mmdetection-distiller

mmdetection-distiller copied to clipboard

# 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

Thanks for your error report and we appreciate it a lot. **Checklist** 1. I have searched related issues but cannot get the expected help. 2. I have read the [FAQ...

laisong127

Traceback (most recent call last): File "./tools/train.py", line 190, in main() File "./tools/train.py", line 186, in main meta=meta) File "/home/syy/MixD/mmdet/apis/train.py", line 154, in train_detector runner.run(data_loaders, cfg.workflow, cfg.total_epochs) File "/home/syy/anaconda3/envs/fgd/lib/python3.7/site-packages/mmcv/runner/epoch_based_runner.py", line...

kobesyy

请问这个repo还在继续维护吗

4

aiboys

QR code expired.

4

Hi, could you please update the QRcode of wechat group?

yarkable

再训练过程中 models/backbone/resnet.py的599行：load_checkpoint(self, pretrained, strict=False, logger=logger)会出现bug，请问是为什么

zengbohan0217

我看项目中resnet50的教师网络是resnext101_64x4d，那resnet101的teacher又是哪个呢？是否需要用精度更高的模型对其进行蒸馏(论文里说teacher的精度越高，蒸馏效果越好)。此外用同样的网络结构自己蒸馏自己，模型精度会有提升么？

HAOCHENYE