ICDAR2021_MFD
ICDAR2021_MFD copied to clipboard
1st Solution For ICDAR 2021 Competition on Mathematical Formula Detection(公式检测冠军方案)
@Yuxiang1995 谢谢你做的这个项目,我想用你这个来试一下把公式的坐标从图片里面提取出来,但是不知道怎么用,我看到了Inference的说明,但是不明白这个`checkpoint path`需要放什么。我试过放`mfd_gfl_s50.pth`,但好像没有用。而且我还有个疑问,按理说我需要把待解析的图片传进去跑,但是要怎么传进去呢?
While I was caluclating the inference with CPU through image_demo.py , I am getting the following  It is working fine when , I was using the GPU. Can anyone...
I am getting this AssertionError: Default process group is not initialized error while training the program . Can anyone help me
 根据您提供的预训练模型进行推理,发现在Ts10上的测试结果并不理想,采用的是s50模型,评估命令如下  不知道是哪里出现了问题
 单卡训练多卡训练都会报这个错误 pred比weight多了一个维度为4
To use the quality focal loss did you passed to it the quality score like [0.1 0.6 0.2 0.4] or you passed the onehot from the target like [0 1...