deep-high-resolution-net.pytorch

deep-high-resolution-net.pytorch copied to clipboard

Can the model infer on CPU or only on GPU? Can it infer high resolution image or at max, what resolution of the image can be inferred? Can it perform...

SoumyajitMukherjee-droid

How to download pretrained models

1

hello,I can't install the pretrained models,because the link for me is error,could you please provide me the pretrained models?

STRUGGLE1999

How can I do fine-tuning?

2

Are there any ways to do fine-tunning on my custom dataset?

Juwan-s

Only reason I can think of is my cuda version is 11.7, but the latest version of PyTorch available is for cuda 11.6. Could that be the issue?  ###...

Masum06

CUDA error: out of memory

3

我正在使用两块2080ti训练hrnet，出现了 Out of memory报错 每块显卡有11GB可用显存 我的配置文件是 " experiments/coco/hrnet/w32_256x192_adam_lr1e-3.yaml" 输出报错信息为： I‘m running the train.py with two 2080ti but got a "Out of memery" error. Each of the two gpus has 11GB...

yux326

Where ic config.py

1

I can't find config.py.

sgs01115

Pytroch and tensorboardx versions are not compatible

13

Pytroch =1.7 tensorboardx=1.6 AttributeError: module 'torch.onnx' has no attribute 'set_training' Lib\site-packages\torch\onnx\__init__.py def select_model_mode_for_export(model, mode): r""" A context manager to temporarily set the training mode of 'model' to 'mode', resetting it...

yup1212

At which epoch does the accuracy tend to converge? @leoxiaobin

heduo-star

About the multi-scale MPII test result, i only got 91.6% instead of 92.3% reported in the paper.

40

I have implemented the multi-scale testing, and I have verified that the MPII validation set accuracy is 90.75% I then go on the apply it to the test set and...

MaxChu719

run train.py，such an error occurs cuDNN error: CUDNN_STATUS_NOT_INITIALIZED，who can solve this problem

chuxiaoshuai