Inference with CPU

[bardia-esm]

Hi. I read issue #3 (https://github.com/Naman-ntc/Pytorch-Human-Pose-Estimation/issues/3) on using pretrained models so I tried to do as you mentioned in the issue:

However, I get this error:

Since I can not use a gpu. I was wondering if inference is possible with CPU only. If so, i would really appreciate it that you explain where i'm doing wrong

[Naman-ntc]

I realize, the dataloader for coco (check datasets/COCO folder) requires gpu. Therefore it throws the provided error. In case you want to use dataloader for MPII a hack could be to remove certain includes from coco.py in datasets folder (you may need to handle other errors of class not defined which can be done via creating temoporaly classes!)

[bardia-esm]

Oh I understand

Thank you Regards

On Wed, Jul 24, 2019 at 12:54 AM Naman Jain notifications@github.com wrote:

I realize, the dataloader for coco (check datasets/COCO folder) requires gpu. Therefore it throws the provided error. In case you want to use dataloader for MPII a hack could be to remove certain includes from coco.py in datasets folder (you may need to handle other errors of class not defined which can be done via creating temoporaly classes!)

— You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub https://github.com/Naman-ntc/Pytorch-Human-Pose-Estimation/issues/8?email_source=notifications&email_token=AHCKUUTA57KMFWZHJH3ACQDQA5SF7A5CNFSM4H3KLCXKYY3PNVWWK3TUL52HS4DFVREXG43VMVBW63LNMVXHJKTDN5WW2ZLOORPWSZGOD2UKP6Y#issuecomment-514369531, or mute the thread https://github.com/notifications/unsubscribe-auth/AHCKUURXE2NVHAZMQDBEBIDQA5SF7ANCNFSM4H3KLCXA .