star

depth is not defined in renderer.ipynb

1

depth-> depth_h ?

Update pose_utils.py

11

fix the error when existing invalid views in the scene. Beside the pose_boundary.npy will be generated, it also will generate "view_imgs.txt" to mark which views are used.

https://github.com/HRNet/HRNet-Facial-Landmark-Detection/blob/f776dbe8eb6fec831774a47209dae5547ae2cda5/experiments/wflw/face_alignment_wflw_hrnet_w18.yaml#L67 Why not enlarge batchsize in training , 48 and bigger?

RuntimeError: Expected object of backend CUDA but got backend CPU for ...

4

The original code doesn't consider the gpu situation for loss, and will lead to the problem: ```RuntimeError: Expected object of backend CUDA but got backend CPU for ...``` original code:...

Hi, A nice work in face alignment! For better compare to other works, I wanna to know the params and flops (in WFLW,98pts) on LUVLI.

wrong index of width and height in unpad_image function

3

https://github.com/LLaVA-VL/LLaVA-NeXT/blob/8c09e0206af91c5c83fc25f55500883e9df261b8/llava/model/llava_arch.py#L137 

about data processing

1

Is the grounding data labeled before or after the data processor?  for example, an image needs padding to make width equal height, and the openai/clip-vit contains the do_center_crop. These...