227
edits
Changes
Jump to navigation
Jump to search
→CNN Model
Some factors /problems to consider for '''future implementation''' on the model:
* Class label is highly imbalanced: o (not cohort) is way more than 1 (cohort) class
**may cause our model favoring the larger class, then the accuracy metric is not reliable
* Convert image data into same format
** [https://www.oreilly.com/library/view/linux-multimedia-hacks/0596100760/ch01s04.html Make image thumbnail]
*I chose to group images into cohort folder or not_cohort folder to let our CNN model detect the class label of an image. There are certainly other ways to detect class label and one may want to modify the Screenshot Tool and <code>cnn.py</code> to assist with other approaches
===Workflow===
