In [65]:

    

#imports
# Set Up image Ordering as theano
from keras.models import Sequential
from keras.layers import Dense
from keras.layers import Reshape
from keras.layers.core import Activation
from keras.layers.normalization import BatchNormalization
from keras.layers.convolutional import UpSampling2D
from keras.layers.convolutional import Convolution2D, MaxPooling2D
from keras.layers.core import Flatten
from keras.optimizers import SGD
from keras.datasets import mnist
import numpy as np
from PIL import Image
import argparse
import math


    

In [67]:

    

import keras.backend as k
k.set_image_dim_ordering('th')
import numpy as np
import matplotlib.pyplot as plt
import matplotlib.image as img
from IPython.display import SVG
from keras.utils.vis_utils import model_to_dot


    

In [68]:

    

# Define the Networks

def generator_model():
    model = Sequential()
    model.add(Dense(input_dim=100, output_dim=1024))
    model.add(Activation('tanh'))
    model.add(Dense(128*7*7))
    model.add(BatchNormalization())
    model.add(Activation('tanh'))
    model.add(Reshape((128, 7, 7), input_shape=(128*7*7,)))
    model.add(UpSampling2D(size=(2, 2)))
    model.add(Convolution2D(64, 5, 5, border_mode='same'))
    model.add(Activation('tanh'))
    model.add(UpSampling2D(size=(2, 2)))
    model.add(Convolution2D(1, 5, 5, border_mode='same'))
    model.add(Activation('tanh'))
    return model

def discriminator_model():
    model = Sequential()
    model.add(Convolution2D(64, 5, 5,border_mode='same',input_shape=(1, 28, 28)))
    model.add(Activation('tanh'))
    model.add(MaxPooling2D(pool_size=(2, 2)))
    model.add(Convolution2D(128, 5, 5))
    model.add(Activation('tanh'))
    model.add(MaxPooling2D(pool_size=(2, 2)))
    model.add(Flatten())
    model.add(Dense(1024))
    model.add(Activation('tanh'))
    model.add(Dense(1))
    model.add(Activation('sigmoid'))
    return model


def generator_containing_discriminator(generator, discriminator):
    model = Sequential()
    model.add(generator)
    discriminator.trainable = False
    model.add(discriminator)
    return model


    

In [69]:

    

#Load and Serialize data
(X_train, y_train), (X_test, y_test) = mnist.load_data()
X_train = (X_train.astype(np.float32) - 127.5)/127.5
X_train = X_train.reshape((X_train.shape[0], 1) + X_train.shape[1:])


#
discriminator = discriminator_model()
generator = generator_model()
discriminator_on_generator = generator_containing_discriminator(generator, discriminator)


    

    




/Users/achanish/anaconda/lib/python2.7/site-packages/ipykernel/__main__.py:21: UserWarning: Update your `Conv2D` call to the Keras 2 API: `Conv2D(64, (5, 5), padding="same", input_shape=(1, 28, 28...)`
/Users/achanish/anaconda/lib/python2.7/site-packages/ipykernel/__main__.py:24: UserWarning: Update your `Conv2D` call to the Keras 2 API: `Conv2D(128, (5, 5))`
/Users/achanish/anaconda/lib/python2.7/site-packages/ipykernel/__main__.py:5: UserWarning: Update your `Dense` call to the Keras 2 API: `Dense(units=1024, input_dim=100)`
/Users/achanish/anaconda/lib/python2.7/site-packages/ipykernel/__main__.py:12: UserWarning: Update your `Conv2D` call to the Keras 2 API: `Conv2D(64, (5, 5), padding="same")`
/Users/achanish/anaconda/lib/python2.7/site-packages/ipykernel/__main__.py:15: UserWarning: Update your `Conv2D` call to the Keras 2 API: `Conv2D(1, (5, 5), padding="same")`

In [71]:

    

#SVG(model_to_dot(discriminator).create(prog='dot', format='svg'))


    

In [32]:

    

#image = img.imread('data_road/training/image_2/um_000001.png')


    

In [33]:

    

#image.shape


    

In [ ]:

    




    

In [ ]: