thtang / CheXNet-with-localization

Weakly Supervised Learning for Findings Detection in Medical Images
https://www.csie.ntu.edu.tw/~yvchen/f106-adl/doc/HTCMedical.pdf
GNU General Public License v3.0
314 stars 108 forks source link

How to run this on a single image ? #6

Closed tanmay-bhatnagar closed 5 years ago

tanmay-bhatnagar commented 5 years ago

I want to use this model and run it on a single image say 'xray.jpeg'. What needs to be done ?

thtang commented 5 years ago

python3 denseNet_localization.py [path to test.txt] [path of images folder]

[path to test.txt]: test.txt contains the image file name, i.e., xray.jpeg [path of images folder]: path to the folder you store that image

Aliktk commented 3 years ago

@thtang how to visualize the heatmap and BB for the predicted output of the given image? Furthermore, I am confused why this model always predicts 8 or 16 or 14 predictions in an image which is not possible to find these abnormalities. So what abnormalities we should focus on to print BB on the heatmap-generated images? Please help me in this regard