SHL
maybe change the same version of CUDA、cuDNN and tensorrt as mine? my enviroment: ``` windows 10 CUDA 11.1 cuDNN 8.0.5 TensorRT 8.2.5.1 ``` or ``` ubuntu18.04 CUDA 10.2 cuDNN 7.X(I...
https://zhuanlan.zhihu.com/p/529642068
I'll try fix this later, during this time you can try to fix the code by yourself as what above says.
coco原数据集能跑起来没问题说明dataloader代码没问题，可能这个代码对数据集的规范性的要求比较高，实在不行的话就转yolo格式吧。
it means there's at least one image with empty label in your val dataset, just check your txt files and remove the empty files, then set use_cache to false to...
> I got the same error and discovered that the problem in my case was caused because of different image formats mingled. By default, the Yolo dataloader takes only the...
这个错误报的是没有读取到cfg文件的参数，请检查训练的cfg文件（示例在文件夹params/train下）位置是否填写正确
具体步骤请按照[README](https://github.com/LSH9832/edgeyolo/blob/main/README_CN.md)中的说明进行，目前支持COCO/VOC/DOTA/VisDrone四种数据集格式（示例在params/dataset下），如为其他格式数据集需要进行格式转换
it means it detects nothing in validate dataset. here are some suggestions. 1. if there's only small amount of images in your dataset, use the pretrained model in coco dataset...
如果使用cpu训练的话，需要自行改代码