CNN模型给出了错误的预测

Question

我目前正致力于区域语言的手写数字识别。目前，我专注于Oriya。我通过CNN模型测试MNIST数据集，我试图在我的Oriya数据集上应用该模型。模特表现不佳。它给出了错误的预测。我有4971个样本的数据集。 如何提高准确性？ 这是我的代码：

from keras.models import Sequential
from keras.layers.core import Dense, Dropout, Activation, Flatten  
from keras.layers.convolutional import Convolution2D, MaxPooling2D
from keras.optimizers import SGD,RMSprop,adam
from keras.utils import np_utils

import numpy as np
import matplotlib.pyplot as plt
import matplotlib
import os
import theano
from PIL import Image
from numpy import *
# SKLEARN
from sklearn.utils import shuffle
from sklearn.cross_validation import train_test_split



# fix random seed for reproducibility
seed = 7
numpy.random.seed(seed)



# input image dimensions
img_rows, img_cols = 28, 28

# number of channels
img_channels = 1


path2 = '/home/saumya/Desktop/Oriya/p'    #path of folder of images


imlist = os.listdir(path2)


im1 = array(Image.open('/home/saumya/Desktop/Oriya/p' + '/'+ imlist[0]))    # open one image to get size
m,n = im1.shape[0:2] # get the size of the images
imnbr = len(imlist) # get the number of images


# create matrix to store all flattened images
immatrix = array([array(Image.open('/home/saumya/Desktop/Oriya/p' + '/'+  im2)).flatten()
           for im2 in imlist],'f')

label=np.ones((num_samples,),dtype = int)
label[1:503]=0
label[503:1000]=1
label[1000:1497]=2
label[1497:1995]=3
label[1995:2493]=4
label[2493:2983]=5
label[2983:3483]=6
label[3483:3981]=7
label[3981:4479]=8
label[4479:4972]=9

print(label[1000])
data,Label = shuffle(immatrix,label, random_state=2)
train_data = [data,Label]

img=immatrix[2496].reshape(img_rows,img_cols)
plt.imshow(img)
plt.show()



(X, y) = (train_data[0],train_data[1])



X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=4)


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)

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')



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')



y_train = np_utils.to_categorical(y_train)
y_test = np_utils.to_categorical(y_test)
num_classes = y_test.shape[1]


def baseline_model():
# create model
model = Sequential()
model.add(Conv2D(32, (3,3), input_shape=(1, 28, 28), activation='relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.2))

#model.add(Conv2D(64, (5, 5), input_shape=(1, 10, 10), activation='relu'))
#model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Flatten())
model.add(Dense(128, activation='relu'))
model.add(Dense(num_classes, activation='softmax', name = 'first_dense_layer'))
# Compile model
model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])
return model



# build the model
model = baseline_model()
# Fit the model
hist=model.fit(X_train, y_train, validation_data=(X_test, y_test), epochs=30, batch_size=100, verbose=2)
# Final evaluation of the model
scores = model.evaluate(X_test, y_test, verbose=0)
print("CNN Error: %.2f%%" % (100-scores[1]*100))



score = model.evaluate(X_test, y_test, verbose=0)
print('Test Loss:', score[0])
print('Test accuracy:', score[1])

test_image = X_test[0:1]
print (test_image.shape)

print(model.predict(test_image))
print(model.predict_classes(test_image))
print(y_test[0:1])




# 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', name='first_dense_layer'))
model.add(Dense(num_classes, activation='softmax'))
# Compile model
model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])
return model


# build the model
model = larger_model()
# Fit the model
model.fit(X_train, y_train, validation_data=(X_test, y_test), epochs=10, 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))

我试图使用opencv调整我的模型大小，它产生以下错误： /root/mc-x64-2.7/conda-bld/opencv-3_1482254119970/work/opencv-3.1.0/modules/imgproc/src/imgwarp.cpp:3229：错误：（-215）ssize.area（）> 0在函数调整大小

Answer 1

如何提高准确性？

有点难以从您发布的内容中给出详细的答案，并且没有看到一些数据样本，但仍会尝试对此进行抨击。我能看到的可能有助于提高准确性的是：

1. 获取更多数据。在深度学习中，通常使用大量数据，并且在添加更多数据时模型几乎总是会改进。如果您无法获得新数据，可以尝试通过添加噪声或类似修改来生成更多样本。
2. 我看到你的模型训练目前有30和10个时代。我建议你增加时代数，这样你的模型就有更多时间收敛。这也是大多数时候在一定程度上提高性能。
3. 我还看到您的模型上的批量大小为100和200。您可以尝试减少培训过程的批量大小，因此您的培训会在每个时期执行更多次的渐变更新（请记住，您甚至可以使用batch_size=1为每个样本而不是批次升级模型）。
4. 或者，您可以尝试迭代地增加架构的复杂性和层次，并比较您的性能。最好从简单的模型开始，训练和测试，然后添加图层和节点，直到您对结果满意为止。我也看到你尝试过混合卷积和非卷积方法;在增加架构的复杂性之前，您可以尝试从其中一种方法开始。