If models not already downloaded in /home/ubuntu/models/
(need 8.6 G)
- Make models directory:
sudo mkdir /home/ubuntu/models
- For view classification model: in models directory, download
clf_urls.txt
and runwget -i clf_urls.txt
- For image segmentation models: in models directory, download
seg_urls.txt
and runwget -i seg_urls.txt
Before running
- Replace
./models/
with/home/ubuntu/models/
in Python files
To run on your own study
0. If data comes from AWS, configure credentials: aws configure
- Replace "Image" with "a" in
predict_viewclass_v2.py
- Make data directory:
mkdir /home/ubuntu/data
- Comment out
dicomdir = "dicomsample"
- For
segment_a4c_a2c_a3c_plax_psax.py
, copyOptionParser
import and code frompredict_viewclass_v2.py
- Run Python file with
-d <study_dir>
option
To run on your own studies
- Run Python file with
-d <study_dir>
option