In [6]:

    

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.utils import np_utils
from keras import backend as K
from keras.callbacks import ModelCheckpoint

import pickle

print "using ordering:", K.image_dim_ordering()


    

    




using ordering: tf

In [7]:

    

# load data from memory

import pickle

pickle_file = '-data.pickle'

with open(pickle_file, 'rb') as f:
    save = pickle.load(f)
    X = save['X']
    y = save['y']
    del save  # hint to help gc free up memory


    

In [8]:

    

# number of classes
num_classes = 2

# image dimensions
img_rows, img_cols = X.shape[1], X.shape[2]

if K.image_dim_ordering() == 'th':
    X = X.reshape(X.shape[0], 3, img_rows, img_cols)
    input_shape = (3, img_rows, img_cols)
else:
    X = X.reshape(X.shape[0], img_rows, img_cols, 3)
    input_shape = (img_rows, img_cols, 3)

y = np_utils.to_categorical(y, num_classes)

print X.shape
print y.shape


    

    




(5726, 32, 32, 3)
(5726, 2)

In [13]:

    

# preview one sample from the reloaded X dataset to make sure nothing happened along the way

%matplotlib inline
from matplotlib.pyplot import imshow
import matplotlib.pyplot as plt

img_num = 0

if K.image_dim_ordering() == 'th':
    img = X[img_num].reshape(img_rows, img_cols, 3)

print img.shape
imshow(img, cmap = plt.get_cmap('gray'), vmin = 0, vmax = 1,  interpolation='nearest')


    

    




---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
<ipython-input-13-61905c63f272> in <module>()
     10     img = X[img_num].reshape(img_rows, img_cols, 3)
     11 
---> 12 print img.shape
     13 imshow(img, cmap = plt.get_cmap('gray'), vmin = 0, vmax = 1,  interpolation='nearest')

NameError: name 'img' is not defined

In [14]:

    

# model hyperparameters
batch_size = 32
nb_epoch = 10

# network architecture
patch_size_1 = 3
patch_size_2 = 3
patch_size_3 = 3

depth_1 = 32
depth_2 = 64
depth_3 = 128

pool_size = 2

num_hidden_1 = 256
num_hidden_2 = 512

dropout = 0.5


    

In [ ]:

    

model = Sequential()

model.add(Convolution2D(depth_1, patch_size_1, patch_size_1,
                        border_mode='valid',
                        input_shape=input_shape))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(pool_size, pool_size)))

model.add(Convolution2D(depth_2, patch_size_2, patch_size_2,
                        border_mode='valid'))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(pool_size, pool_size)))

model.add(Convolution2D(depth_3, patch_size_3, patch_size_3,
                        border_mode='valid'))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(pool_size, pool_size)))

model.add(Flatten())

model.add(Dense(num_hidden_1))
model.add(Activation('relu'))
model.add(Dropout(dropout))

model.add(Dense(num_hidden_2))
model.add(Activation('relu'))
model.add(Dropout(dropout))

model.add(Dense(num_classes))

model.add(Activation('softmax'))


    

In [ ]:

    

checkpoint_name = "-model.hdf5"
checkpointer = ModelCheckpoint(checkpoint_name, verbose=0, save_best_only=True)

model.compile(loss='categorical_crossentropy', optimizer='adadelta', metrics=['accuracy'])


    

In [12]:

    

history = model.fit(X, y, validation_split=0.25, batch_size=batch_size, nb_epoch=nb_epoch,
          verbose=1, callbacks=[checkpointer])


    

    




---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
<ipython-input-12-81b3ecf08bc3> in <module>()
----> 1 history = model.fit(X, y, validation_split=0.25, batch_size=batch_size, nb_epoch=nb_epoch,
      2           verbose=1, callbacks=[checkpointer])

NameError: name 'model' is not defined

In [ ]: