Differences

This shows you the differences between two versions of the page.

--- cs501r_f2018:lab2 [2018/09/10 16:58]
wingated created
+++ cs501r_f2018:lab2 [2021/06/30 23:42]
@@ Line 1: / Line 1: @@
-====Objective:====
-Get started with pytorch.  Begin to understand the basic boilerplate code of most pytorch programs.
-----
-====Deliverable:====
-For this lab, you will submit an ipython notebook via learningsuite.  This notebook will have two parts:
-**Part 1:**  Your notebook should generate a random image.  We will run this
-notebook 5 times; it should generate 5 different, moderately complex
-images.  Each image should be 512 x 288.  Have fun with it!
-The resulting image could, for example, look like this:
-{{:cs401r_w2016:lab1.png?nolink|}}
-**Part 2:** You must play with the Tensorflow playground neural network, and figure out how to create a classifier that successfully classifies the "spiral" dataset.
-[[http://playground.tensorflow.org/|Tensorflow playground]]
-[[http://colab.research.google.com/|Google colab]]
-[[https://colab.research.google.com/drive/1TzaPS3jvRadN-URLbQ9nD1ZNoZktfNRy|A colab notebook teaching you how to use colab notebooks]]
-[[https://sites.google.com/site/artml2018/tutorials|Various colab tutorials]]
-----
-====Grading standards:====
-Your notebook will be graded on the following:
-  * 50% Successfully followed lab video and typed in code
-  * 20% Modified code to include a test/train split
-  * 20% Modified code to include a visualization of train/test accuracies
-  * 10% Tidy and legible figures, including labeled axes where appropriate
-----
-====Description:====
-Throughout this class, we will be using Google's colab environment to develop and test our deep neural networks.  This consists of ipython
-notebooks and a standardized python distribution.  For this lab, you
-must create a google account (or use one you already have), start up colab, and write a simple python program in it.
-As described above, the notebook should do two things:
-) generate simple random images, and 2) display an image that you generate using the Tensorflow playground.
-For part 1, you can generate any sort of random image that you want -- consider
-random lines, random curves, random text, etc.  Each time the program
-is run, it should generate a different random image.  Your image
-should have at least 50 random elements (they can all be the same
-type, such as random lines, and can be created in a loop).  We won't
-count the number of elements; this is just to encourage you to create
-random images with moderate complexity (ie, you can't just generate randomly colored pixels, as in the example below).
-For part 2, you should visit the Tensorflow playground (see link above), and play with different settings.  Most of it will be unfamiliar, but don't worry -- you can't break it!
-Once you have a working classifier, take a screenshot.  Then use your colab notebook to display that image in-line.
-----
-====Starter code:====
-Here's some starter code to help you generate an image.  The ''nbimage'' function will display the image inline in the notebook:
-<code python>
-import IPython.display
-import PIL.Image
-import numpy as np
-# A simple function to display an image in an ipython notebook
-def nbimage( data ):
-    IPython.display.display(PIL.Image.fromarray(data))
-# create an image consisting of random colors
-data = np.random.rand(512,512,3) # a 512x512 image, with 3 color channels (R,G,B)
-# by default, rand creates floating point numbers between [0,1].  We need to convert that to 8-bit bytes between [0,255]
-data = (255*data).astype('uint8')
-# display it!
-nbimage( data )
-</code>
-----
-====Hints:====
-The following python functions might be helpful:
-<code python>
-import matplotlib.pyplot as plt
-plt.legend
-plt.xlabel
-plt.ylabel
-plt.tight_layout
-</code>

BYU CS classes

User Tools

Site Tools

Differences

Page Tools