BowenXu
BowenXu
I am now reproducing yolov6l, the default settings width 1.0 and depth 1.0 shows that level of speed is twice as yolov5l and yolov7, and flops is four times, is...
If I understand correctly, the finetune of repopt needs to start from the model yolov6s_scale.pt every time, there is no way to continue finetune on the basis of an already...
senlinuc你好，感谢你的repo。 （1）请问有基于VGG Synthetic Word Dataset数据集的预训练模型可以提供下载么， 我现在测试了基于中文数据的Denseblock网络的识别效果，发现几乎只能识别印刷体的中文字符，这是由于训练样本造成的么
Hi, thank you for your great work, I am now trying to cast rope3d datasets label into 2d image, but i always get wrong results, the cast code works well...
如题。
Hi，thank you to the friends at the Hikvision Research Institute for open-sourceing your paper source code. we have implemented a semi-supervised object dection for YOLOv5, and in the design of...
Hi! During the process of fine-tuning Llama by following the tutorial, I only received warnings related to the scaling factor used in mixed precision training and did not receive any...
When I was developing a semi-supervised detection library, I followed your work closely. I was sorry to see that your paper was withdrawn from ICLR, but congratulations on getting it...