Li Shihao

数据集中混合使用了多边形标注和RLE编码，但是RLE编码的格式似乎有错误

3

例如，其中某个分割标注是这样的： `"segmentation": { "counts": [ 14400 ], "size": [ 120, 120 ] },` 但是RLE编码的counts应该是一个字符串的编码，而不是一个int为元素的list，请告诉我如何处理这个数据

完整的错误输出： `ERROR: Exception in ASGI application Traceback (most recent call last): File "D:\anaconda3\envs\AniPortrait\lib\site-packages\pydantic\type_adapter.py", line 271, in _init_core_attrs self.core_schema = _getattr_no_parents(self._type, '__pydantic_core_schema__') File "D:\anaconda3\envs\AniPortrait\lib\site-packages\pydantic\type_adapter.py", line 55, in _getattr_no_parents raise AttributeError(attribute) AttributeError:...

Bug Report: ValueError in DataCollator when processing sequences of different lengths during embedding

3

**Description** When running the embedding pipeline, the system encounters a ValueError due to tensor shape mismatch in the DataCollatorForSupervisedDataset class. The error occurs when trying to convert input_ids lists of...

Transformers 上的InternVL3.0模型推理代码是否不可用于InternVL3.5?

10

https://huggingface.co/docs/transformers/v4.55.4/en/model_doc/internvl#video-input 此处如果将模型换为InternVL3.5系列，对样例视频输入仍报错：shape '[8, 27, 13, 2048]' is invalid for input of size 5971968，如何解决，这是否是一个错误。