-
Thanks for sharing the code!
I have tested the repo on DOAI 1.5 and submit it to the online evaluation task 1. But the result is too low.
```
mAP: 0.07475452980149473
ap of each class: plane:0.…
-
Hi Everyone
In the object detection api, What's difference between *_fpn models and those models that don't have *_fpn ? Those models that have *_fpn, in these models used Feature Pyramid Networks?
-
### Search before asking
- [X] I have searched the Ultralytics YOLO [issues](https://github.com/ultralytics/ultralytics/issues) and [discussions](https://github.com/ultralytics/ultralytics/discussion…
-
-
I have 1 GPU,and i run the code for 4000iters.
Before testing, I copyed DynamicSoftLabelAssigner to ConsistentTeacher-main\thirdparty\mmdetection\mmdet\core\bbox\assigners
and change __init__.py
…
-
我是在paddleDetection导出的模型
我的导出流程如下：
1.设置配置文件 faster_rcnn_swin_tiny_fpn_3x_coco.yml
export_onnx: True
batch_size: 1
2.运行paddleDetection的export_model.py
!python tools/export_model.py -c configs/fast…
-
Hi
I am getting following error if i use resnet50-fpn backbone. mobilenet just works fine. Could you help me.
Traceback (most recent call last):
File "/Users/Mansoor/PycharmProjects/pythonProj…
-
https://github.com/czczup/ViT-Adapter/blob/94ffa6b6134b99d838312e2e042d6ac3a52a7ef8/detection/configs/mask_rcnn/dinov2/mask_rcnn_dinov2_adapter_large_fpn_3x_coco.py#L47
has all 127.5 values rather …
-
Hi @duzhixing
Thanks for your great work! I have 2 questions about FRS.
Firstly the paper says FRS is more suitable for detectors with FPN moudle. I wonder if FRS can also improve perfomance on de…
-
According to the log, the mAP of faster-rcnn_r50_fpn_1x_voc0712 is 0.804 in MMdetection version 2.22. However, I could only achieve 77.9 mAP in MMdetection version 3.3, even though the configuration i…