向峻宏

[Bug] error: cannot declare variable ‘mmdeploy::status_domain’ to be of abstract type ‘mmdeploy::StatusDomain’

3

### Checklist - [X] I have searched related issues but cannot get the expected help. - [x] 2. I have read the [FAQ documentation](https://github.com/open-mmlab/mmdeploy/tree/main/docs/en/faq.md) but cannot get the expected help....

yolov8 inference

3

请问一下为什么yolov8 end2end的推理，warmup和没有warmup时间相差这么多吗？没有warmup大概700ms，有warmup只有6ms，Infer函数不都是执行的图片放入gpu，然后推理结果从gpu放到内存吗？难道是warmup之后，图片不需要从内存到gpu了吗？ 另外，如果我是处理视频，需要实时从视频帧读取到gpu，这应该是没办法用warmup吧？这应该怎么处理？

代码有误

1

代码写的有问题，没考虑裁剪图中没有标注点的情况，而且多卡训练也没有实现

exposure question

3

I have a question. Is the training data used by the author the same as the one released? I trained my own model, but it has overexposure issues, for example:...

Hello, author. Thanks for your work! I found that there is a problem with your code. The length of self.feature_loss_module should be 1, which is not equal to the length...

olmocr bench evaluation

1

Can I use the sample data provided in the bench to evaluate my own pipeline? However, I found that the PDF annotation in dataset.jsonl is too simple. What is the...

I encountered the following problem when using llama cpp python on Mac. The model's answer is completely unreasonable. The red box contains the question and answer.  The configuration is...

mmstar dataset

1

I deployed the InternVL3_5-241B-A28B model and tested it on the mmstar benchmark, but the accuracy I got was only 73.76%. I'd like to know how the paper came up with...