search

EricGuo5513 / momask-codes

Official implementation of "MoMask: Generative Masked Modeling of 3D Human Motions (CVPR2024)"
https://ericguo5513.github.io/momask/
MIT License
691 stars 56 forks source link

Training Parameters #8

Closed exitudio closed 6 months ago

exitudio commented 6 months ago

Thank you for open-sourcing your amazing work.

I cannot replicate the result of the first stage training (rvq). As you updated the configurations, I tried both but did not get FID as low as your pretrain model.

  1. Batch size 256 and 50 epochs => FID 0.05146 
    python train_vq.py --name rvq_name --gpu_id 1 --dataset_name t2m --batch_size 256 --num_quantizers 6  --max_epoch 50 --quantize_drop_prob 0.2
  2. Batch size 512 and 500 epochs => FID 0.03358 
    python train_vq.py --name rvq_name --gpu_id 1 --dataset_name t2m --batch_size 512 --num_quantizers 6  --max_epoch 500 --quantize_drop_prob 0.2

    I ran evaluation on your pretrain model FID is 0.019. Could it be due to high variance during training, or is there something specific I should try? Any suggestions would be greatly appreciated.

EricGuo5513 commented 6 months ago

Hi, thanks for your interest. Could you use the configuration indicated in the opt.txt of the given checkpoint, including the learning scheduler? Please note that after all we will use the checkpoint with the best FID on the validation set.

On Fri, 5 Jan 2024 at 08:44, EXIT @.***> wrote:

Thank you for open-sourcing your amazing work.

I cannot replicate the result of the first stage training (rvq). As you updated the configurations, I tried both but did not get FID as low as your pretrain model.

  1. Batch size 256 and 50 epochs => FID 0.05146

python train_vq.py --name rvq_name --gpu_id 1 --dataset_name t2m --batch_size 256 --num_quantizers 6 --max_epoch 50 --quantize_drop_prob 0.2

  1. Batch size 512 and 500 epochs => FID 0.03358

python train_vq.py --name rvq_name --gpu_id 1 --dataset_name t2m --batch_size 512 --num_quantizers 6 --max_epoch 500 --quantize_drop_prob 0.2

I ran evaluation on your pretrain model FID is 0.019. Could it be due to high variance during training, or is there something specific I should try? Any suggestions would be greatly appreciated.

— Reply to this email directly, view it on GitHub https://github.com/EricGuo5513/momask-codes/issues/8, or unsubscribe https://github.com/notifications/unsubscribe-auth/AKRYNB67AKKUJOFKQFR2OTLYNANXVAVCNFSM6AAAAABBOTMWQWVHI2DSMVQWIX3LMV43ASLTON2WKOZSGA3DONJWHE3TOMI . You are receiving this because you are subscribed to this thread.Message ID: @.***>

exitudio commented 6 months ago

Thank you for your suggestion.

weihaosky commented 4 months ago

Thank you for your suggestion.

Hi, I have the same issue. Have you found out how to change the training parameters to replicate the performance of the pre-trained model?