AnchorCaptioner配环境
代码:
https://github.com/guanghuixu/AnchorCaptioner
paper:
Towards Accurate Text-based Image Captioning with Content Diversity Exploration
配环境
conda env create -f textcap.yaml
conda activate textcap
git clone git@github.com:guanghuixu/AnchorCaptioner.git
cd AnchorCaptioner
python setup.py build develop
conda env create -f textcap.yaml时pip报错
解决方式:打开textcap.yaml
找到未安装完成的文件 装入textcap_pip.txt中
执行:
pip install -r textcap_pip.txt
pycocoevalcap安装问题
pip install "git+git://github.com/salaniz/pycocoevalcap.git"
参考:
- https://blog.csdn.net/mr_muli/article/details/108686465?utm_medium=distribute.pc_relevant.none-task-blog-2defaultbaidujs_title~default-0.pc_relevant_default&spm=1001.2101.3001.4242.1&utm_relevant_index=3.
- https://blog.csdn.net/Peggiehu/article/details/120658066
4002中配置完成
具体复现需要参考M4C-Captioner
https://github.com/guanghuixu/AnchorCaptioner/blob/main/projects/M4C_Captioner/README.md.