-
Hello, I have been struggling to recreate the results shown on the detection leaderboard. Can someone provide me with the specific information to recreate?
-
Namespace(alpha=1.0, benchmark=False, beta=1.0, cls_batch_num=6, cls_image_shape='3, 48, 192', cls_model_dir=None, cls_thresh=0.9, cpu_threads=10, crop_res_save_dir='./output', det=True, det_algorithm…
-
请提供下述完整信息以便快速定位问题/Please provide the following information to quickly locate the problem
- 系统环境/System Environment：win10
- 版本号/Version：Paddle： PaddleOCR： 问题相关组件/Related components：
- 运行指令/Comman…
-
Dear @abhinavagarwalla
I replace DCN folder with https://github.com/CharlesShang/DCNv2 to use with latest PyTorch
my Pytorch version is python -c "import torch; print(torch.version)"
1.10.2
DCNv…
-
(rgo-py37-f) fy@neu:~/DCNv2-pytorch_1.9/test$ python test.py
error in modulated_deformable_im2col_cuda: no kernel image is available for execution on the device
error in modulated_deformable_col2im_…
-
Hi, Thanks for your fabulous work.
I have a question Readme.md.
Following your instruction, I tried to build DCN in my conda env
In make.sh which is located in subdirectory of "Deformable-Convo…
-
Hi, I am tryiuse using fp16 in BEVDet (actually the BEVDepth implemented with the BEVDet codebase) with mmcv==1.4.0, torch=1.9, torchvision=0.10.0. However, I encountered this problem:
```
Traceback…
-
I'm training my own dataset using RFLA. I find that the model still use the AITOD metric, though I have change the dataset in config file to 'CocoDataset'.
```python
_base_ = [
'../_base_/datas…
-
Hi, May I know if there is any setting I can use to improve DBNetpp's inference speed? The current inference speed is around 10sec per image.
-
Traceback (most recent call last):
File "/home/toson/softs/pycharm-2018.3/helpers/pydev/pydevd.py", line 1689, in
main()
File "/home/toson/softs/pycharm-2018.3/helpers/pydev/pydevd.py", li…