keras CNN相同的輸出

Question

我已經訓練了CNN神經網絡python與800個樣本，並在60測試。 預測它給我的相同的結果。

#main file - run this to train the network 

import numpy as np 
from keras.datasets import cifar10 
from datasetFetch import DataFetch 
from keras.models import Sequential 
from keras.layers import Dense 
from keras.layers import Dropout 
from keras.layers import Flatten 
from keras.constraints import maxnorm 
from keras.optimizers import SGD 
from keras.layers.convolutional import Conv2D 
from keras.layers.convolutional import MaxPooling2D 
from keras.utils import np_utils 
from keras import backend as K 
K.set_image_dim_ordering('th') 
import simplejson 
from matplotlib import pyplot 
from scipy.misc import toimage 
# load data 
#(X_train, y_train), (X_test, y_test) = cifar10.load_data() 
# create a grid of 3x3 images 
#for i in range(0, 9): 
# pyplot.subplot(3,3,1 + i) 
# pyplot.imshow(toimage(X_train[i])) 
# show the plot 
#pyplot.show() 

#init data 
CONST_PHOTOS = 400 # number of photos of each type 
y_train = [] 

#train data 
data = DataFetch('orange',CONST_PHOTOS) 
data1 = data.openPictures() 
data = DataFetch('apple', CONST_PHOTOS) 
data.removeErrorImages() 
data2 = data.openPictures() 

#test data 
tdata = DataFetch('test-orange',30) 
tdata1 = tdata.openPictures() 
tdata = DataFetch('test-apple',30) 
tdata2 = tdata.openPictures() 

#add togheter data 
X_train = data.connectData(data1,data2,'train') 
y_train = data.getYtrain('train') 
X_test = tdata.connectData(tdata1,tdata2,'test') 
y_test = tdata.getYtrain('test') 

# fix random seed for reproducibility 
seed = 7 
np.random.seed(seed) 

# normalize inputs from 0-255 to 0.0-1.0 
X_train = X_train.astype('float32') 
X_test = X_test.astype('float32') 
X_train = X_train/255.0 
X_test = X_test/255.0 

#one hot encode outputs 
y_train = np_utils.to_categorical(y_train) 
y_test = np_utils.to_categorical(y_test) 
num_classes = y_train.shape[1] #number of categories 


# Create the model 
model = Sequential() 
model.add(Conv2D(224, (11, 11), input_shape=(224, 224, 3), activation='relu', padding='same')) 
model.add(Dropout(0.2)) 
model.add(Conv2D(55, (5, 5), activation='relu', padding='same')) 
model.add(MaxPooling2D(pool_size=(2, 2), data_format="channels_last")) 
model.add(Conv2D(13, (3, 3), activation='relu', padding='same')) 
model.add(Dropout(0.5)) 
model.add(Conv2D(13, (3, 3), activation='relu', padding='same')) 
model.add(MaxPooling2D(pool_size=(2, 2), data_format="channels_last")) 
model.add(Flatten()) 
model.add(Dropout(0.2)) 
model.add(Dense(512, activation='relu', kernel_constraint=maxnorm(3))) 
model.add(Dropout(0.2)) 
model.add(Dense(num_classes, activation='softmax')) 

# Compile model 
epochs = 100 
lrate = 0.01 
decay = lrate/epochs 
sgd = SGD(lr=lrate, momentum=0.9, decay=decay, nesterov=False) 
model.compile(loss='binary_crossentropy', optimizer=sgd, metrics=['accuracy']) 
#print(model.summary()) 
model.fit(X_train, y_train, validation_data=(X_test, y_test), epochs=epochs, batch_size=10) 

# Final evaluation of the model 
scores = model.evaluate(X_test, y_test, verbose=0) 
print("Accuracy: %.2f%%" % (scores[1]*100)) 

#and then we save 
# serialize model to JSON 
model_json = model.to_json() 
with open("Data/model.json", "w") as json_file: 
    json_file.write(simplejson.dumps(simplejson.loads(model_json), indent=4)) 
# serialize weights to HDF5 
model.save_weights("Data/model.h5") 
print("Saved model to disk") 

