改善由mnist数据集训练的神经网络的真实结果

Question

我已经使用mnist数据集使用keras构建了一个神经网络，现在我正尝试在实际手写数字的照片上使用它。当然，我并不期望结果会是完美的，但是我目前得到的结果仍有很大的改进空间。首先，我用一些用最清晰的笔迹写的个人数字照片进行测试。它们是正方形的，并且具有与mnist数据集中的图像相同的尺寸和颜色。它们被保存在名为individual_test的文件夹中，例如：7（2）_digit.jpg。网络通常会非常确定错误的结果，下面我举一个例子：我得到的这张图片的结果如下：

result:  3 . probabilities:  [1.9963557196245318e-10, 7.241294497362105e-07, 0.02658148668706417, 0.9726449251174927, 2.5416460047722467e-08, 2.6078915027483163e-08, 0.00019745019380934536, 4.8302300825753264e-08, 0.0005754049634560943, 2.8358477788259506e-09]

因此，网络上有97％的人确定这是3，而这并不是唯一的情况。在38张照片中，只有16张被正确识别。令我感到震惊的是，尽管网络离正确的结果再远了，但它仍然对结果有把握。我该怎么做才能提高性能？我可以更好地准备图像吗？还是应该将自己的图像添加到训练数据中？如果是这样，我该怎么做？我是一个关于机器学习的初学者，希望您能为我提供帮助。预先谢谢你。

这是我的代码：

# import keras and the MNIST dataset
from tensorflow.keras.datasets import mnist
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense
from keras.utils import np_utils
# numpy is necessary since keras uses numpy arrays
import numpy as np

# imports for pictures
import PIL

# imports for tests
import random
import os

class mnist_network():
    def __init__(self):
        """ load data, create and train model """
        # load data
        (X_train, y_train), (X_test, y_test) = mnist.load_data()
        # flatten 28*28 images to a 784 vector for each image
        num_pixels = X_train.shape[1] * X_train.shape[2]
        X_train = X_train.reshape((X_train.shape[0], num_pixels)).astype('float32')
        X_test = X_test.reshape((X_test.shape[0], num_pixels)).astype('float32')
        # normalize inputs from 0-255 to 0-1
        X_train = X_train / 255
        X_test = X_test / 255
        # one hot encode outputs
        y_train = np_utils.to_categorical(y_train)
        y_test = np_utils.to_categorical(y_test)
        num_classes = y_test.shape[1]


        # create model
        self.model = Sequential()
        self.model.add(Dense(num_pixels, input_dim=num_pixels, kernel_initializer='normal', activation='relu'))
        self.model.add(Dense(num_classes, kernel_initializer='normal', activation='softmax'))
        # Compile model
        self.model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])

        # train the model
        self.model.fit(X_train, y_train, validation_data=(X_test, y_test), epochs=10, batch_size=200, verbose=2)

        self.train_img = X_train
        self.train_res = y_train
        self.test_img = X_test
        self.test_res = y_test


    def predict_result(self, img, num_pixels = None, show=False):
        """ predicts the number in a picture (vector) """
        assert type(img) == np.ndarray and img.shape == (784,)

        """if show:
            # show the picture!!!! some problem here
            plt.imshow(img, cmap='Greys')
            plt.show()"""

        num_pixels = img.shape[0]
        # the actual number
        res_number = np.argmax(self.model.predict(img.reshape(-1,num_pixels)), axis = 1)
        # the probabilities
        res_probabilities = self.model.predict(img.reshape(-1,num_pixels))

        return (res_number[0], res_probabilities.tolist()[0])    # we only need the first element since they only have one



    def prepare_image(self, img):
        """ prepares the partial images used in partial_img_rec by transforming them
            into numpy arrays that the network will be able to process """
        # convert to greyscale
        img = img.convert("L")
        # rescale image to 28 *28 dimension
        img = img.resize((28,28), PIL.Image.ANTIALIAS)
        # inverse colors since the training images have a black background
        img =  PIL.ImageOps.invert(img)
        # transform to vector
        img = np.asarray(img, "float32")
        img = img / 255.
        img[img < 0.5] = 0.
        # flatten image to 28*28 = 784 vector
        num_pixels = img.shape[0] * img.shape[1]
        img = img.reshape(num_pixels)


        return img


    def partial_img_rec(self, image, upper_left, lower_right, results=[], show = False):
        """ partial is a part of an image """
        left_x, left_y = upper_left
        right_x, right_y = lower_right

        print("current test part: ", upper_left, lower_right)
        print("results: ", results)
        # condition to stop recursion: we've reached the full width of the picture
        width, height = image.size
        if right_x > width:
            return results

        partial = image.crop((left_x, left_y, right_x, right_y))
        if show:
            partial.show()
        partial = self.prepare_image(partial)

        step = height // 10
        # is there a number in this part of the image? 

