# -*- coding: utf-8 -*- ''' Created on 2018年1月26日 @author: Jason.F @summary: pip install Keras Keras 神經網絡訓練庫，可使用GPU加速神經網絡的訓練，基于張量庫Theano支持多維數組處理 ''' import numpy as np import time import os import struct import theano from keras.utils import np_utils from keras.models import Sequential from keras.layers.core import Dense from keras.optimizers import SGDdef load_mnist(path,kind='train'):#load mnist data from pathlabels_path = os.path.join(path,'%s-labels.idx1-ubyte'%kind)images_path = os.path.join(path,'%s-images.idx3-ubyte'%kind)with open(labels_path,'rb') as lbpath:magic,n =struct.unpack('>II',lbpath.read(8))labels = np.fromfile(lbpath,dtype = np.uint8)with open(images_path,'rb') as imgpath:magic,num,rows,cols =struct.unpack('>IIII',imgpath.read(16))images = np.fromfile(imgpath,dtype = np.uint8).reshape(len(labels),784)#28X28像素return images,labels ?if __name__ == "__main__":? ?start = time.clock() ?#導入數據集homedir = os.getcwd()#獲取當前文件的路徑X_train,y_train = load_mnist(homedir+'\\mnist', kind='train')print ('Rows:%d,columns:%d'%(X_train.shape[0],X_train.shape[1]))X_test,y_test = load_mnist(homedir+'\\mnist', kind='t10k')print ('Rows:%d,columns:%d'%(X_test.shape[0],X_test.shape[1]))#將MNIST圖像的數組轉換為32位浮點數格式theano.config.floatX='float32'X_train = X_train.astype(theano.config.floatX)X_test = X_test.astype(theano.config.floatX)#onehot編碼print ('First 3 labels:',y_train[:3])y_train_ohe = np_utils.to_categorical(y_train)print('\nFirst 3 labels(one-hot):\n',y_train_ohe[:3])#實現神經網絡，隱層使用雙曲正切函數，輸出層使用softmax函數np.random.seed(1)model = Sequential()model.add(Dense(input_dim=X_train.shape[1],output_dim=50,init='uniform',activation='tanh'))model.add(Dense(input_dim=50,output_dim=50,init='uniform',activation='tanh'))model.add(Dense(input_dim=50,output_dim=y_train_ohe.shape[1],init='uniform',activation='tanh'))sgd =SGD(lr=0.001,decay=1e-7,momentum=.9)model.compile(loss='categorical_crossentropy',optimizer=sgd)model.fit(X_train,y_train_ohe,nb_epoch=50,batch_size=300,verbose=1,validation_split=0.1)#show_accuracy=Truey_train_pred = model.predict_classes(X_train,verbose=0)print ('First 3 predictions:',y_train_pred[:3])train_acc = np.sum(y_train==y_train_pred,axis=0)/float(X_train.shape[0])print ('Training accuracy:%.2f%%'%(train_acc*100))y_test_pred=model.predict_classes(X_test,verbose=0)test_acc = np.sum(y_test==y_test_pred,axis=0)/float(X_test.shape[0])print ('Test accuracy:%.2f%%'%(test_acc*100))end = time.clock()?? ?print('finish all in %s' % str(end - start))

設置：

windows，pip install keras后，到C:\Users\user\.keras目錄下找到keras.json文件，默認設置如下圖：

修改backend為：

結果：

Training accuracy:13.63% Test accuracy:13.45% finish all in 13968.1836241執行一次好長時間，準確率這么低要找下原因。

總結

以上是生活随笔為你收集整理的【Python-ML】神经网络-深度学习库Keras的全部內容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網站內容還不錯，歡迎將生活随笔推薦給好友。