-
-
213sdfsdf
-
### Requested Feature
RIF export ratios need adjustment:
- ratio of types of claims overall
- ratio of claim types per bene
- ratio of lines per claim type
```
Claim Ratio = Claim of Type / …
-
I am trying to do a custom DPO fine-tuning for `internvl_v2_internlm2_2b_lora_finetune`, but the default config is oriented towards vanilla supervised fine-tuning with images. I tried to compare / inc…
-
I think it would be a big time-saver to allow regex rules for matching a lot of lines to the same design icon.
For example, i've managed to break almost 300 Bus and Ferry lines that share a number …
-
hha
-
When training on NYUv2 dataset, did you use HHA encoding image as inputs or did you just use the colorization depth images? Furthermore, did you crop the white border of depth images?
-
When I use the finetuning commands that print out to finetune the CNN,
'jobName = 'hha_cache_features'; I saw the script_detection.m file,there is a code ' the ' net_file = fullfile_ext(p.snapshot_…
-
作者，您好！非常感谢您的开源贡献。我目前对于将cityscapes的深度图disparity转为HHA格式十分困惑，因为我不知道使用disparity数据提供的相机参数通过如下代码计算是否正确？通过如下方式我得到的HHA格式的图片与您在论文提到完全不一样！如果您能开源对cityscapes中disparity的depth转换为HHA格式的代码，我将不甚感激！
![SF )I(@1KJ3_M)4L…
-
作者您好，我想问一下，关于NYUD数据集，我已经训练完HHA和RGB类型的数据集，但是文章中的HHA-RGB类型是如何测试的，我看文章中说需要平均HHA和RGB的边缘结果，具体怎么实现，是使用HHA数据集训练好的模型去训练RGB吗？