When using a single image UnboundLocalError: local variable 'full_frames' referenced before assignment

[seranus]

When using a single image full_frames is not defined

Traceback (most recent call last): File "batch_inference.py", line 228, in <module> main() File "batch_inference.py", line 178, in main print ("Number of frames to be used for inference: "+str(len(full_frames))) UnboundLocalError: local variable 'full_frames' referenced before assignment

Also FPS is a required parameter, in the docs for image it isn't specified

[prajwalkr]

I have fixed both the issues now. Please let me know if it is alright :)

[seranus]

It does not fix my main issue, you are defining full_frames only if the input is a video

LipGAN/batch_inference.py

Line 166 in 0cecae1

full_frames = []

but you are referencing it later for any input

LipGAN/batch_inference.py

Line 198 in 0cecae1

gen = datagen(full_frames.copy(), mfcc_chunks)

[prajwalkr]

Sorry about that. Defined full_frames for single image input as well. Any other errors?

[seranus]

It works now, what model goes into --checkpoint param it doesn't say in the param description. Is it the path to the LipGAN or I have to train a generator?

[prajwalkr]

Please indicate the line you are talking about.

[seranus]

Thanks, it works now. I was using the folder path instead of the LipGan file path for --checkpoint