In [2]:

    

%matplotlib inline

'''
This code was modified from: https://github.com/fchollet/keras/blob/master/examples/mnist_cnn.py

Train a simple convnet on the MNIST dataset.
Run on GPU: THEANO_FLAGS=mode=FAST_RUN,device=gpu,floatX=float32 python mnist_cnn.py
Get 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.
'''
import os

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.convolutional import Convolution2D, MaxPooling2D
from keras.utils import np_utils
from keras.regularizers import l2

from agnez.app_callbacks import LossPlot, VisualizeConvWeights


    

    




Using Theano backend.

In [3]:

    

batch_size = 128
nb_classes = 10
nb_epoch = 12

# input image dimensions
img_rows, img_cols = 28, 28
# number of convolutional filters to use
nb_filters = 32
# size of pooling area for max pooling
nb_pool = 2
# convolution kernel size
nb_conv = 7

# the data, shuffled and split between tran and test sets
(X_train, y_train), (X_test, y_test) = mnist.load_data()

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')

# 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, nb_conv, nb_conv,
                        border_mode='valid', W_regularizer=l2(.01),
                        input_shape=(1, img_rows, img_cols)))
model.add(Activation('relu'))
#model.add(MaxPooling2D(pool_size=(nb_pool, nb_pool)))
#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'))


    

    




X_train shape: (60000, 1, 28, 28)
60000 train samples
10000 test samples

In [4]:

    

model.compile(loss='categorical_crossentropy', optimizer='adadelta')


    

    




WARNING (theano.gof.compilelock): Overriding existing lock by dead process '27820' (I am process '28628')
WARNING:theano.gof.compilelock:Overriding existing lock by dead process '27820' (I am process '28628')

In [5]:

    

# here we are using the default values for `name`, `description` and `app_url`

loss_plot = LossPlot(name='Loss plot',
                     description='train (blue) and validation (green) learning curves',
                     position=0, app_url='http://localhost:3000/api/v1/values')


    

In [6]:

    

# static_path = '/Full/path/to/agnez_app
static_path = '/Users/eder/js/agnez_dash'
conv_weights = VisualizeConvWeights(weights=model.layers[0].W, static_path=static_path, name='Conv weights',
                                    description='weights of convolutional layer', position=1,
                                    app_url='http://localhost:3000/api/v1/values')


    

In [ ]:

    

model.fit(X_train, Y_train, batch_size=batch_size, nb_epoch=nb_epoch,
          show_accuracy=True, verbose=1, validation_data=(X_test, Y_test),
          callbacks=[loss_plot, conv_weights])