One
One
Hello! Thanks for using our library! A lot of models are on the way to be released recently! ( with each of them has **.npz** , **.pb** and **.onnx** format)...
@sulgwyn sorry, I've been busy developing **pifpaf** in the past few weeks. I'll have a check for this problem recently :)
> Dear @Gyx-One & @ganler, we can't reproduce any of the paper's results since the `.npz` files are missing and we can't load the only `.npz` file that was made...
Hello @orestis-z , Thank you for your work! 1. **For accuracy result** The accuracy result we report over the paper is achieved in the python code using "eval.py", the process...
Click the wrong place accidentally, sorry
@orestis-z Sure! Thanks again for your contribution! :) Sorry to response so late, because I've been handling other deadlines this week. The shape mismatch problem has been fixed over several...
Hello! @orestis-z The newest [commit](https://github.com/tensorlayer/hyperpose/commit/e34c6acb91144e1d090466324f99c521fbf47cdb) merged has already fix the shape mismatch issue. This commit also provides a [python_demo.py](https://github.com/tensorlayer/hyperpose/blob/master/python_demo.py) demonstrating how to load the pretrained model weights and the usage...
Hello! Thanks for using our library. We are going to release up to 5+ models recently, including the original **openpose** model with the same accuracy corresponding to the original paper...
Hello! @korejan **Customised dataset** means user can combine multiple datasets together as long as they provide the keypoint conversion functions for each dataset they want to combine, so technically speaking,...
Hello @sudo-vinnie 1. All the model evaluation metric reported in this repo is over the whole MSCOCO or MPII dataset, so maybe you forget to give the function **evaluate** the...