super-song-sir

The number of val images for validation during training is not equal to the val datasets

2

### Search before asking - [X] I have searched the YOLOv8 [issues](https://github.com/ultralytics/ultralytics/issues) and [discussions](https://github.com/ultralytics/ultralytics/discussions) and found no similar questions. ### Question I get a problem when I train my own...

About code modifications

1

Since the content of the file uploaded to kaggle cannot be modified, can I modify the file uploaded to kaggle after connecting remotely via SSH?

RuntimeError: CUDA error: CUBLAS_STATUS_INVALID_VALUE when calling cublasSgemv(handle, op, m, n, &alpha, a, lda, x, incx, &beta, y, incy)

7

当我使用命令 model = YOLOv10('yolov10n.yaml')选定模型后，训练yolov10n.yaml时，进行完一个epoch周期训练再进行验证时会报错CUDA error: CUBLAS_STATUS_INVALID_VALUE when calling `cublasSgemv(handle, op, m, n, &alpha, a, lda, x, incx, &beta, y, incy)`。并伴随有警告UserWarning: __floordiv__ is deprecated, and its behavior will change in a...

关于Query Selection

1

您好，我在rtdetr论文中看到有关Uncertainty-minimal Query Selection的介绍，但是在代码介绍中看到的是IoU感知查询选择，请问这两个是相同的吗？还是后续的代码中采用了IoU感知查询选择而非Uncertainty-minimal Query Selection

在windows10环境下运行代码出现报错RuntimeError: Default process group has not been initialized, please make sure to call init_process_group.运行指令： python train.py -c configs/dfine/dfine_hgnetv2_n_coco.yml --use-amp --seed=0