-
Notifications
You must be signed in to change notification settings - Fork 10
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Error while pre-processing and missing assets files #3
Comments
Hey, thanks for your interest in SMIRK :) Errors:
get each frame individually, and apply the preprocessing. I will try to also upload a correct version of this file soon. Generic Doubts:
|
Thanks for the quick response @filby89 So essentially in the case of videos with N frames, should I be emulating what is being done in mediapipe processing I'm still working my way through procuring the datasets and preprocessing them at a snail's pace. |
@chakri1804 Yes, this is the process exactly as you mentioned :) |
Hey @filby89 I noticed that face alignment pre-processor was not multi-threaded and would take ages on a dataset like lrs2 and mead PS: This code only visualises last frame of the video and dumps it in the path unlike mediapipe one which stitches a whole video with landmarks plotted. 😄
|
Hey @chakri1804 thank you very much for your comment and code :) This will be helpful for others too ! |
Final couple of questions @filby89 From the looks of it, you've seperated mead into And should I rearrange these files around someway ? Similar doubt with LRS2 as well. TL:DR; If we point the config to a certain dir, are videos expected to be at a certain directory depth or is it fine ? |
Hey, |
Hey @filby89 Got the datasets pre-processed and placed them in the right paths. Also I noticed that in |
Hey @chakri1804 I believe you can completely skip BUPT - we did not use it in the end at all and these configs are not used. |
Hey @filby89 I completed the pretraining part with 100 expressions and it worked fine in
Here I believe the famos numpy files you have provided just have 50 length expression vectors so the training step fails. |
Hey @filby89 Could you provide a bit more direction on the above issue ? The pretraining part with 100 exp I could perform |
Hi,
Thanks for sharing this amazing repo 😄
I was trying to retrain the model with a couple of modifications.
In the processes I faced a couple of hitches while trying to run the pre-processing code on the mentioned datasets
Would help me a lot if you can guide me through them
Errors:
apply_mediapipe_to_dataset.py
, inside thedef preprocess_sample()
function,you used
model_asset_path='assets/face_landmarker.task'
but the file is not provided within the assets folder.Could you share a link from where I can download this / update the repo with this file ?
apply_fan_to_dataset.py
I noticed youos.walk()
the root, store the paths and then in L36 we loop on those pairsIn the process we were also storing
.mp4
and.avi
but trying to read them withcv2.imread()
in L44.This would in the end throw
None type has no shape attribuite
error. How do I handle this case / video datasets ?Generic Doubts:
MEAD_front
andMEAD_sides
But the configs do not have provision landmark paths for
MEAD_sides
. Are they already provided with the dataset ?The text was updated successfully, but these errors were encountered: