machine-learning - keras 神经网络为每个手写数字预测相同的数字

Question

我是机器学习新手，所以作为第一个项目，我尝试基于 mnist 数据集构建一个手写数字识别神经网络，当我使用数据集本身提供的测试图像对其进行测试时，它似乎可以工作非常好(这就是函数 test_predict 的用途)。现在我想更进一步，让网络识别我拍摄的一些实际手写数字。函数 partial_img_rec 接受包含多个数字的图像，并且将由 multiple_digits 调用。我知道我在这里使用递归可能看起来很奇怪，并且我确信有一些更有效的方法可以做到这一点，但这不是问题。为了测试 partial_img_rec，我提供了一些存储在文件夹 .\individual_test 中的单个数字的照片，它们看起来都像这样:

问题是:我的神经网络对每一张测试图像的预测都是“5”。无论实际显示的数字是什么，概率始终约为 22%。我完全明白为什么结果不如 mnist 数据集的测试图像所取得的结果那么好，但我当然没有想到这一点。您知道为什么会发生这种情况吗？欢迎任何建议。预先感谢您。

这是我的代码(已编辑，现在可以运行):

# 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
from PIL import Image
from PIL import ImageOps

# 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 test_all(self):
        """ evaluates the success rate using all the test data """
        scores = self.model.evaluate(self.test_img, self.test_res, verbose=0)
        print("Baseline Error: %.2f%%" % (100-scores[1]*100))

    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 test_predict(self, amount_test = 100):
        """ test some random numbers from the test part of the data set """
        assert type(amount_test) == int and amount_test <= 10000
        cnt_right = 0
        cnt_wrong = 0

        for i in range(amount_test):
            ind = random.randrange(0,10000) # there are 10000 images in the test part of the data set
            """ correct_res is the actual result stored in the data set 
                It's represented as a list of 10 elements one of which being 1, the rest 0 """
            correct_list = self.test_res.tolist()
            correct_list = correct_list[ind] # the correct sublist
            correct_res = correct_list.index(1.0)


            predicted_res = self.predict_result(self.test_img[ind])[0]

            if correct_res != predicted_res:
                cnt_wrong += 1
                print("Error in predict ! \
                      index = ", ind, " predicted result = ", predicted_res, " correct result = ", correct_res)
            else:
                cnt_right += 1

        print("The machine predicted correctly ",cnt_right," out of ",amount_test," examples. That is a success rate of ", (cnt_right/amount_test)*100,"%.")

    def partial_img_rec(self, image, upper_left, lower_right, results=[]):
        """ 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))
        # rescale image to 28 *28 dimension
        partial = partial.resize((28,28), Image.ANTIALIAS)

        partial.show()
        # transform to vector
        partial =  ImageOps.invert(partial)
        partial = np.asarray(partial, "float32")
        partial = partial / 255.
        partial[partial < 0.5] = 0.
        # flatten image to 28*28 = 784 vector
        num_pixels = partial.shape[0] * partial.shape[1]
        partial = partial.reshape(num_pixels)

        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 >= 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 test_individual_digits(self):
        """ test partial_img_rec with some individual digits (square shaped images) 
            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 = 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.partial_img_rec(image, (0,0), (image.size[0], image.size[1]), results=[])

            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 quadratic part of the image
        res_list = self.partial_img_rec(img, (0,0),(height ,height))
        res_str =""
        for elem in res_list:
            res_str += str(elem)
        return res_str




network = mnist_network()    
network.test_individual_digits()        

编辑

@Geecode 的回答非常有帮助，网络现在可以正确预测一些图片，包括上面显示的图片。但总体成功率低于50%。您有什么改进的想法吗？

返回不良结果的图像示例:

Answer 1

您的图像本身没有问题，您的模型可以正确地对其进行分类。

问题是您创建了 Floor Division在你的部分上:

partial = partial // 255

结果总是0。因此你总是得到黑色图像。

您必须进行“正常”划分和一些准备，因为您的模型是在黑色即 0. 值像素背景负图像上进行训练的:

# transform to vector
partial = ImageOps.invert(partial)
partial = np.asarray(partial, "float32")
partial = partial / 255.
partial[partial < 0.5] = 0.

之后您的模型将正确分类:

输出:

result:  1 . probabilities:  [0.000431705528171733, 0.7594985961914062, 0.0011404436081647873, 0.00018972357793245465, 0.03162384033203125, 0.008697531186044216, 0.0014472954208031297, 0.18429973721504211, 0.006838776171207428, 0.005832481198012829]
found valid result

请注意，您当然可以进行图像准备，但这不是本答案的目的。

更新:我关于如何在此任务中获得更好性能的详细答案，请参阅here .