我用keras和tensorflow。圖像是224x224像素每個分成2個類別。我對神經網絡瞭解不多，這是我第一次嘗試做這項大型工作。我聽說它可能過於合適，或者我需要一個更重要的圖層，或者我的批量/時代/學習率是錯誤的。

任何幫助表示讚賞！

編輯1：種子如何影響網絡的訓練？ 訓練結束後，精確度正好是50％，並且使用一個單獨的.py文件，它只加載模型並在其上使用預測函數返回所用圖像的確切輸出百分比。我嘗試了用於訓練和外部的圖像。 我添加了dataFetch代碼。

#preparing the photos to be 224x224 and getting them from urls saved in txt files 

from PIL import Image 
import requests 
from io import BytesIO 
import numpy as np 
import socket 
import random 
from scipy import misc 
from PIL import ImageChops 
import math, operator 
from functools import reduce 
import glob 
import os 
import signal 

compare = Image.open('/home/mihai/PycharmProjects/neuralnet/compare.jpg') 
compare1 = Image.open('/home/mihai/PycharmProjects/neuralnet/compare1.jpg') 
compare2 = Image.open('/home/mihai/PycharmProjects/neuralnet/compare2.jpg') 
compare3 = Image.open('/home/mihai/PycharmProjects/neuralnet/compare3.jpg') 
compare4 = Image.open('/home/mihai/PycharmProjects/neuralnet/compare4.jpg') 

def rmsdiff(im1, im2): 
    "Calculate the root-mean-square difference between two images" 

    h = ImageChops.difference(im1, im2).histogram() 

    # calculate rms 
    return math.sqrt(reduce(operator.add, map(lambda h, i: h*(i**2), h, range(256)))/(float(im1.size[0]) * im1.size[1])) 

class DataFetch: 

    chosenFile = '' 
    maxNumber = 0 
    y_train = [] 
    y_test = [] 

    def __init__(self, choice, number): 
     print('Images with '+choice+'s are being prepared') 
     self.chosenFile = choice 
     self.maxNumber = number 

    def getPictures(self): 
     imgArr = np.zeros((self.maxNumber, 224, 224, 3), dtype='uint8') 
     count = 0 
     class timeoutError(Exception): 
      signal.alarm(0) 
     def handler(signum, frame): 
      raise timeoutError 
     with open(self.chosenFile, "r") as ins: 
      for line in ins: 
       if count < self.maxNumber: 
        signal.signal(signal.SIGALRM, handler) 
        signal.alarm(3) 
        try: 
         try: 
          r = requests.get(line) 
          try: 
           img = Image.open(BytesIO(r.content)) 
           ok = 0 
           try: 
            if rmsdiff(compare, img) > 1.3 and rmsdiff(compare1, img) > 1.3 and rmsdiff(compare2, img) > 1.3 and rmsdiff(compare3, img) > 1.3 and rmsdiff(compare4, img) > 1.3: 
             ok = 1 
            else: 
             print('Image removed from website') 
           except ValueError: 
            ok = 1 
           if ok == 1: 
            img = img.resize((224, 224)) 
            img = img.convert('RGB') 
            img.save('/home/mihai/PycharmProjects/neuralnet/images/'+self.chosenFile+'/'+str(count)+".jpg", 'JPEG') 
            imgArr[count, :, :, :] = img 
            count = count + 1 
            print(count) 
          except OSError: 
           print('Image not Available') 
         except socket.error: 
          print('URL not available') 
        except timeoutError: 
         print("URL not available") 
     return imgArr 

    def openPictures(self): 
     cdir = os.getcwd() 
     imgArr = np.zeros((self.maxNumber, 224, 224, 3), dtype='uint8') 
     count = 0 
     for filename in glob.glob(cdir+'/images/'+self.chosenFile+'/*.jpg'): 
      if count < self.maxNumber: 
       img = Image.open(filename) 
       imgArr[count, :, :, :] = img 
       count = count + 1 
     return imgArr 

