tensorlayer
Can I build it in WIN
I looked at several questions to try to use it in Win, but I didn't see if it was successful in Win, so I wanted to ask if it was possible to implement win build
We don't have official guidance to build it on windows. Though I knew that some users have built it on Windows since all of our codes are cross-platform. I would suggest you build it with WSL2 which will bring you a Linux environment so that you can simply follow the instructions from the tutorial.
We don't have official guidance to build it on windows. Though I knew that some users have built it on Windows since all of our codes are cross-platform. I would suggest you build it with WSL2 which will bring you a Linux environment so that you can simply follow the instructions from the tutorial.
Thank you for your reply, how do I build locally on ubuntu 18.04 instead of using docker?
We don't have official guidance to build it on windows. Though I knew that some users have built it on Windows since all of our codes are cross-platform. I would suggest you build it with WSL2 which will bring you a Linux environment so that you can simply follow the instructions from the tutorial.
Thank you for your reply, how do I build locally on ubuntu 18.04 instead of using docker?
https://hyperpose.readthedocs.io/en/latest/markdown/install/prediction.html#build-from-source
We don't have official guidance to build it on windows. Though I knew that some users have built it on Windows since all of our codes are cross-platform. I would suggest you build it with WSL2 which will bring you a Linux environment so that you can simply follow the instructions from the tutorial.
Thank you for your reply, how do I build locally on ubuntu 18.04 instead of using docker?
https://hyperpose.readthedocs.io/en/latest/markdown/install/prediction.html#build-from-source
Thank you for your prompt reply
We don't have official guidance to build it on windows. Though I knew that some users have built it on Windows since all of our codes are cross-platform. I would suggest you build it with WSL2 which will bring you a Linux environment so that you can simply follow the instructions from the tutorial.
Thank you for your reply, how do I build locally on ubuntu 18.04 instead of using docker?
https://hyperpose.readthedocs.io/en/latest/markdown/install/prediction.html#build-from-source
Thank you for your prompt reply
Yes, I built him on ubuntu18.04. Able to realize real-time processing of video streams，like this： ./hyperpose-cli --runtime=operator --source=../data/media/video.avi ，
Q1 ：I want to modify the output format, what should I do, like openpose's output format json file (25 key points)
Q2：Is our key point detection consistent with the key point of openpose body 25 keypoint or 18coco keypoint?
we do 18 coco keypoints. Notably, when supporting openpifpaf, we convert its format to approximate 18 coco format. As for extending a Json output, you can modify the source codes in stream.(hpp or cpp) to add a new output operator.
we do 18 coco keypoints. Notably, when supporting openpifpaf, we convert its format to approximate 18 coco format. As for extending a Json output, you can modify the source codes in stream.(hpp or cpp) to add a new output operator.
I tried it, but it didn't work，I would like to ask where to get the key point code, I am not very familiar with the code from C++, can you have detailed information and implementation examples，Looking forward to your reply
@zhanghongyong123456 See https://github.com/tensorlayer/hyperpose/blob/master/src/stream.cpp#L133
I would appreciate it if you can contribute a JSON writer.