Video Synthesis via Deep Learning

I try to improve some codes regarding video synthesis and video imitation for academic research reason.
I try to run Pose training and test on following github source code on Google Colab.

Some questions :

Issue 1-)
%cd /content/few-shot-vid2vid
!python --name pose --dataset_mode fewshot_pose --adaptive_spade --warp_ref --spade_combine --remove_face_labels --add_face_D --niter_single 100 --niter 200 --batchSize 2

File “/content/few-shot-vid2vid/data/”, line 65, in make_grouped_dataset
assert os.path.isdir(dir), ‘%s is not a valid directory’ % dir
AssertionError: datasets/pose/train_openpose is not a valid directory

How will I use DensePose and/or OpenPose ? I think they are deprecated. Where can I find data for datasets/pose/train_openpose ; datasets/pose/train_images , datasets/pose/train_densepose ?

Issue 2-) What is sample values for PATH_TO_SEQ and PATH_TO_REF_IMG on ?


To test the trained model (bash ./scripts/pose/
python --name pose --dataset_mode fewshot_pose --adaptive_spade --warp_ref --spade_combine --remove_face_labels --finetune --seq_path [PATH_TO_SEQ] --ref_img_path [PATH_TO_REF_IMG]

At that repo, it says: This repo is now deprecated. Please refer to the new Imaginaire repo: GitHub - NVlabs/imaginaire: NVIDIA PyTorch GAN library with distributed and mixed precision support</t.
Could you try with the new repo? And open issue there at Issues · NVlabs/imaginaire · GitHub?

This topic was automatically closed 60 days after the last reply. New replies are no longer allowed.