Johannes
Johannes
 Hi there! I was really impressed by the visualization results in the paper. I managed to find the code for visualizing spotting results in the repository, which was helpful....
I can not run even bs=1 on my 4 4090s, with torch.cuda.OutOfMemoryError: CUDA out of memory. Need help ,thanks
倾斜文字如何检测
你好,我发现qwen-vl对[xmin ymin xmax ymax]这样的bbox坐标的视觉理解较好,比如我说识别某个区域的文字可以做的很好 但是如何解决倾斜文本的问题呢,因为这个格式只能包含一个最大的外包围框。Qwenvl应该不能直接输出polygon定位?