Long-Tailed-Recognition.pytorch

Long-Tailed-Recognition.pytorch copied to clipboard

Cifar experiment setting

15

Thank you for sharing your interesting work. Would you mind clarify some of the Cifar experiment setting: 1. Does the Cifar result in the paper initialised using Imagenet pretrained? If...

anthonytmh

Lvis setting

1

您好，我看到在config里，coco和lvis的num_class分别设置为80和1203,想请教一下这里为什么没有算背景呢？非常感谢～

xinqiaozhao

咨询

3

您好，我有个问题，您说 狮鹫=狮子+鹰，这个是类别之间差异比较大的可以利用头部类信息；但是像细粒度分类任务中，每类之间都很相似，也存在着严重的长尾分布，这个还能借用头部类的信息么？即：狮鹫=狮子+鹰？？

gengyanlei

Where and when can I get the paper

3

interesting work! If it is convenient, can you sent the paper to me? [email protected] thanks.

zwzhang123

感谢本文贡献的优秀idea，但是多头分类器在训练过程中会导致loss和权重会突然变成nan，这个问题麻烦关注一下

gaoxueyi0532

# Welcome update to OpenMMLab 2.0 I am Vansin, the technical operator of OpenMMLab. In September of last year, we announced the release of OpenMMLab 2.0 at the World Artificial...

vansin