HFT-CNN 模型复现（论文 Learning Hierarchical Category Structure for Multi-label Short Text Categorization）

HFT-CNN: Learning Hierarchical Category Structure for Multi-label Short Text Categorization (2018 EMNLP)

开源coding GitHub

https://github.com/superrichiesui/HFT-CNN
https://github.com/ShimShim46/HFT-CNN

下载这个项目到本地，这个要用到CUDA，对显卡有一定要求

官方说使用yml文件安装，但是出现问题，涉及到版权问题，从2019年4月添加的国内镜像都不能用了，需要使用默认源，但是默认源下载很慢，经常超时，左右为难.....

conda env create -f=hft_cnn_env.yml

The remote server could not find the noarch directory for the

requested channel with url: file:///C:/Miniconda36-x64/conda-bld

As of conda 4.3, a valid channel must contain a `noarch/repodata.json` and

associated `noarch/repodata.json.bz2` file, even if `noarch/repodata.json` is

empty. please request that the channel administrator create

`noarch/repodata.json` and associated `noarch/repodata.json.bz2` files.

HFT-CNN 模型复现（论文 Learning Hierarchical Category Structure for Multi-label Short Text Categorization）

猜你喜欢