MIC-DKFZ / medicaldetectiontoolkit

The Medical Detection Toolkit contains 2D + 3D implementations of prevalent object detectors such as Mask R-CNN, Retina Net, Retina U-Net, as well as a training and inference framework focused on dealing with medical images.
Apache License 2.0
1.31k stars 297 forks source link

the function predictor.load_saved_predictions has an unexpected input argument. #66

Closed WENJIANHUANG closed 5 years ago

WENJIANHUANG commented 5 years ago

in the execu.py funciton, the predictor.load_saved_predictions has an unexpected input argument save_preds_to_csv.

        if folds is None:
            folds = range(cf.n_cv_splits)
        for fold in folds:
            cf.fold_dir = os.path.join(cf.exp_dir, 'fold_{}'.format(fold))
            cf.fold = fold
            predictor = Predictor(cf, net=None, logger=logger, mode='analysis') 
            results_list = predictor.load_saved_predictions(apply_wbc=True, save_preds_to_csv=cf.save_preds_to_csv)
            logger.info('starting evaluation...')
            evaluator = Evaluator(cf, logger, mode='test')
            evaluator.evaluate_predictions(results_list)
            evaluator.score_test_df()
pfjaeger commented 5 years ago

thanks, I will fix this!