search

tranluan / Nonlinear_Face_3DMM

Source code for "Nonlinear 3D Face Morphable Model"
http://cvlab.cse.msu.edu/project-nonlinear-3dmm.html
Apache License 2.0
676 stars 124 forks source link

training configuration #26

Open zhangxuan1918 opened 5 years ago

zhangxuan1918 commented 5 years ago

Hello,

I tried to train the model. However I got a few issues. During pre-training, after 200 epochs, the training converges and doesn't improve. The rendered image doesn't look good, especially the pose and texture. Then I switched to unsupervised training. However after 100 epochs, the image rendered is super blurred.

I'm not sure if the configuration in the code is the default setting you use. Thus, could you share your configuration for training, e.g.

pre-training:

training

Thanks a lot

linshuheng6 commented 4 years ago

Hello, I have no idea about how to run the pre_training model. Could you please share your configuration for pre_training. Thank you !!!

HOMGH commented 4 years ago

Hello,

I tried to train the model. However I got a few issues. During pre-training, after 200 epochs, the training converges and doesn't improve. The rendered image doesn't look good, especially the pose and texture. Then I switched to unsupervised training. However after 100 epochs, the image rendered is super blurred.

I'm not sure if the configuration in the code is the default setting you use. Thus, could you share your configuration for training, e.g.

pre-training:

  • number of epochs

training

  • number of epochs, in code, it says 1000, do you really use 1000 epochs?
  • which loss you use? Do you use all the loss mentioned in the paper/code?

Thanks a lot

Hi @zhangxuan1918 I'm trained the model. but the results (rendered images and textures) are not reasonable. I used just 1000 images and 40 epochs for training. Could you train the model correctly?