-
(D_FINE) ➜ D_FINE CUDA_VISIBLE_DEVICES=1,4,5,6 torchrun --master_port=7777 --nproc_per_node=4 train.py -c configs/dfine/custom/dfine_hgnetv2_${model}_custom.yml --use-amp --seed=0
[2024-10-30 19:35:…
-
**Dont work tuning from checkpoint from [README.txt](https://github.com/lyuwenyu/RT-DETR/tree/main/rtdetrv2_pytorch#base-models)**
---
**ModuleNotFoundError: No module named 'cvperception'**
```
…
ksv87 updated
2 months ago
-
### 问题确认 Search before asking
- [X] 我已经查询[历史issue](https://github.com/PaddlePaddle/PaddleDetection/issues)，没有发现相似的bug。I have searched the [issues](https://github.com/PaddlePaddle/PaddleDetection/issu…
-
@lyuwenyu 你好，自有数据，原图为1920*640（w*h）的图片，eval_spatial_size设置为[1920, 640] # h w时，训练3个epoch，指标能到73%， 但是eval_spatial_size修改为[640, 1920] # h w，即原图宽高训练，指标反而无法训练起来，训练30个epoch最高就是0.2的样子，其他设置相同，这个是啥原因呢？
训练配置基于r…
-
十分感谢您的卓越工作，在更换backbone时，我已经将新的backbone通过register注册过了，新的config文件也添加了，加载模型时，core中的workspace中报错显示
Traceback (most recent call last):
File "D:\Medical_segmentation\Kingmed\RT-DETR-main\rtdetrv2_pytorc…
-
I got this error:
Traceback (most recent call last):
File "C:\Users\m.rahamneh\Documents\MiTool\det\app\detection\model_hub\rtdetrv2\rtdetrv2_torch.py", line 83, in
main(args)
File "C:\Us…
-
Hello,
I installed rtdetrv2_pytorch with requirements text but It didn't work in the below code
`CUDA_VISIBLE_DEVICES=0,1,2,3 torchrun --master_port=9909 --nproc_per_node=4 tools/train.py -c path/…
-
### 问题确认 Search before asking
- [X] 我已经查询[历史issue](https://github.com/PaddlePaddle/PaddleDetection/issues)，没有发现相似的bug。I have searched the [issues](https://github.com/PaddlePaddle/PaddleDetection/issu…
-
Will the training logs of rtdetrv2 be released？
I run rtdetrv2-r18 120 epochs and rtdetrv-r18 100epochs on coco2017_25k(Sampling 25k images from coco2017), and I get same ap on this two models. Is it…
-
非常感谢您更新RT-DETRv2，但是我有一些问题，在新的configs/rtdetrv2/xxx.yml中rtdetrv2_r18vd_120e_coco.yml 中的120e表示什么？1x/3x/6x/7x中的数字表示什么，是decoder的数量么