init_inference Issue

[cw-258]

Hi, I am trying to run the dlc_live.init_inference() step but am having some issues.

I checked that my image (frame) was converted into a numpy array.

When I run the code, I get the following error.

dlc_live.init_inference(frame)

639 def __init__(self, name, mode):

--> 640 super().init(open(name, mode))

PermissionError: [Errno 13] Permission denied: 'C:\Users\username\Documents\my_dlc_model'

I have checked that the folder is writable and tried moving everything to a new folder but still seem to run into the same issue.

Has anybody else ran into this issue?

[cw-258]

Additionally, I am wondering if I am maybe not loading the correct input for DLCLive. I exported my pytorch DLC model and just got one output, a .pt file. I saw in other posts online (ex: https://forum.image.sc/t/how-to-use-an-exported-model/46250), however, that other files are also exported with the .pb/.pt file like pose_cfg.yaml. Is this still the case and if so, does anyone know where I could be going wrong in my model export? Thanks!

[sneakers-the-rat]

I can't quite tell where those lines of code you're referencing are, are those in the dlclive3 branch? or what is the file that has super().init(open(name, mode)) on its 640th line? a full traceback would be useful here :)