Hao Shao

met the same question + 1

Hi, Kin-Zhang 3M frames includes 8 towns * 21 kind of weather. In our work, we only take use of part of towns and weather and the traning dataset size...

> Two minor details to add to this discussion: The CVPR TransFuser you mentioned only uses 150k frames as per their appendix. > > > In the stage of data...

> Thanks for @Kait0 pointing out here detail. And I check the [TPAMI'22] Transfuser training data are around 228k frames in total which is also smaller compared with others. Is...

> Yes, std > 0 and is a small number. So we claim the dataset is **redundant** not the **same**.

Thanks, i will leave the discussions here and there are two points needed to be clarified: 1) 3000k data size is the full size of the dataset, we dont use...

@Kait0 @Kin-Zhang Thanks for your disscussions. I will compelete the ablation studies about dataset size and update the results here.

The simulatior run at 20 fps which is same as official leaderboard, and we collect data for 2 frames each second.

用一个分词库训练出来的模型肯定是只适用于该分词库的，可以理解成分词模型也是整个模型的一部分，所以你这种尝试理论上就不太对。然后你训练的模型泛化性可能也不强，我看了一下你的example里的差异的地方，感觉效果差不多，谈不上谁好谁坏。 目前产生差异的问题估计主要是自定义词典的问题，有新的进展我会update上来。

> 长文本分词： > jieba_fast: 7m15.049s > jieba: 7m16.053s 加速接口仅支持jieba.lcut, jieba.lcut