使用python Pickle eoferor.pkl keras

本周我将尝试做一些分类练习，从MNIST手写检测器开始。我使用互联网上的一些文件来识别纸上的数字，但我正在尝试用神经网络训练自己的模型

我必须对数据进行pickle以格式化.pkl文件，以便识别器能够读取数据。我用keras训练我的模特，我用那个训练有素的模特。首先，我的问题是我不能pickle数据，但我必须添加函数“makekeras picklable”，然后我设法pickle

现在的问题是，当我试图加载pickle模型时，我得到了错误EOR。我认为我用泡菜的方法是正确的，但问题可能出在凯拉斯。我正在使用Ubuntu16.04和python2.7。代码文件包括在下面：

OwnClassificationtrain文件：

import types
import tempfile
import keras
import keras.models
from keras.datasets import mnist
from keras.models import Sequential
from keras.layers import Dense
from keras.layers import Dropout
from keras.layers import Flatten
from keras.layers.convolutional import Conv2D
from keras.layers.convolutional import MaxPooling2D
from keras.utils import np_utils
from keras import backend as K
K.set_image_dim_ordering('th')
# fix random seed for reproducibility
seed = 7
numpy.random.seed(seed)
# load data
(X_train, y_train), (X_test, y_test) = mnist.load_data()
# reshape to be [samples][pixels][width][height]
X_train = X_train.reshape(X_train.shape[0], 1, 28, 28).astype('float32')
X_test = X_test.reshape(X_test.shape[0], 1, 28, 28).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]

# define the larger model
def larger_model():
    # create model
    model = Sequential()
    model.add(Conv2D(30, (5, 5), input_shape=(1, 28, 28), activation='relu'))
    model.add(MaxPooling2D(pool_size=(2, 2)))
    model.add(Conv2D(15, (3, 3), activation='relu'))
    model.add(MaxPooling2D(pool_size=(2, 2)))
    model.add(Dropout(0.2))
    model.add(Flatten())
    model.add(Dense(128, activation='relu'))
    model.add(Dense(50, activation='relu'))
    model.add(Dense(num_classes, activation='softmax'))
    # Compile model
    model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])
    return model

def make_keras_picklable():
    def __getstate__(self):
        model_str = ""
        with tempfile.NamedTemporaryFile(suffix='.hdf5', delete=True) as fd:
            keras.models.save_model(self, fd.name, overwrite=True)
            model_str = fd.read()
        d = { 'model_str': model_str }
        return d

    def __setstate__(self, state):
        with tempfile.NamedTemporaryFile(suffix='.hdf5', delete=True) as fd:
            fd.write(state['model_str'])
            fd.flush()
            model = keras.models.load_model(fd.name)
        self.__dict__ = model.__dict__


    cls = keras.models.Model
    cls.__getstate__ = __getstate__
    cls.__setstate__ = __setstate__

model = larger_model()
# Fit the model
model.fit(X_train, y_train, validation_data=(X_test, y_test), epochs=1, batch_size=200)
# Final evaluation of the model
scores = model.evaluate(X_test, y_test, verbose=0)
print("Large CNN Error: %.2f%%" % (100-scores[1]*100))
make_keras_picklable()
with open('filename.pkl', 'wb') as file:
    pickle.dump(model, file, protocol=pickle.HIGHEST_PROTOCOL)

# Import the modules
import cv2
import cPickle
from skimage.feature import hog
import numpy as np

# Load the classifier
with open('traineddata.pkl','rb') as f:  #load working with originalfile with command clf=joblib.load('digits_cls.pkl') (from sklearn.externals import joblib)
    clf = cPickle.load(f)

print(clf)

# Read the input image 
im = cv2.imread("photo10.jpg")

# Convert to grayscale and apply Gaussian filtering
im_gray = cv2.cvtColor(im, cv2.COLOR_BGR2GRAY)
im_gray = cv2.GaussianBlur(im_gray, (5, 5), 0)

# Threshold the image
ret, im_th = cv2.threshold(im_gray, 100, 255, cv2.THRESH_BINARY_INV)

# Find contours in the image
image, ctrs, hier = cv2.findContours(im_th.copy(), cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)

