HalvesChen

Results 7 issues of HalvesChen

The error arises in follow command: ``` import pclpy ``` How do I solve it?

**操作系统信息** ubuntu 20.04 python 3.8 。。。 **错误描述** 下载文件出错 ![image](https://user-images.githubusercontent.com/55949813/229274876-d85476c4-533d-43f2-ab8f-943c4c689e41.png) 。。。

Hello, I'm confused by the parameter settings that are over-segmented on scannet test set. The author of scannet-v2 does not provide test scenes '*.seg.json' . I want to generate it...

Hi, thanks for you job, could you show us how your model performs on MS-COCO?

Hi~ Thank you for your work. I would like to know if you have compared the ablation experiments on the LAION-COCO fine-tuning.

LazySupervisedDataset的token_length计算感觉存在问题。在线计算token_length的时候,第一次计算的token_length是input_id的长度。而保存到字典conv2length中的value却是input_id加上图片token的长度。 ``` if self.group_by_length: self.conv2length = {} # Using a dictionary to speed up token length calculation self.length = [] for data_item in self.raw_data: data_item = json.loads(data_item) if 'length' in...