-
Thanks for the great work! It's useful for our work, but we had a problem during the training.
The 3D_IoU is always 0.00, leading to a lower performance than paper.
The training process just …
-
- [x] : decoder (MLP)도 포함되어야함
- [x] : https://huggingface.co/docs/transformers/en/model_doc/segformer
- [x] : BCE loss
train_iou의 큰 개선없음
http://219.252.39.224:5000/#/metric/val_iou?runs=[%226b33…
-
> Mean IoU: 0.0054892840770171146
> Mean precision: 0.00883236695325248
> Mean recall: 1.0
> Validation loss: 1.0013856360545526
>
> Epoch: 0, Train loss: 0.9933058513062341
> Mean IoU: 0.005…
-
exp, the model is yolo. This good loss can replace the original IOU-loss?
how do it?
Look forward to your reply!
------If your detection model is yolo, this will be very easy, just find the desti…
-
Have you use smooth l1 loss instead of IOU loss in fcos? And which one is better?
-
hi @bo-zhang-cs
when test your release model, i find that the acc is lower than the paper, which is 73%. and i try to figure out how to fix this problem. after doing multi-experiments, i i have foun…
-
hi, when I run 'from spconv.utils import rbbox_iou, rbbox_iou_loss' in box_np_ops.py, it occurs an error: ImportError: cannot import name 'rbbox_iou_loss'. However, when I ask the author about rrbox_i…
-
I am getting a weird loss and IoU score.. Dice loss becomes negative just after 2-3 epochs, and IoU becomes greater than 1 at the same time.
Why is this happening? I have already checked and my mask…
-
`2024-06-10 17:07:33,221 - mmdet - INFO - workflow: [('train', 1)], max: 200 epochs
2024-06-10 17:07:33,221 - mmdet - INFO - Checkpoints will be saved to /public/home/2022050834/Co-DETR-main/work_dir…
-
This project developed a U-Net model for image segmentation, specifically for identifying lunar craters in images. The model was trained on a dataset of lunar images and corresponding masks, with data…