-
MMDetection의 base model을 돌려본다.
-
**Describe the bug**
When using ViT as a backbone in Faster R-CNN, the bbox mAP is always 0 during validation, even though the training loss is decreasing normally. The training shows normal loss val…
-
### log:
12/04 16:06:52 - mmengine - INFO - Evaluating bbox...
Loading and preparing results...
DONE (t=0.01s)
creating index...
index created!
Running per image evaluation...
Evaluate annotati…
-
when running
python setup.py develop
in pytorch1.9 version using docker, with environment as python==3.8, torch==1.9.0 and cudatoolkit==11.0,
there exist error:
/opt/conda/envs/s2anet/compil…
-
How can i train my custom dataset ? Do i need to label the images in VOC format with Labelimg ? How should i prepare the dataset for VarifocalNet training ? Looking forward to your reply ! And really …
-
I cannot find tutorials or if mmdetection produces results of images with annotations when evaluating while training as well as mAP metric.
-
**Notice**
There are several common situations in the reimplementation issues as below
1. Reimplement a model in the model zoo using the provided configs
**Checklist**
1. I have searched r…
-
Traceback (most recent call last):
File "/home/li/testcode/tool2/convert_dataloader.py", line 490, in
fp_model = copy.deepcopy(convert(onnx_model).to(device))
File "/home/li/.local/lib…
-
### Prerequisite
- [x] I have searched [Issues](https://github.com/open-mmlab/mmdetection/issues) and [Discussions](https://github.com/open-mmlab/mmdetection/discussions) but cannot get the expected …
-
### Prerequisite
- [X] I have searched [Issues](https://github.com/open-mmlab/mmdetection/issues) and [Discussions](https://github.com/open-mmlab/mmdetection/discussions) but cannot get the expected …