_paths):img_labels = []for img_path in img_paths:animal = img_path.split("/")[-1].split('.')[0]if animal == 'cat':img_labels.append(0)else:img_labels.append(1)img_labels=to_categorical(img_labels,2)return img_labels#读取图片
def load_batch_image(img_path,train_set=True,target_size=(IMAGE_WIDTH,IMAGE_HEIGHT)):im=load_img(img_path,target_size=target_size)if train_set:return img_to_array(im)else:return img_to_array(im)/255.0#建立一个数据迭代器
def get_dataset_shuffle(X_sample,batch_size,train_set=True):random.shuffle(X_sample)batch_num=int(len(X_sample)/batch_size)max_len=batch_num*batch_sizeX_sample=np.array(X_sample[:max_len])y_samples=get_img_label(X_sample)X_batches=np.split(X_sample,batch_num)y_batches=np.split(y_samples,batch_num)for i in range(len(X_batches)):if train_set:x=np.array(list(map(load_batch_image,X_batches[i],[True for _ in range(batch_size)])))else:x=np.array(list(map(load_batch_image,X_batches[i],[False for _ in range(batch_size)])))y=np.array(y_batches[i])yield x,y#数据增强处理train_datagen = ImageDataGenerator(rescale=1. / 255,rotation_range=10,width_shift_range=0.2,height_shift_range=0.2,shear_range=0.2,zoom_range=0.2,horizontal_flip=True)def build_model():# Define the modelmodel = Sequential()model.add(Conv2D(filters=32, kernel_size=(5, 5), padding='Same',activation='relu', input_shape=(IMAGE_WIDTH, IMAGE_HEIGHT, 3)))model.add(Conv2D(filters=32, kernel_size=(5, 5), padding='Same',activation='relu'))model.add(MaxPool2D(pool_size=(2, 2)))model.add(Dropout(0.25))model.add(Conv2D(filters=64, kernel_size=(3, 3), padding='Same',activation='relu'))model.add(Conv2D(filters=64, kernel_size=(3, 3), padding='Same',activation='relu'))model.add(MaxPool2D(pool_size=(2, 2), strides=(2, 2)))model.add(Dropout(0.25))model.add(Flatten())model.add(Dense(256, activation="relu"))model.add(Dropout(0.5))model.add(Dense(2, activation="sigmoid"))# Define the optimizeroptimizer = RMSprop(lr=0.001, rho=0.9, epsilon=1e-08, decay=0.0)# Compile the modelmodel.compile(optimizer=optimizer, loss="categorical_crossentropy", metrics=["accuracy"])return modeldef train():model=build_model()train_X=[train_path+item for item in train_list]# Set the random seedrandom_seed = 2# Split the train and the validation set for the fittingtrain_X, val_X = train_test_split(train_X, test_size = 0.1, random_state=random_seed)n_epoch=20batch_size=16for e in range(n_epoch):print('epoch',e)batch_num=0loss_sum=np.array([0.0,0.0])for X_train,y_train in get_dataset_shuffle(train_X,batch_size,True):for X_batch,y_batch in train_datagen.flow(X_train,y_train,batch_size=batch_size):loss=model.train_on_batch(X_batch,y_batch)loss_sum+=lossbatch_num+=1break#手动breakif batch_num%200==0:print("epoch %s, batch %s: train_loss = %.4f, train_acc = %.4f" % (e, batch_num, loss_sum[0] / 200, loss_sum[1] / 200))loss_sum = np.array([0.0, 0.0])res=model.evaluate_generator(get_dataset_shuffle(val_X,batch_size,False),int(len(val_X)/batch_size))print("val_loss = %.4f, val_acc = %.4f: " % (res[0], res[1]))model.save('weight.h5')def test():model=load_model('weight.h5')X_test_path=[test_path+item for item in test_list]results=[]for path in X_test_path:X_test=np.array(load_batch_image(path,False))X_test=np.expand_dims(X_test,axis=0)results.append(model.predict(X_test))results=np.array(results)results=np.argmax(results,axis=2)test_df=pd.read_csv('./input/sample_submission.csv')test_df['label']=resultstest_df.to_csv('result1.csv', index=False)if __name__=='__main__':train()test()