Question

我正在尝试使用Keras解决Cats vs Dogs问题。这是我正在使用的模型。

from keras.preprocessing.image import ImageDataGenerator
from keras.models import Sequential
from keras.layers import Conv2D, MaxPooling2D
from keras.layers import Activation, Dropout, Flatten, Dense
from keras import backend as K
from keras import regularizers
from keras.utils import plot_model

img_width, img_height = 150, 150
train_data_dir = 'kateVSdoge/train'
validation_data_dir = 'kateVSdoge/validation'
nb_train_samples = 2000
nb_validation_samples = 800
epochs = 50
batch_size = 16
if K.image_data_format() == 'channels_first':
    input_shape = (3, img_width, img_height)
else:
    input_shape = (img_width, img_height, 3)

model = Sequential()

model.add(Conv2D(32, (3, 3), input_shape=input_shape))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))

model.add(Conv2D(32, (3, 3)))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))

model.add(Conv2D(64, (3, 3)))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))

model.add(Flatten())
model.add(Dense(64))
model.add(Activation('relu'))
model.add(Dropout(0.5))
model.add(Dense(1,kernel_regularizer=regularizers.l2(0.01),
                activity_regularizer=regularizers.l1(0.01)))
model.add(Activation('sigmoid'))

model.compile(loss='binary_crossentropy',
              optimizer='rmsprop',
              metrics=['accuracy'])


train_datagen = ImageDataGenerator(
                rescale=1. / 255,
                shear_range=0.2,
                zoom_range=0.2,
                horizontal_flip=True)

test_datagen = ImageDataGenerator(rescale=1. / 255)
train_generator = train_datagen.flow_from_directory(
                    train_data_dir,
                    target_size=(img_width, img_height),
                    batch_size=batch_size,
                    class_mode='binary')
validation_generator = test_datagen.flow_from_directory(
                        validation_data_dir,
                        target_size=(img_width, img_height),
                        batch_size=batch_size,
                        class_mode='binary',
                        )
xm=model.fit_generator(
                    train_generator,
                    steps_per_epoch=nb_train_samples // batch_size,
                    epochs=epochs,
                    validation_data=validation_generator,
                    validation_steps=nb_validation_samples // batch_size)

model.save_weights('first_try3.h5')
model_json=model.to_json()
with open("model3.json","w+") as json_file:
    json_file.write(model_json)
plot_model(model,to_file="model.jpeg")

该模型最终精确度为0.79-0.80。但是当我尝试在预测器脚本中加载模型并使用 model.predict_generator（）预测时，我似乎做错了，因为我无法在预测中获得类名。我尝试过 .predict（）和 .predict_proba（）。

以下是预测器脚本：

from keras.models import Sequential, model_from_json
from keras.preprocessing import image
from keras.preprocessing.image import ImageDataGenerator
import numpy as np


p_model = Sequential();
jsonfile = open('model3.json','r')
model_json = jsonfile.read()
p_model = model_from_json(model_json)
p_model.load_weights('first_try3.h5')
p_model.compile(loss='binary_crossentropy',
                optimizer='rmsprop',
                metrics=['accuracy'])

img = image.load_img('do.jpg', target_size=(150,150))
x=image.img_to_array(img)
x=x.reshape((1,)+x.shape)
test_datagen = ImageDataGenerator(rescale=1. /255)
m=test_datagen.flow(x,batch_size=1)


preds = p_model.predict_generator(m,1,verbose=1)
print preds

此外，我观察到一个有趣的事情，图像似乎没有重新缩放。我打印出 x 和 m.x ，两个矩阵似乎都相等，且值不会转换为介于0和1之间。

这是猫和狗图片的输出。

(myenv)link@zero-VirtualBox:~/myenv/keras_app$ python predictor.py 
Using Theano backend.
1/1 [==============================] - 0s
[[ 0.29857877]]
(myenv)link@zero-VirtualBox:~/myenv/keras_app$ python predictor.py 
Using Theano backend.
1/1 [==============================] - 0s
[[ 0.77536112]]

我已经使用了https://stackoverflow.com/a/41833076/4159447给出的建议来介绍正则化和重新缩放。

我做错了什么？我想要的只是让猫狗标签与他们的分数相符。

Answer 1

唯一错误的是期望来自分类器的类名。分类器不知道类名，即后处理步骤，如：

preds = p_model.predict_generator(m,1,verbose=1)[0]

if preds > 0.5:
    output = "cat"
else:
   output = "dog"

请注意，0.5可能不是最佳阈值，您也可以选择概率最大的类（p vs 1 - p）。

Keras Predictions中没有类别标签

1 个答案: