gaowq2017
gaowq2017
+1 BTW the work same to 'few shot' leanning that used prototype, Thanks
@wenguanwang Thanks for your great work. I am agree that Prototype learning isn't only few-shot learning. I look forward to more similar work, thanks
when update the link of the pre-trained model
I also have same issue especially in 'Compute loss and scores on test set'. It have easily unknow error when run to caculating the segmentation AUROC. BTW i used MobileNet_V3_large.
> Thanks for your interest in our work. As explained in the comment of the referenced code `self.source[i1]` samples a new crop from i1. The cropping is included in the...
Hi @AlessioGalluccio, I haven't update the version of torch and the code can run. The detial as follow:  Only change this way.
The same looking forward to openning the full code!
> 用的python版本是多少 python3.9
> 建议尝试一下PaddleOCR2.7.0试下呢，另外能贴一下报错信息吗 安装paddleocr==2.7.0时提示PyMuPDF这个包build失败！具体为：ERROR: Could not build wheels for PyMuPDF, which is required to install pyproject.toml-based project 以下是具体的错误信息 /Users/theoyu/miniforge3/envs/py39/lib/python3.9/site-packages/lmdb/__pycache__/lmdb_cffi.c:268:14: fatal error: 'preload.h' file not found #include "preload.h" ^~~~~~~~~~~ 1 error generated....
> 可以尝试clone PaddleOCR套件代码，采用自定义安装的方式`cd PaddleOCR; pip install -e .` 试过了，可以安装，但是import还是同样的错误，我怀疑是我的编译器有问题