search

zhangboshen / A2J

Code for paper "A2J: Anchor-to-Joint Regression Network for 3D Articulated Pose Estimation from a Single Depth Image". ICCV2019
MIT License
289 stars 46 forks source link

Data augmentation #20

Open egistific opened 4 years ago

egistific commented 4 years ago

Thanks for sharing the testing code. I'm trying to reproduce the training code would like to know the implementation details for data augmentation.

. Random in-plain rotation: what are the parameters used? . Random scaling for both in-plain and depth dimension: is each dimension scaled independently and what are the parameters used? . Random gaussian noise is also randomly added with the probability of 0.5: which dimensions is noise added to and what are the parameters used? . For each image in the training set, is data augmentation performed 3 times (rotation, scaling, adding noise)? . Does data augmentation increase the number of samples in the training set (i.e. both original images and augmented images are used)?

zhangboshen commented 4 years ago

Thanks for sharing the testing code. I'm trying to reproduce the training code would like to know the implementation details for data augmentation.

. Random in-plain rotation: what are the parameters used? . Random scaling for both in-plain and depth dimension: is each dimension scaled independently and what are the parameters used? . Random gaussian noise is also randomly added with the probability of 0.5: which dimensions is noise added to and what are the parameters used? . For each image in the training set, is data augmentation performed 3 times (rotation, scaling, adding noise)? . Does data augmentation increase the number of samples in the training set (i.e. both original images and augmented images are used)?

Hi, please check our training code for details: https://github.com/zhangboshen/A2J/tree/master/src_train