Closed humzaahmad906 closed 4 years ago
Yes but if i'm passing custom images here like
clicks_list, ious_arr, pred = evaluate_sample(cv2.imread("example.jpg"), cv2.imread("1.jpg", cv2.IMREAD_GRAYSCALE), predictor, pred_thr=MODEL_THRESH, max_iou_thr=TARGET_IOU, max_clicks=EVAL_MAX_CLICKS)
Do i need to change something? Also can i use the evaluation process without giving it a mask?
There are two options:
evaluate_sample
as in this mode user clicks are generated automatically with a certain strategy (refer to the paper for details).In both options image should be normalized before passing it to the network.
It helped alot. Thanks
Yes, checkout Evaluation section of readme and jupyter notebook for details.