Algorithmic newcomer

Results 8 issues of Algorithmic newcomer

Kernel affine transformation results are inconsistent with OpencV affine transformation results, how to modify?

I use your trained model to reason my own data with the following command: python render_reposing.py --scene_dir data/mydata/output --weights_path out/lab_human/checkpoint.pth.tar --motion_name=jumpandroll. the result for a frame is as follows: ![out_0007](https://user-images.githubusercontent.com/71183069/194804262-a8742ada-0f85-494c-aa5f-88fbd55d5c3f.png)...

I test my own dataset using your trained bike_human model, Enter python render_360.py --scene_dir data/mydata/output --weights_path out/bike_human/checkpoint.pth --mode canonical_360, we get the following result ![out_0000](https://user-images.githubusercontent.com/71183069/194686969-a870d7f3-1961-4805-9b79-4b4dcd11eaf9.png) Excuse me, is there something...

In addition to openpose, can I use other key points to detect the model? I run the code to test my own data measured waist circumference is about 88, and...

Hello, can I reconstruct the human body with your method and then measure the waist circumference

I'm compiling /libmaix/examples/nn_pose/ Times this error. ![image](https://github.com/sipeed/libmaix/assets/71183069/5d18d026-4e24-41bf-b79a-094de8a33b54) How to modify it?

Hello, I ran pose_trainer.py and mistakenly reported no smplx_Shapes.npz file, how did I get this file

My scene is like this: a person rotates once under the depth camera. Can such data be registered using your method