Aninda Saha comments

Repositories
Issues
Comments

Results 4 comments of


                                            Aninda Saha

this repo is good ONLY for INFERENCE with PROVIDED WEIGHTS.

> @tjiagoM yes I did. > https://github.com/ultralytics/yolov3. I achieved much much better results using their model. Are there any minimal Yolov3 implementations that achieve the original results from the authors?...

How to obtain a good accuracy + how to get mAP?

For COCO dataset, perhaps you can use the pycocotools API: https://github.com/cocodataset/cocoapi/blob/master/PythonAPI/pycocoEvalDemo.ipynb

too much time in get_evaluation_bboxes in yolo v3

Try suppressing the number of boxes by amending the second line in the non_max_suppression function to `bboxes = sorted(bboxes, key=lambda x: x[1], reverse=True)[:max_boxes]`. Also, evaluate after a couple of epochs...

too much time in get_evaluation_bboxes in yolo v3

Same here. Haven't been able to reproduce 78% as described.