227
edits
Changes
Jump to navigation
Jump to search
→Image Processing
*Current training dataset: <code>The File to Rule Them All</code>, contains information of 160 accelerators (homepage url, cohort url etc.). We will train our model on those 145 accelerators that have cohort urls found
*Type of input for CNN model: picture of the web page(generated from the above screenshot tool) and cohort indicator (1 - it is a cohort page, 0 - not a cohort page)
** The cohort indicator indicates that our input dataset is a labeled dataset, this may become handy when choosing packages for building the CNN model
====Data Preprocessing====
