Skip to content
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

FileNotFoundError: [Errno 2] No such file or directory: 'DATA_FOLDER/keypoints #8

Closed
Piero-M opened this issue Jun 30, 2019 · 11 comments

Comments

@Piero-M
Copy link

Piero-M commented Jun 30, 2019

Good morning, this model seems to me extremely exciting!

I have configuration problems, in fact I have this error and I do not understand, keypoints should be generated by myself or should I do something?

This is the error:

python smplifyx/main.py --config cfg_files/fit_smplx.yaml --data_folder DATA_FOLDER --output_folder OUTPUT_FOLDER --visualize="True" --model_folder MODEL_FOLDER --vposer_ckpt VPOSER_FOLDER --part_segm_fn smplx_parts_segm.pkl
Traceback (most recent call last):
File "smplifyx/main.py", line 272, in
main(args)
File "smplifyx/main.py", line 201, in main
for idx, data in enumerate(dataset_obj):
File "/Users/piero
******/anaconda3/envs/AVATAR/smplify-x/smplifyx/data_parser.py", line 206, in next
return self.next()
File "/Users/piero********/anaconda3/envs/AVATAR/smplify-x/smplifyx/data_parser.py", line 215, in next
return self.read_item(img_path)
File "/Users/piero********/anaconda3/envs/AVATAR/smplify-x/smplifyx/data_parser.py", line 185, in read_item
use_face_contour=self.use_face_contour)
File "/Users/piero********/anaconda3/envs/AVATAR/smplify-x/smplifyx/data_parser.py", line 54, in read_keypoints
with open(keypoint_fn) as keypoint_file:
FileNotFoundError: [Errno 2] No such file or directory: 'DATA_FOLDER/keypoints/76_img_keypoints.json'

@geopavlakos
Copy link
Collaborator

For a new image, you are supposed to provide the keypoints as input to the code. You need to use OpenPose for this. If you want to fit the SMPL-X model, for best results, please remember to active the --hand and --face flags, to generate the additional keypoints on the hands and the face respectively.

The OpenPose output should be stored in the DATA_FOLDER/keypoints folder. I copy from the README:

DATA_FOLDER should contain two subfolders, images, where the images are located, and keypoints, where the OpenPose output should be stored.

@Piero-M
Copy link
Author

Piero-M commented Jun 30, 2019

hi, thanks for the answer, but don't hop understood one thing, OpenPose runs automatically and creates the output in the keypoints folder?

or do I have to run OpenPose for each image and then manually insert it in the keypoints folder of smplifyx?

@geopavlakos
Copy link
Collaborator

You need to run OpenPose yourself to generate the keypoints. OpenPose can take as input a folder of images and process all of them at once, so you can specify the input folder to be DATA_FOLDER/images and the output DATA_FOLDER/keypoints. This way, you will not need to do any manual moving of files.

@Piero-M
Copy link
Author

Piero-M commented Jun 30, 2019

perfect thank you! can I create a unique command to run OpenPose and SMPL-X?

Also I would like to find the size of some points that interest me of the avatar? How can I do that?

Here's an example of what I mean:
https://youtu.be/wnc2lXAf6f8

@geopavlakos
Copy link
Collaborator

can I create a unique command to run OpenPose and SMPL-X?

We don't provide this functionality at the moment in this repo, but this should be easy to do, e.g., by writing a short shell script.

@Piero-M
Copy link
Author

Piero-M commented Jun 30, 2019

Perfect, thank you!

Can you help me to extract the measurements from the avatar model?

@vchoutas
Copy link
Owner

vchoutas commented Jul 2, 2019

@PieroMondora Once you have the final mesh of the model you want,
you can load it in e.g. Blender and then select
the vertices/triangles, etc., that you want for your measurements.

@Piero-M
Copy link
Author

Piero-M commented Jul 2, 2019

@vchoutas Thanks, I'll try.

@vchoutas vchoutas closed this as completed Jul 3, 2019
@Piero-M
Copy link
Author

Piero-M commented Jul 3, 2019

Sorry, but the program does not work without CUDA? I would like to try it on Mac with CPU

@johndpope
Copy link

@PieroMondora

I have a nice latest new imac sitting on my desk - but all machine learning stuff is using cuda / cudnn -> nvidia. Apple have ostrasized nvididia so you won't find nvidia drivers past high sierra.

I ended up buying a hp workstation z440 and I'm running docker + ubuntu
here's the docker file I used to get open pose
https://gist.github.com/johndpope/f0ec2a70e18041990e37f93876d6af19

@Piero-M
Copy link
Author

Piero-M commented Jul 9, 2019

@johndpope

So there's no chance of trying it on a mac?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

4 participants