roywang021

why + torch.lgamma(ones).sum(dim=1, keepdim=True) in kl_divergence?

2

Torch.lgamma(1)=0 and no such term in the original paper

roi head中背景类数量占比过高

1

注意到你的代码，roi head中背景类数量过高，占比约为4000/4096，是否是roi head的proposal采样没有成功？

请问一下21-80类的有做什么特殊处理么

1

作者您好，请问一下21-80类的预测概率在训练/测试阶段有做什么特殊处理么？

Running command python setup.py egg_info error: Multiple top-level packages discovered in a flat-layout: ['data', 'engine', 'solver', 'config', 'modeling', 'evaluation'].

1

Running command python setup.py egg_info error: Multiple top-level packages discovered in a flat-layout: ['data', 'engine', 'solver', 'config', 'modeling', 'evaluation'].

Test on the RealToxicityPrompts Dataset

1

We fed clean.jpeg (panda) into the llava model to calculate the toxic scores and found that there were also 50~60%, do you have the same results