Closed CodeLHY closed 4 years ago
Hi 李弘洋 Thanks, The final test code achieve 27.7fps at most 5 people appears on python environment with webcam.
2020년 4월 20일 (월) 오후 1:06, 李弘洋 notifications@github.com님이 작성:
hi @noirmist https://github.com/noirmist , Nice work, have you test this code's running speed?
— You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub https://github.com/noirmist/Pytorch_Pose_Proposal_Network/issues/2, or unsubscribe https://github.com/notifications/unsubscribe-auth/ACCDXVMO7HDDYFQNSKM3DUTRNPC2TANCNFSM4MMDKUBA .
Hi 李弘洋 Thanks, The final test code achieve 27.7fps at most 5 people appears on python environment with webcam. Jungwoo Choi 2020년 4월 20일 (월) 오후 1:06, 李弘洋 notifications@github.com님이 작성: … hi @noirmist https://github.com/noirmist , Nice work, have you test this code's running speed? — You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub <#2>, or unsubscribe https://github.com/notifications/unsubscribe-auth/ACCDXVMO7HDDYFQNSKM3DUTRNPC2TANCNFSM4MMDKUBA .
Thank you for your early reply.
BTW, what about the device you are using?
I used Ubuntu PC with one nvidia gtx1080 ti graphic card
2020년 4월 20일 (월) 오후 2:12, 李弘洋 notifications@github.com님이 작성:
BTW, what about the device you are using?
— You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub https://github.com/noirmist/Pytorch_Pose_Proposal_Network/issues/2#issuecomment-616313385, or unsubscribe https://github.com/notifications/unsubscribe-auth/ACCDXVNDGOH7XEPQFVP4CP3RNPKSNANCNFSM4MMDKUBA .
I used Ubuntu PC with one nvidia gtx1080 ti graphic card 2020년 4월 20일 (월) 오후 2:12, 李弘洋 notifications@github.com님이 작성: … BTW, what about the device you are using? — You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub <#2 (comment)>, or unsubscribe https://github.com/notifications/unsubscribe-auth/ACCDXVNDGOH7XEPQFVP4CP3RNPKSNANCNFSM4MMDKUBA .
But the paper said that they can get a 200FPS speed. And there is also a Chainer's reimplementation in github that gets a 130 FPS speed. Do you know the reason for this gap?
The big difference is Deep learning frameworks. And I guess some part I need look into it. I didn't realize there are hight speed version is released( https://github.com/Idein/chainer-pose-proposal-net/issues/12#issuecomment-452214909 ). Thanks
2020년 4월 20일 (월) 오후 3:01, 李弘洋 notifications@github.com님이 작성:
I used Ubuntu PC with one nvidia gtx1080 ti graphic card 2020년 4월 20일 (월) 오후 2:12, 李弘洋 notifications@github.com님이 작성: … <#m1956818301706506115> BTW, what about the device you are using? — You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub <#2 (comment) https://github.com/noirmist/Pytorch_Pose_Proposal_Network/issues/2#issuecomment-616313385>, or unsubscribe https://github.com/notifications/unsubscribe-auth/ACCDXVNDGOH7XEPQFVP4CP3RNPKSNANCNFSM4MMDKUBA .
But the paper said that they can get a 200FPS speed. And there is also a Chainer's reimplementation in github that gets a 130 FPS speed. Do you know the reason for this gap?
— You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub https://github.com/noirmist/Pytorch_Pose_Proposal_Network/issues/2#issuecomment-616329422, or unsubscribe https://github.com/notifications/unsubscribe-auth/ACCDXVNYNMZQRZELLXKRD6TRNPQNJANCNFSM4MMDKUBA .
The big difference is Deep learning frameworks. And I guess some part I need look into it. I didn't realize there are hight speed version is released( Idein/chainer-pose-proposal-net#12 (comment) ). Thanks 2020년 4월 20일 (월) 오후 3:01, 李弘洋 notifications@github.com님이 작성: … I used Ubuntu PC with one nvidia gtx1080 ti graphic card 2020년 4월 20일 (월) 오후 2:12, 李弘洋 @.***님이 작성: … <#m1956818301706506115> BTW, what about the device you are using? — You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub <#2 (comment) <#2 (comment)>>, or unsubscribe https://github.com/notifications/unsubscribe-auth/ACCDXVNDGOH7XEPQFVP4CP3RNPKSNANCNFSM4MMDKUBA . But the paper said that they can get a 200FPS speed. And there is also a Chainer's reimplementation in github that gets a 130 FPS speed. Do you know the reason for this gap? — You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub <#2 (comment)>, or unsubscribe https://github.com/notifications/unsubscribe-auth/ACCDXVNYNMZQRZELLXKRD6TRNPQNJANCNFSM4MMDKUBA .
Thank you very much, I'll close this issue.
hi @noirmist , Nice work, have you test this code's running speed?