Using Convolutional Neural Networks

In [1]:

    

%matplotlib inline


    

In [4]:

    

from __future__ import division, print_function
import os, sys, json
# import keras as K
# os.environ['KERAS_BACKEND'] = 'theano'
sys.path.insert(1, os.path.join('../utils/'))
import utils; from utils import plots
import glob as glob
import numpy as np
np.set_printoptions(precision=4, linewidth=100)
from matplotlib import pyplot as plt


    

    




Using Theano backend.

In [5]:

    

import vgg16;
from vgg16 import Vgg16


    

In [6]:

    

from numpy.random import random, permutation
from scipy import misc, ndimage
from scipy.ndimage.interpolation import zoom

import keras
from keras import backend as K
from keras.utils.data_utils import get_file
from keras.models import Sequential, Model
from keras.layers.core import Flatten, Dense, Dropout, Lambda
from keras.layers import Input
from keras.layers.convolutional import Convolution2D, MaxPooling2D, ZeroPadding2D
from keras.optimizers import SGD, RMSprop
from keras.preprocessing import image


    

In [7]:

    

FILES_PATH = 'http://files.fast.ai/models/'; CLASS_FILE='imagenet_class_index.json'
# Keras' get_file () is a handy function that downloads files, and caches them for reuse later
fpath = get_file(CLASS_FILE, FILES_PATH+CLASS_FILE, cache_subdir='models')
with open(fpath) as f: class_dict = json.load(f)
# Convert dictionary with string indices into an array
classes = [class_dict[str(i)][1] for i in range(len(class_dict))]


    

In [8]:

    

classes[:5]


    

    
Out[8]:





[u'tench', u'goldfish', u'great_white_shark', u'tiger_shark', u'hammerhead']

In [9]:

    

def ConvBlock(layers, model, filters):
    for i in range(layers): 
        model.add(ZeroPadding2D((1,1)))
        model.add(Convolution2D(filters, 3, 3, activation='relu'))
    model.add(MaxPooling2D((2,2), strides=(2,2)))
def FCBlock(model):
    model.add(Dense(4096, activation='relu'))
    model.add(Dropout(0.5))


    

In [10]:

    

# Mean of each channel as provided by VGG researchers
vgg_mean = np.array([123.68, 116.779, 103.939]).reshape((3,1,1))
def vgg_preprocess(x):
    x = x - vgg_mean     # subtract mean
    return x[:, ::-1]    # reverse axis bgr->rgb


    

In [11]:

    

def VGG_16():
    model = Sequential()
    model.add(Lambda(vgg_preprocess, input_shape=(3,224,224)))

    ConvBlock(2, model, 64)
    ConvBlock(2, model, 128)
    ConvBlock(3, model, 256)
    ConvBlock(3, model, 512)
    ConvBlock(3, model, 512)

    model.add(Flatten())
    FCBlock(model)
    FCBlock(model)
    model.add(Dense(1000, activation='softmax'))
    return model


    

In [12]:

    

model = VGG_16()


    

    




/Users/WayNoxchi/Miniconda3/envs/FAI/lib/python2.7/site-packages/keras/layers/core.py:622: UserWarning: `output_shape` argument not specified for layer lambda_1 and cannot be automatically inferred with the Theano backend. Defaulting to output shape `(None, 3, 224, 224)` (same as input shape). If the expected output shape is different, specify it via the `output_shape` argument.
  .format(self.name, input_shape))

In [13]:

    

def ConvBlock(layers, model, filters):
    for i in range(layers):
        model.add(ZeroPadding2D((1, 1)))
        model.add(Convolution2D(filters, 3, 3, activation='relu'))
    model.add(MaxPooling2D((2, 2), strides=(2, 2)))


def FCBlock(model):
    model.add(Dense(4096, activation='relu'))
    model.add(Dropout(0.5))


def VGG_16():
    model = Sequential()
    model.add(Lambda(vgg_preprocess, input_shape=(3,224,224), output_shape=(3,224,224)))

    ConvBlock(2, model, 64)
    ConvBlock(2, model, 128)
    ConvBlock(3, model, 256)
    ConvBlock(3, model, 512)
    ConvBlock(3, model, 512)

    model.add(Flatten())
    FCBlock(model)
    FCBlock(model)
    model.add(Dense(1000, activation='softmax'))

    # fname = 'vgg16.h5'
    # model.load_weights(get_file(fname, self.FILE_PATH+fname, cache_subdir='models'))

model = VGG_16()


    

In [ ]:

    




    

In [ ]:

    




    

In [ ]:

    




    

In [ ]:

    




    

In [ ]:

    




    

In [ ]:

    




    

In [ ]: