Peterisfar
commented
4 years ago Thank you so much, you are so careful, thanks again. 1、you are right , it's a bug. it should be min 2、i think this case is low probability，if it happens, i think no influence.but add a condition is better. 3、'Bag of Freebies' has three versions, this code follows v1 4、bbox_loss_scale follows the darknet, and GIOU don't have it.the reason for using it is to balance the impact of different scale boxes on the loss. this code only use one factor, no scale factor(alpha is 1.0) in the folcal loss, but worth to try as the paper.
wangren97
Very thanks for your work. These days I am working on the implementation of YOLOv3 and find your work. I have some questions about the code. 1) random_crop function. In utils/data_augment.py, line 'crop_xmax = max(w_img, int(max_bbox[2] + random.uniform(0, max_r_trans)))' and 'crop_ymax = max(h_img, int(max_bbox[3] + random.uniform(0, max_d_trans)))' I think the 'max' function should be changed to 'min' because 'h_img' and 'w_img' are always the maximum ones. 2) mixup function: utils/datasets.py line 'item_mix = random.randint(0, len(self.__annotations)-1)'. when I test by myself, there exists a case that item_mix = item. I think it is better to add a if condition for this case to avoid 'bboxes = np.concatenate([bboxes_org, bboxes_mix])' 3) label_smooth: I read the paper 'Bag of Freebies' and in section 3.2, equation (3), the formula is different with your implementation. The one shown in the paper is 1 - delta if i=y else delta (K -1) and your code is 1 - delta + delta / K if i=y else delta / K. Is it correct? 4) loss function: I didn't understand 'bbox_loss_scale = 2.0 - 1.0 label_xywh[..., 2:3] label_xywh[..., 3:4] / (img_size * 2)' in giou loss. Is it shown in the GIOU paper? why the format is 2 minus the label box area / image area? For 'label_noobj_mask FOCAL(input=p_conf, target=label_obj_mask)' in confidence loss. I find in some other implementations, there is a scale factor for the balance of negative samples. see https://github.com/eriklindernoren/PyTorch-YOLOv3/issues/309. Then how to determine the scale value? Could you please explain them? Very thanks!