-
Thank you for your work firstly, I am curious about why you choose L2 as criteria in "Soft Localization learning loss" instead of L1?
What good properties of L2 do you consider?
Lilyo updated
4 years ago
-
Hi @akanazawa,
thanks for the great work. I'm currently working on a TF2.0 implementation of your work in a `Keras` Model Based version.
While evaluating, I am not sure which training setting I re…
-
Hello.
- In your paper said: **_Loss is computed at each stage output_**. However, only calculate final loss in project:
https://github.com/anibali/margipose/blob/56c7b48454ace5660393899893e3fea8ae…
-
HI Team ,
I am trying to replicate the human 3D pose detection model published here : https://github.com/openvinotoolkit/open_model_zoo/blob/master/models/public/human-pose-estimation-3d-0001/desc…
-
`Human` is compatible with new web workers, but...
web workers are finicky:
- cannot pass `HTMLImage` or `HTMLVideo` to web worker, so need to pass canvas instead
- canvases can execute `tran…
-
Hi, I am trying to develop for Unity android and have tested a lot of body pose models (single person is enough) using opencv for unity. The goal is to attach a 3D humanoid avatar to the joint, howeve…
-
@mks0601 Hi, thank you for your great work.
I had a problem while training the model in the first 'lixel' stage.
I care more about the Human Pose and Mesh Estimation performance, and I've downloaded…
-
**Submitting author:** @trettenbrein (Patrick C. Trettenbrein)
**Repository:** https://github.com/trettenbrein/OpenPoseR
**Version:** v1.0
**Editor:** Pending
**Reviewer:** Pending
**Managing EiC:** D…
-
Hi @ravijo ,
I am trying to use ros_openpose for Kinect Azure camera. The Kinect Azure Ros driver can be found [here](https://github.com/microsoft/Azure_Kinect_ROS_Driver).
After installing all t…
-
I want to add some obstacles to the scene in order to get the sensor reading from hokuyo laser scanner and then avoid obstacles while planning trajectory. How can I do this in Tutorial 3 ? Is it simpl…