I set 30 expected particles/mrc for the training job; it seems to have performed well (see attached). This is the command used to start the extraction:
/home/cryosparc_user/miniconda3/envs/topaz/bin/topaz extract --radius 7 --threshold -6 --up-scale 4 --assignment-radius -1 --min-radius 5 --max-radius 100 --step-radius 5 --num-workers 8 --device 4 --model /ddn/gs1/project/cryoemCore/process/cryosparc_callisto/[NAME HERE]/P141/J251/models/model_epoch10.sav -o /ddn/gs1/project/cryoemCore/process/cryosparc_callisto/Stanley/P141/J265/topaz_particles_prediction.txt
These are my params for the extract job, none of which are changed from default:
Downsampling factor: 4
Number of iterations: 200
Score threshold: 0
Number of parallel threads: 8
Radius of extracted regions: 7
Extraction threshold: -6
Particle threshold: 0
Max assignment radius: -1
Min extraction radius: 5
Max extraction radius: 100
Step radius: 5
Number of CPUs: 8
