From 3ebdfb7de7324d4cf5fb22ad5378b2c2a9b29fb1 Mon Sep 17 00:00:00 2001 From: Silver-T Date: Thu, 24 May 2018 20:36:35 +1000 Subject: [PATCH 1/2] Cleaned a little bit of code --- mini_proj/waldo_model.py | 77 +++++++++++++++++++++++++++++++++++++--- 1 file changed, 73 insertions(+), 4 deletions(-) diff --git a/mini_proj/waldo_model.py b/mini_proj/waldo_model.py index ed09794..f62e5c9 100644 --- a/mini_proj/waldo_model.py +++ b/mini_proj/waldo_model.py @@ -25,7 +25,7 @@ from keras.utils import to_categorical ''' Model definition define the network structure ''' -def FCN(): +def CNN(): ## List of model layers inputs = Input((3, 64, 64)) @@ -33,7 +33,6 @@ def FCN(): m_pool1 = MaxPooling2D(pool_size=(2, 2))(conv1) conv2 = Conv2D(32, (3, 3), activation='relu', padding='same')(m_pool1) - #drop1 = Dropout(0.2)(conv2) # Drop some portion of features to prevent overfitting m_pool2 = MaxPooling2D(pool_size=(2, 2))(conv2) conv3 = Conv2D(32, (3, 3), activation='relu', padding='same')(m_pool2) @@ -47,13 +46,81 @@ def FCN(): drop3 = Dropout(0.2)(dense) classif = Dense(2, activation='sigmoid')(drop3) # Final layer to classify - ## Define the model structure + ## Define the model start and end model = Model(inputs=inputs, outputs=classif) # Optimizer recommended Adadelta values (lr=0.01) model.compile(optimizer=Adam(), loss='binary_crossentropy', metrics=['accuracy', f1]) return model +''' +Model definition for a fully convolutional (no dense layers) network structure +''' +def FCN(): + ## List of model layers + inputs = Input((3, 64, 64)) + + conv1 = Conv2D(16, (3, 3), activation='relu', padding='same', input_shape=(64, 64, 3))(inputs) + m_pool1 = MaxPooling2D(pool_size=(2, 2))(conv1) + + conv2 = Conv2D(32, (3, 3), activation='relu', padding='same')(m_pool1) + m_pool2 = MaxPooling2D(pool_size=(2, 2))(conv2) + + conv3 = Conv2D(32, (3, 3), activation='relu', padding='same')(m_pool2) + drop2 = Dropout(0.2)(conv3) # Drop some portion of features to prevent overfitting + m_pool2 = MaxPooling2D(pool_size=(2, 2))(drop2) + + conv4 = Conv2D(64, (2, 2), activation='relu', padding='same')(m_pool2) + + flat = Flatten()(conv4) # Makes data 1D + drop3 = Dropout(0.2)(flat) + classif = Dense(2, activation='sigmoid')(drop3) # Final layer to classify + + ## Define the model start and end + model = Model(inputs=inputs, outputs=classif) + # Optimizer recommended Adadelta values (lr=0.01) + model.compile(optimizer=Adam(), loss='binary_crossentropy', metrics=['accuracy', f1]) + + return model + + +''' +Model definition for the network structure of LeNet +Note: LeNet was designed to classify into 10 classes, but we are only performing binary classification +''' +def LeNet(): + ## List of model layers + inputs = Input((3, 64, 64)) + + conv1 = Conv2D(6, (5, 5), activation='relu', padding='valid', input_shape=(64, 64, 3))(inputs) + m_pool1 = MaxPooling2D(pool_size=(2, 2))(conv1) + + conv2 = Conv2D(16, (5, 5), activation='relu', padding='valid')(m_pool1) + m_pool2 = MaxPooling2D(pool_size=(2, 2))(conv2) + + flat = Flatten()(m_pool2) # Makes data 1D + + dense1 = Dense(120, activation='relu')(flat) # Fully connected layer + dense2 = Dense(84, activation='relu')(dense1) # Fully connected layer + drop3 = Dropout(0.2)(dense2) + classif = Dense(2, activation='sigmoid')(drop3) # Final layer to classify + + ## Define the model start and end + model = Model(inputs=inputs, outputs=classif) + model.compile(optimizer=Adam(), loss='binary_crossentropy', metrics=['accuracy', f1]) + + return model + +''' +AlexNet architecture +''' +def AlexNet(): + inputs = Input(shape=(3, 64, 64)) + + + return model + + def f1(y_true, y_pred): def recall(y_true, y_pred): """Recall metric. @@ -110,14 +177,16 @@ lbl_train = to_categorical(lbl_train) # One hot encoding the labels lbl_test = to_categorical(lbl_test) ## Define model +#model = CNN() model = FCN() +#model = LeNet() # svm_iclf = ImageClassifier(svm.SVC) # tree_iclf = ImageClassifier(tree.DecisionTreeClassifier) # naive_bayes_iclf = ImageClassifier(naive_bayes.GaussianNBd) # ensemble_iclf = ImageClassifier(ensemble.RandomForestClassifier) ## Define training parameters -epochs = 10 # an epoch is one forward pass and back propogation of all training data +epochs = 25 # an epoch is one forward pass and back propogation of all training data batch_size = 150 # batch size - number of training example used in one forward/backward pass # (higher batch size uses more memory, smaller batch size takes more time) #lrate = 0.01 # Learning rate of the model - controls magnitude of weight changes in training the NN From 1e0631c84dbccf77da73a657e0c1f6bbe9fe7f20 Mon Sep 17 00:00:00 2001 From: Silver-T Date: Fri, 25 May 2018 11:44:59 +1000 Subject: [PATCH 2/2] Added image preprocessing information --- mini_proj/report/references.bib | 1 + mini_proj/report/waldo.tex | 51 +++++++++++++++++++++++++++++---- 2 files changed, 47 insertions(+), 5 deletions(-) diff --git a/mini_proj/report/references.bib b/mini_proj/report/references.bib index e69de29..fefbbe7 100644 --- a/mini_proj/report/references.bib +++ b/mini_proj/report/references.bib @@ -0,0 +1 @@ +@misc{openData, title={Open Database License (ODbL) v1.0}, url={https://opendatacommons.org/licenses/odbl/1.0/}, journal={Open Data Commons}, year={2018}, month={Feb}} \ No newline at end of file diff --git a/mini_proj/report/waldo.tex b/mini_proj/report/waldo.tex index da620bb..0c6dd95 100644 --- a/mini_proj/report/waldo.tex +++ b/mini_proj/report/waldo.tex @@ -6,8 +6,8 @@ \usepackage[justification=centering]{caption} % Used for captions \captionsetup[figure]{font=small} % Makes captions small \newcommand\tab[1][0.5cm]{\hspace*{#1}} % Defines a new command to use 'tab' in text - % Math package - \usepackage{amsmath} + \usepackage[comma, numbers]{natbib} % Used for the bibliography + \usepackage{amsmath} % Math package % Enable that parameters of \cref{}, \ref{}, \cite{}, ... are linked so that a reader can click on the number an jump to the target in the document \usepackage{hyperref} %enable \cref{...} and \Cref{...} instead of \ref: Type of reference included in the link @@ -18,6 +18,7 @@ % Easier compilation \usepackage{bookmark} \usepackage{natbib} + \bibliographystyle{ieeetr} \begin{document} \title{Waldo discovery using Neural Networks} @@ -32,13 +33,53 @@ \section{Background} - \section{Methods} + A couple of papers that may be useful: + - LeNet: http://yann.lecun.com/exdb/publis/pdf/lecun-01a.pdf + - AlexNet: http://papers.nips.cc/paper/4824-imagenet-classification-with-deep-convolutional-neural-networks + - General comparison of LeNet and AlexNet: + "On the Performance of GoogLeNet and AlexNet Applied to Sketches", Pedro Ballester and Ricardo Matsumura Araujo + - Deep NN Architecture: + https://www-sciencedirect-com.ezproxy.lib.monash.edu.au/science/article/pii/S0925231216315533 + \section{Methods} + \tab + In order to effectively utilize the aforementioned modelling and classification techniques, a key consideration is the data they are acting on. + A dataset containing Waldo and non-Waldo images was obtained from an Open Database\footnote{``The Open Database License (ODbL) is a license agreement intended to allow users to freely share, modify, and use [a] Database while maintaining [the] same freedom for others"\cite{openData}}hosted on the predictive modelling and analytics competition framework, Kaggle. + The distinction between images containing Waldo, and those that do not, was providied by the separation of the images in different sub-directories. + It was therefore necessary to preprocess these images before they could be utilised by the proposed machine learning algorithms. + + \subsection{Image Processing} + \tab + The Waldo image database consists of images of size 64$\times$64, 128$\times$128, and 256$\times$256 pixels obtained by dividing complete Where's Waldo? puzzles. + Within each set of images, those containing Waldo are located in a folder called `waldo', and those not containing Waldo, in a folder called `not\_waldo'. + Since Where's Waldo? puzzles are usually densely populated and contain fine details, the 64$\times$64 pixel set of images were selected to train and evaluate the machine learning models. + These images provide the added benefit of containing the most individual images of the three size groups. + \\ + \par + Each of the 64$\times$64 pixel images were inserted into a Numpy + \footnote{Numpy is a popular Python programming library for scientific computing} + array of images, and a binary value was inserted into a seperate list at the same index. + These binary values form the labels for each image (waldo or not waldo). + Colour normalisation was performed on each so that artefacts in an image's colour profile correspond to meaningful features of the image (rather than photographic method). + \\ + \par + Each original puzzle is broken down into many images, and only contains one Waldo. Although Waldo might span multiple 64$\times$64 pixel squares, this means that the non-Waldo data far outnumbers the Waldo data. + To combat the bias introduced by the skewed data, all Waldo images were artificially augmented by performing random rotations, reflections, and introducing random noise in the image to produce news images. + In this way, each original Waldo image was used to produce an additional 10 variations of the image, inserted into the image array. + This provided more variation in the true positives of the data set and assists in the development of more robust methods by exposing each technique to variations of the image during the training phase. + \\ + \par + Despite the additional data, there were still over ten times as many non-Waldo images than Waldo images. + Therefore, it was necessary to cull the no-Waldo data, so that there was an even split of Waldo and non-Waldo images, improving the representation of true positives in the image data set. + \\ \section{Results} \section{Discussion and Conclusion} - \bibliographystyle{humannat} + \clearpage % Ensures that the references are on a seperate page + \pagebreak + % References + \section{References} + \renewcommand{\refname}{} \bibliography{references} - \end{document}