Lite-HRNet

Lite-HRNet copied to clipboard

您好，我测试您的模型18——256×192的模型得到的和您论文的结果不一样，我测试的结果是AP=64.4，论文是AP = 64.8。不知道我哪里出问题，而且我训练的到结果更低63.3，我是单卡2080ti

zouxuelian

怎么通过模型配置文件对模型进行剪枝？

1

APeiZou

Not able to download the test jsons?

1

When I tried to download the MPII converted json files following error orrcurs: ``` This XML file does not appear to have any style information associated with it. The document...

sourabhyadav

ImportError: cannot import name 'build_posenet' from 'models' (unknown location)

2

who can help to solve this error,Thanks!

zstuli

Could you provide ONNX format exporting code?

13

Hi This is awesome lightweight networks!! I want to test it on other mobile device. Could you provide ONNX format exporting code? Thanks a lot!!

polor1010

Our new study on lightweight high resolution networks: Dite-HRNet

1

Hi, thank you so much for your excellent work. Based on your research on lightweight high resolution networks, we have done some further exploratory studies. Our paper was accepted by...

ZiyiZhang27

onnx problem

5

how to convert to onnx, I meet the problem, assert target.dim() == 4 and target_weight.dim() == 3 AttributeError: 'NoneType' object has no attribute 'dim' code: model = build_posenet(cfg.model) load_checkpoint(model, args.checkpoint,...

jxncyym

KeyError: 'LiteHRNet is already registered in models'

10

there is a problem KeyError: 'LiteHRNet is already registered in models' how to solve it thanks

LiFeiBiao

Traceback (most recent call last): File "./tools/train.py", line 166, in main() File "./tools/train.py", line 155, in main train_model( File "/mnt/DATA/AI/project/Lite-HRNet-hrnet/venv/lib/python3.8/site-packages/mmpose/apis/train.py", line 200, in train_model runner.run(data_loaders, cfg.workflow, cfg.total_epochs) File "/mnt/DATA/AI/project/Lite-HRNet-hrnet/venv/lib/python3.8/site-packages/mmcv/runner/epoch_based_runner.py", line...

xukefang

linux train error

1

 how to solve this problem，thank you very much!

wangm-word