    def removeErrorImages(self): 
     cdir = os.getcwd() 
     for filename in glob.glob(cdir+'/images/'+self.chosenFile+'/*.jpg'): 
      img = Image.open(filename) 
      try: 
       if rmsdiff(compare, img) < 1.3 or rmsdiff(compare1, img) < 1.3 or rmsdiff(compare2, img) < 1.3 or rmsdiff(compare3, img) < 1.3 or rmsdiff(compare4, img) < 1.3: 
        os.remove(cdir+'/images/'+self.chosenFile+'/'+filename+'.jpg') 
      except ValueError: 
       pass 

    def getYtrain(self,outParam): 
     if outParam == 'train': 
      self.y_train = np.reshape(self.y_train, (len(self.y_train), 1)) 
      return self.y_train 
     else: 
      self.y_test = np.reshape(self.y_test, (len(self.y_test), 1)) 
      return self.y_test 

    def connectData(self, data1, data2, outParam): 
     d1c = 0 
     d2c = 0 
     outList = [] 
     X_train = np.zeros((2 * self.maxNumber, 224, 224, 3), dtype='uint8') 
     for i in range(2 * self.maxNumber): 
      if d1c < self.maxNumber and d2c <self.maxNumber: 
       if random.random() <= 0.5: 
        X_train[d1c + d2c, :, :, :] = data1[d1c, :, :, :] 
        d1c = d1c + 1 
        outList.append(0) 
       else: 
        X_train[d1c + d2c, :, :, :] = data2[d2c, :, :, :] 
        d2c = d2c + 1 
        outList.append(1) 
      else: 
       if d1c < self.maxNumber: 
        X_train[d1c + d2c, :, :, :] = data1[d1c, :, :, :] 
        d1c = d1c + 1 
        outList.append(0) 
       else: 
        if d2c < self.maxNumber: 
         X_train[d1c + d2c, :, :, :] = data2[d2c, :, :, :] 
         d2c = d2c + 1 
         outList.append(1) 
     if outParam == 'train': 
      self.y_train = outList 
     else: 
      if outParam == 'test': 
       self.y_test = outList 
     return X_train 

代碼預測：

#run this to test a sample 

from keras.utils import np_utils 
from keras.models import model_from_json 
from keras.optimizers import SGD 
from datasetFetch import DataFetch 

# load json and create model 
json_file = open('Data/model2.json', 'r') 
loaded_model_json = json_file.read() 
json_file.close() 
loaded_model = model_from_json(loaded_model_json) 

# load weights into new model 
loaded_model.load_weights("Data/model2.h5") 
print("Loaded model from disk") 

epochs = 100 
lrate = 0.01 
decay = lrate/epochs 
sgd = SGD(lr=lrate, momentum=0.9, decay=decay, nesterov=False) 
loaded_model.compile(loss='categorical_crossentropy', optimizer=sgd, metrics=['accuracy']) 

#prepare X_test 
tdata = DataFetch('test-orange',int(3)) 
tdata1 = tdata.openPictures() 
tdata = DataFetch('test-apple',int(3)) 
tdata2 = tdata.openPictures() 
X_test = tdata.connectData(tdata1,tdata2,'test') 
y_test = tdata.getYtrain('test') 
X_test = X_test.astype('float32') 
X_test = X_test/255.0 
y_test = np_utils.to_categorical(y_test) 
print('Number of samples to be tested: '+str(X_test.shape[0])) 

scores = loaded_model.evaluate(X_test, y_test, verbose=0) 
print(scores[1]*100) 

score = loaded_model.predict(X_test,batch_size=6, verbose=1) 
print(score) #prints percentages 

Answer 1

圖像準備是正確的。問題出在神經網絡的結構加上使用的優化方法。

由於用於分類只有2個類的神經元數量巨大，結構過度擬合，導致精度保持在50％。

第二個問題是使用sgd優化器。我使用：

opt=keras.optimizers.rmsprop(lr=0.0001, decay=1e-6) 
model.compile(loss='binary_crossentropy', optimizer=opt, metrics=['accuracy'] 

希望這可以幫助別人！