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

How to run Trained Pose model on a single image instead of creating tfrecord from a test dataset ? #22

Open
abhishekiitd327 opened this issue Feb 26, 2019 · 5 comments

Comments

@abhishekiitd327
Copy link

abhishekiitd327 commented Feb 26, 2019

@charliememory Once I have trained the model, I want to run Pose Transfer on a given image. But the current implementation required a tfrecord file to be generated from images and poses, and applies pose transfer on those. Any quick solution for that ?

@charliememory
Copy link
Owner

If you want to run on a given image, you will need to implement a data load script for the single image and pose keypoints.

@leonardishere
Copy link

@abhishekiitd327 Any luck? I'm looking for the same thing

@jianti
Copy link

jianti commented Mar 8, 2019

@charliememory If I have a image and the keypoints heatmap, how shall I do, thanks...

@jianti
Copy link

jianti commented Mar 8, 2019

@charliememory The script mean the attribute of the image? such as the weight and high of the image and the keypoints location of the body?

@leonardishere
Copy link

@charliememory The run_convert_DF.sh script assumes that you already have all_peaks_dic_DeepFashion.p and subsets_dic_DeepFashion.p. However, I want to run pose transfer on an image that wasn't in the provided database. There is nowhere in the code that explains how to generate these, can you help? Or at least point me towards a resource that explains how to generate these for a single photo

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