Visualizing a CNN

Using Quiver to visualize a Keras CNN Debugging a neural network is tricky. CNNs are a little bit more “understandable” because we can look which features of an image activates different neurons. The following video is from the CS231n class...

GTSRB with tensorflow.js

TL;DR You can try my Traffic Sign Recognition Model in your browser: https://pollithy.com/gtsrb/index.html. The accuracy won’t overwhelm you ;) This blog post explains how to build such a website. Using tensorflow.js to run a Keras model in browser Tensorflow.js is...

Keras

GTSRB with Keras In my last blog post I described how I built a model for traffic sign recognition with tensorflow. The data set contains 43 different German traffic signs: It is made out of 39.000 training images and the...

GTSRB

Classifying german traffic signs Having reached something like a checkpoint in the cs231n lecture plan I decided to train a CNN to detect German street signs before going on with recurrent neural networks. Tensorflow will be employed and the network...

Summarizing large graphs

VoG: Summarizing and understanding large graphs In summer 2017 I attended a data mining seminar. Every participant had to summarize and analyze a different algorithm. Mine was ”VoG - Summarizing and Understanding Large Graphs” by Danai Koutra (Carnegie Mellon University),...

CIFAR-10

Writing a CNN for cifar-10 Alex Krizhevsky, Vinod Nair and Geoffrey Hinton collected a data set called called CIFAR-10 where the Canadian Institute of Advanced Research was the name donor. It is a subset of 80 million tiny images with...

Tutorial pypcd

Pypcd Handling point cloud .pcd files with python. The point cloud library develops its own format called PCD (Point Cloud Data). Details can be found here. If I want to process the 3d data stored in pcd with python I...

Intro to Cython

Intro to Cython Python is not the fastest. Everything is an object and all of them are implemented as a dictionary. Numpy’s vectorized matrix operations can speed up a lot of things. Especially for-loops should not be written. But in...

Blogging with Jupyter

Blogging with Jupyter I realized that most of my blog posts behave like a jupyter notebook (markdown, code and repeat). So why not just write a jupyter notebbok and post it as a blog entry. I am going evaluate if...

Tic Tac Toe CNN

Experiment: Writing a CNN for tic tac toe Let’s write a CNN which detects the current state of a tic tac toe game. Although it might be super easy to write an opencv2 script which makes this I want to...

Kaggle Titanic 83%

How I achieved 83% accuracy in the Kaggle Titanic challenge After trying different things (a custom linear model, different cvs, different random forests, randomized searches, pca) I found the GradientBoostingClassifier with {‘max_depth’: 4, ‘n_estimators’: 200} to perform the best with...

Google Cloud ML

Training a CNN for MNIST on Google Cloud ML In this post I am going to describe how to setup a tensorflow graph to run on the Google Cloud. Sign up for the 12 months 300$ trial account Create a...

React Login with Django

Example of a React SPA that logs into a Django backend with JWT A scenario for SPAs is that you might be building it to further use it in a mobile app (maybe react-native). To avoid switching from session_ids stored...

Pipeline with Scikit

Processing data with scikit’s pipelines, pandas and numpy Fiddling around with my first kernels on Kaggle I found processing data time consuming and it easily looked messy in the jupyter notebook. Especially the fact that I splitted the data set...

Point Cloud Registration Figure

Thoughts on how to design a registration figure As mentioned in my last post I was facing the challenge of registrating point clouds captured by multiple depth cameras. The general idea behind registration in this context is to rotate and...

Point cloud from mesh object

How to create a point cloud from an arbitrary mesh in Blender If you want to registrate multiple tof cameras on one spot, chances are high that you are using Iterative Closest Point (ICP) to maximize the overlap between your...

Backpropagation and stochastic gradient descent

Calculating backpropagation by hand My last post was about a feed forward net. I did not explain where the weights in the network came from. This entry explains back propagation and contains a calculation for the example from the last...

A neural network in plain python

Let’s build a neural net from scratch without numpy and scikit In my last blog entries I have been discovering neural networks: Calculating a feed forward net by hand Backpropagation As long as it is possible, I am a fan...

Calculating a feed forward net by hand

Calculating a feed forward network by hand In computer science the building blocks of everything are ones and zeros. This simplicity is not an obstacle for building complex systems. For Artifical Neural Networks the simple building blocks are the perceptrons....

A Decision Tree

Decision Tree I have got a small data set (my working hours as a working student) on which I want to train a binary classifier to tell working days from non-working days apart. My regular days in the office changed...

Support Vector Machine

Using a support vector machine to classify workdays I use the same data set as in my last post which is a list of days (weekday, day of the month, month) from the last years labeled with 1 or 0...

Principal components analysis

Principal components analysis with numpy The first section of the deeplearningbook aims to refresh basic knowledge about linear algebra. Only the most important concepts to understand machine learning were covered. New for me (or I just did not remember from...

Django migration: Add through="..." to a ManyToManyField

Django migration for through model to a ManyToMany I recently had the problem that a m2n relation in a django application should be sortable. So I wanted to add a through model to the relation but unfortunately as of now...

MNIST with a CNN in TensorFlow

Quickstart to TensorFlow I decided to build the classic MNIST hello world digit recognition with a convolutional neural network in tensorflow. And then I wrote a small Tkinter user interface to draw numbers, sample them down and feed them into...

Hack4Climate in Bonn

DLT against climate change In November 2017 I participated at a hackathon in Bonn called “Hack4Climate”. Actually on a boat which was anchored five minutes from the city center in the river Rhine. A cool location to host an event....