# Get rectangles contains each contour
rects = [cv2.boundingRect(ctr) for ctr in ctrs]

# For each rectangular region, calculate HOG features and predict
# the digit using Linear SVM.
for rect in rects:
    # Draw the rectangles
    cv2.rectangle(im, (rect[0], rect[1]), (rect[0] + rect[2], rect[1] + rect[3]), (0, 255, 0), 3) 
    # Make the rectangular region around the digit
    leng = int(rect[3] * 1.6)
    pt1 = int(rect[1] + rect[3] // 2 - leng // 2)
    pt2 = int(rect[0] + rect[2] // 2 - leng // 2)
    roi = im_th[pt1:pt1+leng, pt2:pt2+leng]
    # Resize the image
    roi = cv2.resize(roi, (28, 28), interpolation=cv2.INTER_AREA)
    roi = cv2.dilate(roi, (3, 3))
    # Calculate the HOG features
    roi_hog_fd = hog(roi, orientations=9, pixels_per_cell=(14, 14), cells_per_block=(1, 1), visualise=False)
    nbr = clf.predict(np.array([roi_hog_fd], 'float64'))
    cv2.putText(im, str(int(nbr[0])), (rect[0], rect[1]),cv2.FONT_HERSHEY_DUPLEX, 2, (128, 255, 0), 3)

imS = cv2.resize(im, (960, 540))
cv2.imshow("Resulting Image with Rectangular ROIs", imS)
cv2.waitKey()

# Import the modules
from sklearn.externals import joblib
from sklearn import datasets
from skimage.feature import hog
from sklearn.svm import LinearSVC
import numpy as np
from collections import Counter

# Load the dataset
dataset = datasets.fetch_mldata("MNIST Original")

# Extract the features and labels
features = np.array(dataset.data, 'int16') 
labels = np.array(dataset.target, 'int')

# Extract the hog features
list_hog_fd = []
for feature in features:
    fd = hog(feature.reshape((28, 28)), orientations=9, pixels_per_cell=(14, 14), cells_per_block=(1, 1), visualise=False)
    list_hog_fd.append(fd)
hog_features = np.array(list_hog_fd, 'float64')

print "Count of digits in dataset", Counter(labels)

# Create an linear SVM object
clf = LinearSVC()

# Perform the training
clf.fit(hog_features, labels)

# Save the classifier
joblib.dump(clf, "digits_cls.pkl", compress=3)

识别文件：

import types
import tempfile
import keras
import keras.models
from keras.datasets import mnist
from keras.models import Sequential
from keras.layers import Dense
from keras.layers import Dropout
from keras.layers import Flatten
from keras.layers.convolutional import Conv2D
from keras.layers.convolutional import MaxPooling2D
from keras.utils import np_utils
from keras import backend as K
K.set_image_dim_ordering('th')
# fix random seed for reproducibility
seed = 7
numpy.random.seed(seed)
# load data
(X_train, y_train), (X_test, y_test) = mnist.load_data()
# reshape to be [samples][pixels][width][height]
X_train = X_train.reshape(X_train.shape[0], 1, 28, 28).astype('float32')
X_test = X_test.reshape(X_test.shape[0], 1, 28, 28).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]

# define the larger model
def larger_model():
    # create model
    model = Sequential()
    model.add(Conv2D(30, (5, 5), input_shape=(1, 28, 28), activation='relu'))
    model.add(MaxPooling2D(pool_size=(2, 2)))
    model.add(Conv2D(15, (3, 3), activation='relu'))
    model.add(MaxPooling2D(pool_size=(2, 2)))
    model.add(Dropout(0.2))
    model.add(Flatten())
    model.add(Dense(128, activation='relu'))
    model.add(Dense(50, activation='relu'))
    model.add(Dense(num_classes, activation='softmax'))
    # Compile model
    model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])
    return model

def make_keras_picklable():
    def __getstate__(self):
        model_str = ""
        with tempfile.NamedTemporaryFile(suffix='.hdf5', delete=True) as fd:
            keras.models.save_model(self, fd.name, overwrite=True)
            model_str = fd.read()
        d = { 'model_str': model_str }
        return d

    def __setstate__(self, state):
        with tempfile.NamedTemporaryFile(suffix='.hdf5', delete=True) as fd:
            fd.write(state['model_str'])
            fd.flush()
            model = keras.models.load_model(fd.name)
        self.__dict__ = model.__dict__


    cls = keras.models.Model
    cls.__getstate__ = __getstate__
    cls.__setstate__ = __setstate__

model = larger_model()
# Fit the model
model.fit(X_train, y_train, validation_data=(X_test, y_test), epochs=1, batch_size=200)
# Final evaluation of the model
scores = model.evaluate(X_test, y_test, verbose=0)
print("Large CNN Error: %.2f%%" % (100-scores[1]*100))
make_keras_picklable()
with open('filename.pkl', 'wb') as file:
    pickle.dump(model, file, protocol=pickle.HIGHEST_PROTOCOL)

# Import the modules
import cv2
import cPickle
from skimage.feature import hog
import numpy as np

# Load the classifier
with open('traineddata.pkl','rb') as f:  #load working with originalfile with command clf=joblib.load('digits_cls.pkl') (from sklearn.externals import joblib)
    clf = cPickle.load(f)

print(clf)