        res, prop = self.predict_result(partial)
        print("result: ", res, ". probabilities: ", prop)
        # only count this result if the network is at least 50% sure
        if prop[res] >= 0.5:        
            results.append(res)
            # step is 80% of the partial image's size (which is equivalent to the original image's height) 
            step = int(height * 0.8)
            print("found valid result")
        else:
            # if there is no number found we take smaller steps
            step = height // 20 
        print("step: ", step)
        # recursive call with modified positions ( move on step variables )
        return self.partial_img_rec(image, (left_x + step, left_y), (right_x + step, right_y), results = results)

    def individual_digits(self, img):
        """ uses partial_img_rec to predict individual digits in square images """
        assert type(img) == PIL.JpegImagePlugin.JpegImageFile or type(img) == PIL.PngImagePlugin.PngImageFile or type(img) == PIL.Image.Image

        return self.partial_img_rec(img, (0,0), (img.size[0], img.size[1]), results=[])

    def test_individual_digits(self):
        """ test partial_img_rec with some individual digits (shape: square) 
            saved in the folder 'individual_test' following the pattern 'number_digit.jpg' """
        cnt_right, cnt_wrong = 0,0
        folder_content = os.listdir(".\individual_test")

        for imageName in folder_content:
            # image file must be a jpg or png
            assert imageName[-4:] == ".jpg" or imageName[-4:] == ".png"
            correct_res = int(imageName[0])
            image = PIL.Image.open(".\\individual_test\\" + imageName).convert("L")
            # only square images in this test
            if image.size[0]  != image.size[1]:
                print(imageName, " has the wrong proportions: ", image.size,". It has to be a square.")
                continue 
            predicted_res = self.individual_digits(image)

            if predicted_res == []:
                print("No prediction possible for ", imageName)
            else:
                predicted_res = predicted_res[0]

            if predicted_res != correct_res:
                print("error in partial_img-rec! Predicted ", predicted_res, ". The correct result would have been ", correct_res)
                cnt_wrong += 1
            else:
                cnt_right += 1
                print("correctly predicted ",imageName)
        print(cnt_right, " out of ", cnt_right + cnt_wrong," digits were correctly recognised. The success rate is therefore ", (cnt_right / (cnt_right + cnt_wrong)) * 100," %.")

    def multiple_digits(self, img):
        """ takes as input an image without unnecessary whitespace surrounding the digits """

        #assert type(img) == myImage
        width, height = img.size
        # start with the first square part of the image
        res_list = self.partial_img_rec(img, (0,0),(height ,height), results = [])
        res_str = ""
        for elem in res_list:
            res_str += str(elem)
        return res_str

    def test_multiple_digits(self):
        """ tests the function 'multiple_digits' using some images saved in the folder 'multi_test'.
            These images contain multiple handwritten digits without much whitespac surrounding them.
            The correct solutions are saved in the files' names followed by the characte '_'. """

        cnt_right, cnt_wrong = 0,0
        folder_content = os.listdir(".\multi_test")
        for imageName in folder_content:
            # image file must be a jpg or png
            assert imageName[-4:] == ".jpg" or imageName[-4:] == ".png"            
            image = PIL.Image.open(".\\multi_test\\" + imageName).convert("L")

            correct_res = imageName.split("_")[0]
            predicted_res = self.multiple_digits(image)
            if correct_res == predicted_res:
                cnt_right += 1
            else:
                cnt_wrong += 1
                print("Error in multiple_digits! The network predicted ", predicted_res, " but the correct result would have been ", correct_res)

        print("The network predicted correctly ", cnt_right, " out of ", cnt_right + cnt_wrong, " pictures. That's a success rate of ", cnt_right / (cnt_right + cnt_wrong) * 100, "%.")

network = mnist_network()
# 7(2).digit.jpg is the image shown above
network.individual_digits(PIL.Image.open(".\individual_test\\7(2)_digit.jpg"))

Answer 1

您在MNIST数据集上的测试分数是多少？我想到的一件事是您的图像缺少阈值，

阈值处理是将某个像素以下的像素值设为零，请参阅OpenCV阈值示例，您可能需要使用反阈值并再次检查结果。

做，请告知是否有进展。

Answer 2

您的主要问题是，您正在测试的图像与MNIST图像不同，可能是由于您已经完成了准备的图像，您可以在将prepare_image应用到它。

Answer 3

您有三个选择可以在此特定任务中获得更好的性能：

1. 使用卷积网络，因为它在处理带有空间数据的任务（例如图像）中表现更好，并且是更具生成性的分类器（例如此）。
2. 使用或创建和/或生成更多类型的图片和培训网络，并与他们一起使用网络来学习它们。
3. Preprocess您的图像可以更好地与原始MNIST图像对齐。