As the semester develops links to additional course resources will
be placed here.
Early OpenCV Examples
Interactive Fourier Transform Sites
- Tomáš
Bořil Fourier Series 3D. This site lets you control the
construction of different functions by manipulating the phase and
magnitude of constiuent parts of the signal. The visualization takes
advanatage of a 3D view that is clever and allows more information
be shown in a single presentation.
- Evan Wallace's interactive
DFT Demo. Evan Wallace has built a very nice interactive site
to experiment with the Discrete Fourier Transform. The demo includes
the ability through simple mouse over moves to low pass filter a
signal.
- Dave
Watts Ejectamenta Fourier Site. Dave Watts has built an
excellent 2D fourier transform visualization tool that allows one to
move backward and forward between the spatial domain, e.i. a
greyscale image, and the Frequency domain. For testing I prefer the
following image of
the CSU Oval. Pay attention to the Short
Instructions and in particular the guideance on how to
construct a low pass and a high pass filter. Also, if you want to
test your skill, supress the 'noise' consisting of a sinusoidal
disturbance in this image
of the letter B.
Tensorflow Examples with Backprogagation made Explicit
- Dan
Aloni has developed a nice tutorial and working example of how
backpropogation works on the MNIST dataset. Ben Sattleberg here at
CSU made some modifications to make the example work more smoothly
with the
dataset.py
library. You can download this
local version here at aloni_backprop.zip
Keras Examples of Standard and Convolutional Nets
- Jason
Brownlee's MNIST Keras Tutorial is an excellent introduction to
the simplicity of specifiying and training networks using the Keras
interface. Keep in mind how much is hidden from the user with this
level of abstraction in the code, and then enjoy the compact and
relatively clear specifications provided in the examples. For
convenience this zipped
folder has the first two examples from Brownlee's tutorial
readdy to unpack and run.
Using Inception Net
- Matt Dragon, our guest lecturer for April 22, is making cs510-inception-demo.tar
available before lecture so that all students, or at a minimum all
student teams, can have this code downloaded on a laptop and ready
to begin working with in adviance of lecture on Monday April 22.
TensorBoard MNIST Summaries
- There are a variety of ways to utilze TensorBoard to inspect
different aspects of a network during test and training. Source code
for the mnist_with_summaries.py
is availble on GitHub. We will review this example in Class on
April 26.