search

EricGuo5513 / text-to-motion

Official implementation for "Generating Diverse and Natural 3D Human Motions from Texts (CVPR2022)."
MIT License
484 stars 40 forks source link

Do we need to load the pretrained checkpoints when training the feature extractor? #15

Closed linjing7 closed 1 year ago

linjing7 commented 1 year ago

Hi, I use a different motion representation from HumanML3D, and thus I need to train a new feature extractor for evaluation. I run the following command: python train_tex_mot_match.py --name text_mot_match --gpu_id 1 --batch_size 8 --dataset_name t2m But an error occurs because I need to load the pretrained checkpoint. Do I need to train a new motion autoencoder before training the feature extraction network?

image
EricGuo5513 commented 1 year ago

Hi, for text_mot_match model, our model require a preliminary autoencoder to extract high level feature. This can reduce the sequence length. But if you are training your own text_mot_match model, you may skip this and directly feed raw pose sequence. This is up to you.

linjing7 commented 1 year ago

Okay, thanks for your reply!