search

KaihuaTang / Long-Tailed-Recognition.pytorch

[NeurIPS 2020] This project provides a strong single-stage baseline for Long-Tailed Classification, Detection, and Instance Segmentation (LVIS). It is also a PyTorch implementation of the NeurIPS 2020 paper 'Long-Tailed Classification by Keeping the Good and Removing the Bad Momentum Causal Effect'.
GNU General Public License v3.0
555 stars 68 forks source link

imagenet-LT #25

Open xiaohua-chen opened 3 years ago

xiaohua-chen commented 3 years ago

Thank you, the author, would like to ask how to generate Imagenet LT, according to what rules are sampled out

KaihuaTang commented 3 years ago

ImageNet-LT is generated based on the code of https://github.com/zhmiao/OpenLongTailRecognition-OLTR For fair comparisons, we directly use the same ImageNet-LT subset created by https://github.com/facebookresearch/classifier-balancing

xiaohua-chen commented 3 years ago

嗯嗯，非常谢谢您(*°∀°)=3，我试一试哈 祝您身体健康，学业顺利，生活愉快每一天~

🌸🌸🌸🌸🌸🌸

---Original--- From: "Kaihua Tang"<notifications@github.com> Date: Fri, Nov 27, 2020 14:23 PM To: "KaihuaTang/Long-Tailed-Recognition.pytorch"<Long-Tailed-Recognition.pytorch@noreply.github.com>; Cc: "CXShan"<1587905087@qq.com>;"Author"<author@noreply.github.com>; Subject: Re: [KaihuaTang/Long-Tailed-Recognition.pytorch] imagenet-LT (#25)

ImageNet-LT is generated based on the code of https://github.com/zhmiao/OpenLongTailRecognition-OLTR For fair comparisons, we directly use the same ImageNet-LT subset created by https://github.com/facebookresearch/classifier-balancing

— You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub, or unsubscribe.