如何改進數字識別模型？

Question

我正在制作一個簡單的應用程序來實現數字識別。 問題在於，它在mnist數據集上效果很好，但在從Google下載的隨機圖像上卻很難預測。 我應該怎么做才能提高模型的准確性？

另一個問題：有人建議在模型中添加更多層。 如果是這樣，如何為模型添加更多圖層？

訓練模型的文件：

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
import cv2
import matplotlib.pyplot as plt
from keras.models import load_model
import pickle
import h5py
import numpy as np
from keras.callbacks import ModelCheckpoint
batch_size = 128
num_classes = 10
epochs = 12

# input image dimensions
img_rows, img_cols = 28, 28

model=load_model('my_model.h5')



the data, split between train and test sets
(x_train, y_train), (x_test, y_test) = mnist.load_data()
print('initial shape')
print('x_test ',x_test.shape)
print('y_test ',y_test.shape)


# print(x_test);
# print(y_test.shape)

if K.image_data_format() == 'channels_first':
    print('reshape1')
    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:
    print('reshape2')
    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_test shape: ' , x_test.shape)
print(x_train.shape[0], 'train samples')
print(x_test.shape[0], 'test samples')

print('x_test final : ')
print(x_test)

# 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(0.10))
model.add(Flatten())
model.add(Dense(128, activation='relu'))
model.add(Dropout(0.20))
model.add(Dense(256,activation='relu'))
model.add(Dropout(0.40))

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))

model.save('my_model.h5')
score = model.evaluate(x_test, y_test, verbose=0)


# print(x_test.shape)
# print('\n')
# print(y_test.shape)

print('Test loss:', score[0])
print('Test accuracy:', score[1])

以下代碼用於使用我自己的圖像測試模型

image = cv2.imread("2.jpg")
img_rows, img_cols = 28, 28

x_test1 = cv2.resize(image, (28, 28)) 

x_test1 = cv2.cvtColor(x_test1,cv2.COLOR_RGB2GRAY)


print(x_test1.shape)

if K.image_data_format() == 'channels_first':
    print('reshape1')
    x_test1 = x_test1.reshape(1, 1, img_rows, img_cols)
    input_shape = (1, img_rows, img_cols)

else:
    print('reshape2')
    x_test1 = x_test1.reshape(1, img_rows, img_cols, 1)
    input_shape = (img_rows, img_cols, 1)

x_test1 = x_test1.astype('float32')
x_test1 /= 255
y_test1 = np.array([[ 0., 0., 1., 0., 0., 0., 0., 0., 0., 0.]])
score = model.evaluate(x_test1, y_test1, verbose=0)
print('done')
print('score of image = ')
print(score[1])
print(score[0])
score=model.predict_classes(x_test1)
print(score)

以下代碼用於加載先前訓練的模型，並從先前的檢查點繼續對其進行訓練。 如果有任何錯誤，請提出建議。

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'])
filepath="my_model.h5"
checkpoint = ModelCheckpoint(filepath, monitor='acc', verbose=1, save_best_only=True, mode='max')
callbacks_list = [checkpoint]

score=model.fit(x_test1, y_test1,epochs=12, batch_size=128, callbacks=callbacks_list, verbose=0)


new_model = load_model("my_model.h5")
np.testing.assert_allclose(model.predict(x_test1),
                new_model.predict(x_test1),
                1e-5)


checkpoint = ModelCheckpoint(filepath, monitor='loss', verbose=1, save_best_only=True, mode='min')
callbacks_list = [checkpoint]
new_model.fit(x_train, y_train, epochs=12, batch_size=128, callbacks=callbacks_list)

上面的代碼是否會導致模型過度擬合？ 如果是，我如何使它更有效，以便能夠預測任何類型的數據？ 需要幫助！！

Answer 1

您不會對這些結果感到驚訝，因為您在一個數據域上訓練了模型，但在另一個數據域上進行了測試。 是的，如果您的網絡設計更好，則性能可能會略有提高，但是這種差距仍然存在。

為了縮小這一差距，您可以改善以下方面：

1. 改善您的訓練數據 ：（a）使用更真實的數字數據訓練模型，例如，街景房號（ SVHN ）數據集或char74K數據集中的數字，以及（b）使用更好的數據訓練模型增強技術，例如，將數字樣本與隨機背景圖像混合。
2. 調整您的測試數據 ：對測試樣本進行預處理，以使其看起來與訓練數據中的樣本相似，例如，在將樣本饋送到網絡進行預測之前，對測試樣本進行二進制編碼，使其看起來與MNIST相似。
3. 通過顯式考慮實際數據的變化來改進模型 ：例如，如果您認為rotation測試數據會降低模型性能，則可以通過在預測數字旋轉中添加輔助任務來考慮模型訓練中的這一因素； 或者您認為好的模型應該只預測數字，而不能預測該訓練樣本所屬的數據集，那么您可以添加對抗性任務，以迫使網絡忘記此信息。