WangZ
WangZ
目前没有支持并行方式，可以自己修改代码尝试
显存的占用不仅仅取决于模型的大小，还与模型结构、批量大小等有关。
> > 显存的占用不仅仅取决于模型的大小，还与模型结构、批量大小等有关。 > > 训练ppocrV4的rec(hgent)和det(teacher)需要多大显存啊，老师，btach size较小的情况下 微调det db++的情况下batch size 16的情况下 显存大概消耗 18G， 这两个模型可以根据机器情况测一下
> 就是在不跑的时候，也会占用好几个G. 从模型初始化到就绪，发现一直占着好几G的cpu内存. GPU占810M，CPU内存占2个G左右。从启动以后就一直占着，不跑也一直占着。就算跑，一副图也不会占这么大把？ 框架的加载，数据的预处理后处理等等都是在CPU阶段执行的，因此会占用比较大的内存，显存占用是正常的，输入图像大小的不同，也会导致推理阶段显存使用的不同。
Can you give a more detailed example? Based solely on what you mentioned in your question, there is a scenario where a key points to multiple values in your data,...
Did you use the official model for inference? Have you used the data from the current document for fine-tuning the model?
You can refer to the following document to fine tune the official model to fit your data, including data preparation, starting training, and so on. Chinese document address: https://github.com/PaddlePaddle/PaddleOCR/blob/main/doc/doc_ch/kie.md English...
Thank you. I checked the Huggingface website you provided. It provides all Adet model files, but there is no gt_ctw1500.zip file required to run the evaluation. The file maybe about...
该issue长时间未更新，暂将此issue关闭，如有需要可重新开启。