Open beyerch opened 3 years ago
NOTE - I believe the intent of this was really to skip anything that was not AP or PA.
therefore, code should look like:
We mainly get 3 kinds of datasets: 'AP' or 'PA' images, just 'AP' images, and just 'PA' imges.
All of Kaggle data is from 'AP' view. In order to keep consistent, we select 'AP' from covid data. But, the covid data is too few. Therefor, we also added 'PA' images as complement.
Got it; however, the way the loop is written all PA images are excluded even for COVID images. (due to line 61) I'll submit an update to fix this; however, it will be different than what I proposed above so that PA is only included for COVID
Looking to clarify if a filter restricting process only to Views of 'AP' is intentional or an oversight.
This can be found in the main processing loop:
I ask if this was intentional due to the fact that later processing code looks for 'PA' views. Due to the filter above, there will never be any PA items.
Could you please confirm if this is intended functionality?