Skip to content

This is a complement version of ‘pseudo-3d-pytorch’ realized by qijiezhao.

Notifications You must be signed in to change notification settings

lihui52/pytorch-p3d-train-eval

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

4 Commits
 
 
 
 

Repository files navigation

pytorch-p3d-train-eval

This is a complement version of ‘pseudo-3d-pytorch’ realized by qijiezhao.

Note that:

  • Aiming at training and testing P3D model using my own dataset,I added a few parts including 1.Data Fetching Cell, 2.Training Cell,and3.Evaling Cell.
  • The input of P3D model should be preprocessing,more details about preprocessing dataset : https://github.com/yfxc/pseudo-3d-tensorflow (You can add data augmentation cell with refering to 'DataAugmenter.py')
  • Using Pytorch,remember executing model.train() when you train model,while model.eval() for testing,especially when you have BatchNorm Layers.

About

This is a complement version of ‘pseudo-3d-pytorch’ realized by qijiezhao.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Jupyter Notebook 100.0%