Partially Trained Neural Network Updates

Week 7 Progress Update         This week I debugged much of the data input system as well as the creation of the neural net architecture. The new slightly modified code is shown below, I just basically created a placeholder for x_batch so that it could initialize before I actually run the network. Other than that I made a few minor corrections across the code. The NN architecture

Week 6 Progress Update This week has again been very slow, I fixed my code for importing Cifar-10 which involved switching from a prebuilt TensorFlow library which handled Cifar-10 to custom code which imported the data using the TensorFlow data module (shown below). As with any module that I have not worked with before, it took a significant amount of time to learn and implement. I have moved on to debugging where I will probably be stuck for the remainder of this week and possibly further if any major problems arise, which they most likely will. The functions I used to import the Cifar 10 dataset

Week 5 Progress Update I spent much of this week making my CNN with Cifar-10 an image set that offers a lot of training data. I didn't get a whole lot done code wise this week because this was my main focus and I am not very well acquainted with the data pipeline system in Tensorflow. However I do have the beginning of processing code and I completed the code for optimizing the CNN which should work pretty well with my code for the rest of the model. Over the next week I will probably finish up my data processing code and start debugging the CNN. Data processing functions and variables (above) and optimization code (below)

Week 4 Progress Update         This week I spent the first few days doing more research into how to build a CNN in TensorFlow. I primarily used the TensorFlow example ( https://www.tensorflow.org/tutorials/images/deep_cnn ) and the corresponding documentation for this. Once I found I had a solid understanding of the basics of TensorFlow I began programming my own CNN, loosely based off of the TensorFlow example. I have not yet used it or chosen a dataset to test it with but I have created all of my helper functions and built the framework for the model as shown below.

Week 3 progress update         Most of the progress I made this week was just research, I focused on getting familiar with the TensorFlow framework. I made several neural networks that work in slightly different ways and using different data sets. I have not completely decided on a data set that I want to use but I am probably going to use Image Net as it provides a relatively large sample for each class as well as plenty of classes. During my research I also designed a small script for processing "pickled" data, which has been stored for use in python as well as a script for processing some particular data sets such as Mnist, both of these are shown below. I also did a bit of research on making a CNN in TensorFlow which I will start actually building over the course of the next week or two.

Week 2 Progress Update.         I spent the majority of this week learning how to use the TensorFlow Framework. In order to do this I built a very simple neural network with it. All this neural network does is sort 28 x 28 pictures of street signs into 62 different categories, below is the code, the sections that are commented out (surrounded by ''' or proceeded by #) are either notes or remnants of the tutorial I was following. Below the code is an image which randomly samples some of the signs in the testing dataset once the network has been trained. It then attempts to predict what category it belongs to, if the predicted category matches the actual category it shows green text, if not, it shows red text. # imports import tensorflow as tf import os import skimage import numpy as np import matplotlib.pyplot as plt import random as r from skimage import transform ''' #init constants x1 = tf.constant([1,2,3,4]) x2 = tf.constant([5,6,7,8]) #multi...

Week 1 progress           This week I started building the algorithms for operating my convnet. I first installed TensorFlow, the framework I am using to build the models, which took far longer than it should have because of compatibility issues with the python installation on my machine. After I got this installed I did some minor research into data sets and chose a beginner data set for creating a neural network. This data set consists of different classifications of Belgian street signs. I then created a small algorithm to load the data as shown below. The complications in installing TensorFlow set me back and this was as far as I got during the week.