# Read the input image 
im = cv2.imread("photo10.jpg")

# Convert to grayscale and apply Gaussian filtering
im_gray = cv2.cvtColor(im, cv2.COLOR_BGR2GRAY)
im_gray = cv2.GaussianBlur(im_gray, (5, 5), 0)

# Threshold the image
ret, im_th = cv2.threshold(im_gray, 100, 255, cv2.THRESH_BINARY_INV)

# Find contours in the image
image, ctrs, hier = cv2.findContours(im_th.copy(), cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)

# Get rectangles contains each contour
rects = [cv2.boundingRect(ctr) for ctr in ctrs]

# For each rectangular region, calculate HOG features and predict
# the digit using Linear SVM.
for rect in rects:
    # Draw the rectangles
    cv2.rectangle(im, (rect[0], rect[1]), (rect[0] + rect[2], rect[1] + rect[3]), (0, 255, 0), 3) 
    # Make the rectangular region around the digit
    leng = int(rect[3] * 1.6)
    pt1 = int(rect[1] + rect[3] // 2 - leng // 2)
    pt2 = int(rect[0] + rect[2] // 2 - leng // 2)
    roi = im_th[pt1:pt1+leng, pt2:pt2+leng]
    # Resize the image
    roi = cv2.resize(roi, (28, 28), interpolation=cv2.INTER_AREA)
    roi = cv2.dilate(roi, (3, 3))
    # Calculate the HOG features
    roi_hog_fd = hog(roi, orientations=9, pixels_per_cell=(14, 14), cells_per_block=(1, 1), visualise=False)
    nbr = clf.predict(np.array([roi_hog_fd], 'float64'))
    cv2.putText(im, str(int(nbr[0])), (rect[0], rect[1]),cv2.FONT_HERSHEY_DUPLEX, 2, (128, 255, 0), 3)

imS = cv2.resize(im, (960, 540))
cv2.imshow("Resulting Image with Rectangular ROIs", imS)
cv2.waitKey()

# Import the modules
from sklearn.externals import joblib
from sklearn import datasets
from skimage.feature import hog
from sklearn.svm import LinearSVC
import numpy as np
from collections import Counter

# Load the dataset
dataset = datasets.fetch_mldata("MNIST Original")

# Extract the features and labels
features = np.array(dataset.data, 'int16') 
labels = np.array(dataset.target, 'int')

# Extract the hog features
list_hog_fd = []
for feature in features:
    fd = hog(feature.reshape((28, 28)), orientations=9, pixels_per_cell=(14, 14), cells_per_block=(1, 1), visualise=False)
    list_hog_fd.append(fd)
hog_features = np.array(list_hog_fd, 'float64')

print "Count of digits in dataset", Counter(labels)

# Create an linear SVM object
clf = LinearSVC()

# Perform the training
clf.fit(hog_features, labels)

# Save the classifier
joblib.dump(clf, "digits_cls.pkl", compress=3)

原始训练文件：

import types
import tempfile
import keras
import keras.models
from keras.datasets import mnist
from keras.models import Sequential
from keras.layers import Dense
from keras.layers import Dropout
from keras.layers import Flatten
from keras.layers.convolutional import Conv2D
from keras.layers.convolutional import MaxPooling2D
from keras.utils import np_utils
from keras import backend as K
K.set_image_dim_ordering('th')
# fix random seed for reproducibility
seed = 7
numpy.random.seed(seed)
# load data
(X_train, y_train), (X_test, y_test) = mnist.load_data()
# reshape to be [samples][pixels][width][height]
X_train = X_train.reshape(X_train.shape[0], 1, 28, 28).astype('float32')
X_test = X_test.reshape(X_test.shape[0], 1, 28, 28).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]

# define the larger model
def larger_model():
    # create model
    model = Sequential()
    model.add(Conv2D(30, (5, 5), input_shape=(1, 28, 28), activation='relu'))
    model.add(MaxPooling2D(pool_size=(2, 2)))
    model.add(Conv2D(15, (3, 3), activation='relu'))
    model.add(MaxPooling2D(pool_size=(2, 2)))
    model.add(Dropout(0.2))
    model.add(Flatten())
    model.add(Dense(128, activation='relu'))
    model.add(Dense(50, activation='relu'))
    model.add(Dense(num_classes, activation='softmax'))
    # Compile model
    model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])
    return model

def make_keras_picklable():
    def __getstate__(self):
        model_str = ""
        with tempfile.NamedTemporaryFile(suffix='.hdf5', delete=True) as fd:
            keras.models.save_model(self, fd.name, overwrite=True)
            model_str = fd.read()
        d = { 'model_str': model_str }
        return d

