This is an official implementation of our CVPR 2020 paper "HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimation" (https://arxiv.org/abs/1908.10357)
MIT License
1.35k
stars
272
forks
source link
RuntimeError: CUDA error: no kernel image is available for execution on the device #98
Hello, I am currently trying to run the single-scale testing code of HRNet using the following command:
python tools/valid.py \ --cfg experiments/coco/higher_hrnet/w32_512_adam_lr1e-3.yaml \ TEST.MODEL_FILE models/pytorch/pose_coco/pose_higher_hrnet_w32_512.pth
I am able to load the model, but soon face the following error: RuntimeError: CUDA error: no kernel image is available for execution on the device
Does anyone know what is causing this? PS: I have installed cuda 10.1 in the environment with pytorch 1.4