-
hi,I use my own dataset for training，but i got this error:
Traceback (most recent call last):
File "mmdetection-3.x/tools/train.py", line 133, in
main()
File "mmdetection-3.x/tools/train.…
-
-
Issue description
Attempting to run Detectron 2, getting the above error
Code example
python demo.py –config-file ../configs/COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_3x.yaml --webcam \ --opts…
-
I used this config [e2e_mask_rcnn_R_101_FPN_4x_voc_coco_aug_cocostyle] to retrain and seems like the model is not trained correctly with the two new losses for mask ?, After training the result for ma…
-
Can anyone use this mothed in YOLOV4?
author says
"CDIoU and CDIoU loss have
different excellent performances in several models such as
Faster R-CNN, YOLOv4, RetinaNet and ATSS. There is a
maximu…
-
Under some (failure) condition, ParallelQuery somehow gets a response that it cannot process for error reporting. This is reported as:
```python
2023-12-12 17:56:27,885 : ERROR : aperturedb.Paral…
bovlb updated
2 months ago
-
When exporting a panoptic_fpn from detectron 2, there is the following subgraph in the onnx graph. The subgraph follows the NMS in the RPN. For my application, I would like to understand where the `If…
-
Hello, thank you for your work. I’m having a bit of difficulty using your sbir_baseline to reproduce the Siam.-VGG16 results from your paper when training and evaluating on FS-COCO for the FG-SBIR tas…
-
Hi, thank you for sharing your work. Would you be able to share your trained weights for the BCNet + Faster R-CNN (with ResNet-50 backbone) model trained on COCO train2017, which you reported on Table…
-
I train the model on both train and evl coco dataset as a result my model generates output in .ckpt format which i prior use for estimation of pose but i am confuse how i can get the .json file for ev…