Forteee

Thank you for your prompt reply！ 1) before: {'spacing': array([1., 1., 1.]), 'spacing_transposed': array([1., 1., 1.]), 'data.shape (data is transposed)': (1, 51, 576, 764)} after: {'spacing': array([1.282432, 1.282432, 1.282432]), 'data.shape...

Hi, My fault(＃－.－), I was trying to say 3D ultrasound images. Sorry about the misunderstanding. I have re-edited the issue I have attached the whole dataset and my own data...

Thanks a lot, I'll send you the corresponding splits_final.pkl file later. Best Fabian Isensee ***@***.***> 于2022年3月4日周五 16:39写道： > Just to let you know that I am currently running a training....

Hi, Fabian Thank u for your reply, which is quite useful to me. I have been struggling with this dataset for a long time. As u said I should start...

> 有没有详细一点的web_demo推理部署流程？按readme去做，接连报错。 1、先是报 Repo is must be in the form ‘repo_name’ or namespace/repo_name......，排查是readme中“mv demo_VITA_ckpt/config.json demo_VITA_ckpt/origin_config.json”这句话把config.json去掉了，把config.json补上，问题解决。 2、然后遇到 limit_mm_per_prompt is only supported for multimodal models. 把limit_mm_per_prompt={‘image’:256, 'audio':50}注释掉，问题解决。 3、又遇到vllm中['VITAQwen2ForCausalLM'] are not supported for...

完全相同的问题，只使用了图片和文本构成的数据进行按照文档提示进行微调，微调后model.safetensors.index.json和之前相比少了tts的439层，模型大小相应的也笑了一些，使用之前的部署方法就无法正常部署了