Thanks for your code! @ifzhang
when i use the pretrained model hrnetv2_w18_imagenet_pretrained.pth or w32 and change the arch into hrnet_18 for training, it will show the error KeyError: 'epoch' 'state_dict', it seems that the pretrained model havs no corresponding cheekpoint.
but when i change the --load model into ' ' and keep the arch 'hrnet_18',it seems to have worked and it shows that i was using hrnetv2_w18_imagenet_pretrained.pth. So if there an illegal training is under way。
Thanks for your code! @ifzhang when i use the pretrained model hrnetv2_w18_imagenet_pretrained.pth or w32 and change the arch into hrnet_18 for training, it will show the error KeyError: 'epoch' 'state_dict', it seems that the pretrained model havs no corresponding cheekpoint. but when i change the --load model into ' ' and keep the arch 'hrnet_18',it seems to have worked and it shows that i was using hrnetv2_w18_imagenet_pretrained.pth. So if there an illegal training is under way。![image](https://user-images.githubusercontent.com/96114577/146504817-26c278f9-5b42-46e4-a5c3-310bb6469e72.png)