GOODJUICE

可以用来评估在NYUD和Multicue数据集的结果吗？

1

原始文件夹里没这两个gt文件夹

Thanks for your work, does the training code mean that I can use my labeled segmented data containing one class to train a model that segments only that one class?...

about the train code

4

Thanks for your work, does the training code mean that I can use my labeled segmented data containing one class to train a model that segments only that one class?...

修改问句搜索知识库方法

1

**功能描述 / Feature Description** 您好，请问怎么改成langchain原版的similarity_search_with_score_by_vector呢 **解决的问题 / Problem Solved** server/knowledge_base/kb_service/faiss_kb_service.py中的 with self.load_vector_store().acquire() as vs: docs = vs.similarity_search_with_score_by_vector(embeddings, k=top_k, score_threshold=score_threshold) 没有找到similarity_search_with_score_by_vector在哪里实现的 请问怎么修改

cant use GPU

4

thanks for your great work! but i cant use GPU in anylabeling-gpu error： [ WARN:[email protected]] global net_impl.cpp:178 cv::dnn::dnn4_v20230620::Net::Impl::setUpNet DNN module was not built with CUDA backend; switching to CPU how...