格式化图像数据以预测图像中的数字以用于 MNIST 数据模型

Question

我在使用 MNIST 尝试 Keras 时遇到问题。我有一个保存的模型，其准确率超过 99%，但是当我用它来预测一些图像时，它总是预测为 1。我认为这是由于我在 test.py 文件中以错误的方式重新调整了图像数据输入。

我得到了错误：

ValueError: Error when checking : expected conv2d_1_input to have 4 dimensions, but got array with shape (28, 28)

或者，如果我尝试随机重塑 (1, 1, 28, 28)，我会收到以下错误：

ValueError: Error when checking : expected conv2d_1_input to have shape (None, 28, 28, 1) but got array with shape (1, 1, 28, 28)

所以我尝试在 image_to_data 函数中添加以下内容：

image_data = image_data.reshape((1, 28, 28, 1))

现在代码运行但总是预测相同的值。如何以正确的方式将图像数据重塑为 28 x 28 像素，使其适合模型中的第一层以预测一个图像的类别？

train.py

from __future__ import print_function
import keras
from keras.datasets import mnist
from keras.models import Sequential
from keras.layers import Dense, Dropout, Flatten
from keras.layers import Conv2D, MaxPooling2D
from keras import backend as K

batch_size = 128
num_classes = 10
epochs = 20

# input image dimensions
img_rows, img_cols = 28, 28

# the data, shuffled and split between train and test sets
(x_train, y_train), (x_test, y_test) = mnist.load_data()

if K.image_data_format() == 'channels_first':
x_train = x_train.reshape(x_train.shape[0], 1, img_rows, img_cols)
x_test = x_test.reshape(x_test.shape[0], 1, img_rows, img_cols)
input_shape = (1, img_rows, img_cols)
else:
x_train = x_train.reshape(x_train.shape[0], img_rows, img_cols, 1)
x_test = x_test.reshape(x_test.shape[0], img_rows, img_cols, 1)
input_shape = (img_rows, img_cols, 1)

x_train = x_train.astype('float32')
x_test = x_test.astype('float32')
x_train /= 255
x_test /= 255
print('x_train shape:', x_train.shape)
print(x_train.shape[0], 'train samples')
print(x_test.shape[0], 'test samples')

# convert class vectors to binary class matrices
y_train = keras.utils.to_categorical(y_train, num_classes)
y_test = keras.utils.to_categorical(y_test, num_classes)

model = Sequential()
model.add(Conv2D(32, kernel_size=(3, 3),
             activation='relu',
             input_shape=input_shape))
model.add(Conv2D(64, (3, 3), activation='relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.25))
model.add(Flatten())
model.add(Dense(128, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(num_classes, activation='softmax'))

model.compile(loss=keras.losses.categorical_crossentropy,
          optimizer=keras.optimizers.Adadelta(),
          metrics=['accuracy'])

model.fit(x_train, y_train,
      batch_size=batch_size,
      epochs=epochs,
      verbose=1,
      validation_data=(x_test, y_test))
score = model.evaluate(x_test, y_test, verbose=0)
print('Test loss:', score[0])
print('Test accuracy:', score[1])

# serialize model to YAML
model_yaml = model.to_yaml()
with open("model-new.yaml", "w") as yaml_file:
yaml_file.write(model_yaml)
# serialize weights to HDF5
model.save_weights("model-new.h5")
print("Saved model to disk")

test.py

from PIL import Image
from keras.models import model_from_yaml
import numpy as np

def load_model():
    # load YAML and create model
    yaml_file = open('model.yaml', 'r')
    model_yaml = yaml_file.read()
    yaml_file.close()
    model = model_from_yaml(model_yaml)
    # load weights into new model
    model.load_weights("model.h5")
    print("Loaded model from disk")
    model.compile(loss='binary_crossentropy', optimizer='rmsprop', metrics=['accuracy'])
    return model

def image_to_data(image):
    image_data = np.array(image) / 255
    image_data = image_data.reshape((1, 28, 28, 1))
    return image_data

def predict(model, image):
    data = image_to_data(image)
    prediction = model.predict_classes(data)
    return prediction

def predict_image(model, filename):
    image = Image.open(filename)
    data = image_to_data(image)
    prediction = predict(model, data)
    return prediction

model = load_model()
print(predict_image(model, '3.png'))
print(predict_image(model, '6.png'))
print(predict_image(model, '8.png'))

Answer 1

可能的问题：

• （不是您的情况）MNIST 数据在 0 和 1 之间进行归一化，并且您的图像可能像往常一样从 0 到 255（比较 image_data.max() 和 x_train.max()）
• MNIST 数据的黑白颜色可能与您的图像相关。在确保所有内容都在 0 和 1 之间标准化后，使用工具从x_train 绘制图像并绘制image_data。看看颜色是否反转。或者尝试使用image_data = 1 - image_data 进行预测。
• 根据您加载图像的方式，您可能会对其进行转置。检查前两项后，您可以尝试image_data = numpy.swapaxes(image_data,1,2)
• 如@hi_im_vinzent 所述，过度拟合。如果前三项都ok，尝试用训练图像进行预测，看看模型是否做对了。
• 如果前面的方法都不起作用，那么您可能在保存/加载模型时遇到了问题。