I want to return the SMILES text from a PDF or PNG image of a molecule
#2
by
NoazDad
- opened
The demo app - where you drag and drop an image file and it generates out the SMILES string - can someone please share the Python code that would do that same function?
I got this far from the docs, but this isn't the result I'm after:
from ultralytics import YOLO
model = YOLO("moldet_yolo11l_960_doc.pt")
model.predict("Basic-molecular-structures-analyzed.png", save=True, imgsz=640, conf=9.5)
model.results[0].show()
conf=9.5 -> conf=0.5
MolDet is only a detection model for molecule structure. For OCSR task, you need use MolParser model (will be open sourced asap)
