mafeng

>  1、有底纹时，分割不准。2、负数情况需要添加字符识别。3、表盘浓度过高，识别有错。  存在问题： 1、指针仪表盘为倾斜状态 2、仪表刻度有负数如何解决

Is there a solution

(base) D:\软件安装\labelme\cvat-2.14.4>labelme 2024-06-28 11:58:14,133 [INFO ] __init__:get_config:67- Loading config file from: C:\Users\Administrator\.labelmerc Traceback (most recent call last): File "D:\Anaconda3\lib\site-packages\labelme\widgets\canvas.py", line 973, in keyReleaseEvent index = self.shapes.index(self.selectedShapes[0]) ValueError: is not in...

 Use the smaller image as a template and match it to determine where in the larger image. Match error, what method can solve

>  使用较小的图像作为模板，匹配以确定较大图像中的位置。匹配错误，有什么方法可以解决 Who can help me answer this question, thank you very much

> 到底哪里出了问题？ python versions, torch versions are always problematic, so I wanted to provide a reference environment

  I am also eager to know how to generate such images using match_keypoints？

> 你好，我今年夏天不在家，九月初会带着一些演示回来。 Special look forward to, excellent algorithm let people worship. I hope to see a detailed explanation then, thank you

I found that the algorithm did not work well for small objects and was not rotation invariant. Is there any solution?

> 上述问题似乎与[map_location 参数](https://stackoverflow.com/questions/53186736/runtimeerror-attempting-to-deserialize-object-on-cuda-device-2-but-torch-cuda-d)有关，为了解决：替换[此处](https://github.com/UditSinghParihar/RoRD/blob/main/lib/model_test.py#L62)的 行`self.load_state_dict(torch.load(model_file)['model'])`[](https://github.com/UditSinghParihar/RoRD/blob/main/lib/model_test.py#L62) > > 和 ： `self.load_state_dict(torch.load(model_file, map_location='cuda:0')['model'])` > > 如果有帮助的话请告诉我:) Solved thanks