时间戳

首页 > 解决方案 > CNN 模型预测任何输入的相同输出

python - CNN 模型预测任何输入的相同输出

问题描述

enter code here
from keras.models import Sequential
from keras.layers import Convolution2D
from keras.layers import Flatten
from keras.layers import Dense
from keras.layers import MaxPooling2D
classifier = Sequential()
classifier.add(Convolution2D(32,(3,3),input_shape = (64,64,3), activation = 'relu'))

classifier.add(MaxPooling2D(pool_size = (2, 2)))
classifier.add(Convolution2D(32,(3,3), activation = 'relu'))

classifier.add(MaxPooling2D(pool_size = (2, 2)))

classifier.add(Flatten())
classifier.add(Dense(units=32,activation = 'relu'))
classifier.add(Dense(units=64,activation = 'relu'))

classifier.add(Dense(units=128,activation = 'relu'))

classifier.add(Dense(units=256,activation = 'relu'))

classifier.add(Dense(units=256,activation = 'relu'))

classifier.add(Dense(units=6,activation = 'softmax'))

classifier.compile(optimizer = 'adam', loss = 'categorical_crossentropy', metrics = ['accuracy'])

from keras.preprocessing.image import ImageDataGenerator
train_datagen = ImageDataGenerator(rescale = 1./255, # To rescaling the image in range of [0,1]
                               shear_range = 0.2, # To randomly shear the images 
                               zoom_range = 0.2, # To randomly zoom the images
                               horizontal_flip = True) #  for randomly flipping half of the images 
horizontally 

test_datagen = ImageDataGenerator(rescale = 1./255)
print("\nTraining the data...\n")
training_set = train_datagen.flow_from_directory('train',
                                            target_size=(64,64),
                                            batch_size=12, #Total no. of batches
                                            class_mode='categorical')

test_set = test_datagen.flow_from_directory('test',
                                        target_size=(64,64),
                                        batch_size=12,
                                        class_mode='categorical')

classifier.fit_generator(training_set,
                     steps_per_epoch=len(training_set), # Total training images
                     epochs = 20, # Total no. of epochs
                     validation_data = test_set,
                     validation_steps = len(test_set)) # Total testing images

classifier.save("model.h5")


#Prediction
classes = ['Fresh Apple','Fresh Banana','Fresh Orange','Rotten Apple','Rotten Banana','Rotten 
Orange']
from keras.preprocessing import image
from keras.models import load_model
import numpy as np
new_model = load_model('model.h5')
filename = 'a1.jpeg'
new_model.summary()
test_image = image.load_img('images\\a1.jpg',target_size=(64,64))
test_image = image.img_to_array(test_image)
test_image = np.expand_dims(test_image, axis = 0)
result = new_model(test_image)
result1 = result[0]
for i in range(6):
  if result1[i] == 1.:
    break;
prediction = classes[i]
print(prediction)

我的模型为任何输入提供相同的输出。错误和警告已被删除，但输出仍然保持不变。早些时候，模型在删除警告之前给出了相同的值“A”（示例），在删除警告之后，模型给出了相同的值“B”。我不知道我的代码中的问题是在模型中还是在#Prediction 中。

标签： pythontensorflowkerasdeep-learningconv-neural-network

解决方案

有几件事。在您的生成器中，您将批量大小设置为 12。然后在 model.fit 中，您有 steps_per_epoch=len(training_set)。这意味着您将在每个 epoch 中遍历您的训练集 12 次。我通常将每个时期的步骤和验证步骤保留为无。model.fit 将在内部确定值，但如果你想然后设置

steps_per_epoch = int(len(train_set/batch_size) + 1
validation_steps= int(len(test_set/batch_size) +1

现在在预测中。您将训练和测试图像缩放了 1/255。您需要对希望预测的图像执行相同的操作。所以在扩展维度的代码之后添加代码

test_image=test_image/255

推荐阅读