    def __setstate__(self, state):
        with tempfile.NamedTemporaryFile(suffix='.hdf5', delete=True) as fd:
            fd.write(state['model_str'])
            fd.flush()
            model = keras.models.load_model(fd.name)
        self.__dict__ = model.__dict__


    cls = keras.models.Model
    cls.__getstate__ = __getstate__
    cls.__setstate__ = __setstate__

model = larger_model()
# Fit the model
model.fit(X_train, y_train, validation_data=(X_test, y_test), epochs=1, batch_size=200)
# Final evaluation of the model
scores = model.evaluate(X_test, y_test, verbose=0)
print("Large CNN Error: %.2f%%" % (100-scores[1]*100))
make_keras_picklable()
with open('filename.pkl', 'wb') as file:
    pickle.dump(model, file, protocol=pickle.HIGHEST_PROTOCOL)

# Import the modules
import cv2
import cPickle
from skimage.feature import hog
import numpy as np

# Load the classifier
with open('traineddata.pkl','rb') as f:  #load working with originalfile with command clf=joblib.load('digits_cls.pkl') (from sklearn.externals import joblib)
    clf = cPickle.load(f)

print(clf)

# Read the input image 
im = cv2.imread("photo10.jpg")

# Convert to grayscale and apply Gaussian filtering
im_gray = cv2.cvtColor(im, cv2.COLOR_BGR2GRAY)
im_gray = cv2.GaussianBlur(im_gray, (5, 5), 0)

# Threshold the image
ret, im_th = cv2.threshold(im_gray, 100, 255, cv2.THRESH_BINARY_INV)

# Find contours in the image
image, ctrs, hier = cv2.findContours(im_th.copy(), cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)

# Get rectangles contains each contour
rects = [cv2.boundingRect(ctr) for ctr in ctrs]

# For each rectangular region, calculate HOG features and predict
# the digit using Linear SVM.
for rect in rects:
    # Draw the rectangles
    cv2.rectangle(im, (rect[0], rect[1]), (rect[0] + rect[2], rect[1] + rect[3]), (0, 255, 0), 3) 
    # Make the rectangular region around the digit
    leng = int(rect[3] * 1.6)
    pt1 = int(rect[1] + rect[3] // 2 - leng // 2)
    pt2 = int(rect[0] + rect[2] // 2 - leng // 2)
    roi = im_th[pt1:pt1+leng, pt2:pt2+leng]
    # Resize the image
    roi = cv2.resize(roi, (28, 28), interpolation=cv2.INTER_AREA)
    roi = cv2.dilate(roi, (3, 3))
    # Calculate the HOG features
    roi_hog_fd = hog(roi, orientations=9, pixels_per_cell=(14, 14), cells_per_block=(1, 1), visualise=False)
    nbr = clf.predict(np.array([roi_hog_fd], 'float64'))
    cv2.putText(im, str(int(nbr[0])), (rect[0], rect[1]),cv2.FONT_HERSHEY_DUPLEX, 2, (128, 255, 0), 3)

imS = cv2.resize(im, (960, 540))
cv2.imshow("Resulting Image with Rectangular ROIs", imS)
cv2.waitKey()

# Import the modules
from sklearn.externals import joblib
from sklearn import datasets
from skimage.feature import hog
from sklearn.svm import LinearSVC
import numpy as np
from collections import Counter

# Load the dataset
dataset = datasets.fetch_mldata("MNIST Original")

# Extract the features and labels
features = np.array(dataset.data, 'int16') 
labels = np.array(dataset.target, 'int')

# Extract the hog features
list_hog_fd = []
for feature in features:
    fd = hog(feature.reshape((28, 28)), orientations=9, pixels_per_cell=(14, 14), cells_per_block=(1, 1), visualise=False)
    list_hog_fd.append(fd)
hog_features = np.array(list_hog_fd, 'float64')

print "Count of digits in dataset", Counter(labels)

# Create an linear SVM object
clf = LinearSVC()

# Perform the training
clf.fit(hog_features, labels)

# Save the classifier
joblib.dump(clf, "digits_cls.pkl", compress=3)

photo10.jpg的链接：

---

我认为我不应该混合使用keras和sklearn，但我不知道如何替换识别文件中的sklearn函数。

现在我明白了合并sklearn和keras是不可能的，但是可以用sklearn做深度学习和神经网络吗？可以用scikit neuralnetwork做手写数字的模型吗识别器？现在我知道不可能合并sklearn和keras，但有可能用sklearn做深度学习和神经网络吗？有可能用scikit神经网络为手写数字识别器建模吗？