keras.ipynb

Kernel: Python 2 (SageMath)

from keras.datasets import mnist

(X_train, y_train), (X_test, y_test) = mnist.load_data()

'''Trains a simple deep NN on the MNIST dataset.   
Gets to 98.40% test accuracy after 20 epochs 
(there is *a lot* of margin for parameter tuning). 
2 seconds per epoch on a K520 GPU. 
''' 

from __future__ import print_function 
import numpy as np 
np.random.seed(1337)  # for reproducibility 

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

batch_size = 64
nb_classes = 10 
nb_epoch = 20

# the data, shuffled and split between train and test sets 
(X_train, y_train), (X_test, y_test) = mnist.load_data() 
 
X_train = X_train.reshape(60000, 784) 
X_test = X_test.reshape(10000, 784) 
X_train = X_train.astype('float32') 
X_test = X_test.astype('float32') 
X_train /= 255 
X_test /= 255 
print(X_train.shape[0], 'train samples') 
print(X_test.shape[0], 'test samples') 
 
 
# convert class vectors to binary class matrices 
Y_train = np_utils.to_categorical(y_train, nb_classes) 
Y_test = np_utils.to_categorical(y_test, nb_classes) 
 
model = Sequential() 



model.add(Dense(100, input_shape=(784,))) 
model.add(Activation('relu')) 
model.add(Dense(input_dim =100, output_dim =10))
model.add(Activation('softmax'))

sgd = SGD(lr=0.1, decay=0, momentum=0.0, nesterov=False)



model.summary() 


#D, H, C = 1000, 100, 10
#model.add(Dense(input_dim =D, output_dim = H))
# model.add(Dense(input_dim =H, output_dim = C))


model.compile(loss='categorical_crossentropy', 
               optimizer=sgd, 
               metrics=['accuracy']) 
 
history = model.fit(X_train, Y_train, 
                     batch_size=batch_size, nb_epoch=nb_epoch, 
                     verbose=0, validation_data=(X_test, Y_test)) 
score = model.evaluate(X_test, Y_test, verbose=0) 
print('Test score:', score[0]) 
print('Test accuracy:', score[1]) 

60000 train samples
10000 test samples
____________________________________________________________________________________________________
Layer (type)                     Output Shape          Param #     Connected to                     
====================================================================================================
dense_5 (Dense)                  (None, 100)           78500       dense_input_3[0][0]              
____________________________________________________________________________________________________
activation_5 (Activation)        (None, 100)           0           dense_5[0][0]                    
____________________________________________________________________________________________________
dense_6 (Dense)                  (None, 10)            1010        activation_5[0][0]               
____________________________________________________________________________________________________
activation_6 (Activation)        (None, 10)            0           dense_6[0][0]                    
====================================================================================================
Total params: 79,510
Trainable params: 79,510
Non-trainable params: 0
____________________________________________________________________________________________________
Test score: 0.0688523479761
Test accuracy: 0.9777

'''Trains a simple convnet on the MNIST dataset. 
  
 Gets to 99.25% test accuracy after 12 epochs 
 (there is still a lot of margin for parameter tuning). 
 16 seconds per epoch on a GRID K520 GPU. 
 ''' 
 
 
from __future__ import print_function 
import numpy as np 
np.random.seed(1337)  # for reproducibility 
 
 
from keras.datasets import mnist 
from keras.models import Sequential 
from keras.layers import Dense, Dropout, Activation, Flatten 
from keras.layers import Convolution2D, MaxPooling2D 
from keras.optimizers import SGD, Adam, RMSprop 
from keras.utils import np_utils 
from keras import backend as K 
 
 
batch_size = 128 
nb_classes = 10
nb_epoch = 12
#--------------------------
# NIELSEN  batch_size = 10
# NIELSEN 
#nb_epoch = 60
 
# input image dimensions 
img_rows, img_cols = 28, 28 
# number of convolutional filters to use
#nb_filters = 32 
# NIELSEN 
nb_filters = 20
# size of pooling area for max pooling 
pool_size = (2, 2) 
# convolution kernel size 
#kernel_size = (3, 3) 
# NIELSEN 
kernel_size = (5, 5)



 
# the data, shuffled and split between train and test sets 
(X_train, y_train), (X_test, y_test) = mnist.load_data() 
 
 
if K.image_dim_ordering() == 'th': 
     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: 
     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_train.shape[0], 'train samples') 
print(X_test.shape[0], 'test samples') 
 
 
# convert class vectors to binary class matrices 
Y_train = np_utils.to_categorical(y_train, nb_classes) 
Y_test = np_utils.to_categorical(y_test, nb_classes) 
 
 
model = Sequential() 
 
 
#model.add(Convolution2D(nb_filters, kernel_size[0], kernel_size[1], 
#                         border_mode='valid', 
#                         input_shape=input_shape)) 
#model.add(Activation('relu')) 
#model.add(Convolution2D(nb_filters, kernel_size[0], kernel_size[1])) 
#model.add(Activation('relu')) 
#model.add(MaxPooling2D(pool_size=pool_size)) 
#model.add(Dropout(0.25)) 
#model.add(Flatten()) 
#model.add(Dense(128)) 
#model.add(Activation('relu')) 
#model.add(Dropout(0.5)) 
#model.add(Dense(nb_classes)) 
#model.add(Activation('softmax')) 
 

    
    
model.add(Convolution2D(nb_filters, kernel_size[0], kernel_size[1], 
                         border_mode='valid', 
                         input_shape=input_shape)) 
model.add(Activation('sigmoid')) 
model.add(MaxPooling2D(pool_size=pool_size)) 
model.add(Flatten()) 
#model.add(Dense(20*12*12)) 
model.add(Dense(input_dim =20*12*12, output_dim = 100))
model.add(Activation('sigmoid'))
          
model.add(Dense(input_dim =100, output_dim = nb_classes)) 
model.add(Activation('softmax'))    

# model.compile(loss='categorical_crossentropy', optimizer='adadelta', metrics=['accuracy']) 
sgd = SGD(lr=0.1, decay=0, momentum=0.0, nesterov=False)


model.summary() 

model.compile(loss='categorical_crossentropy', 
               optimizer=sgd, 
               metrics=['accuracy']) 
 
model.fit(X_train, Y_train, batch_size=batch_size, nb_epoch=nb_epoch, 
           verbose=0, validation_data=(X_test, Y_test)) 
score = model.evaluate(X_test, Y_test, verbose=0) 
print('Test score:', score[0]) 
print('Test accuracy:', score[1])