search

UttaranB127 / STEP

Spatial Temporal Graph Convolutional Networks for Emotion Perception from Gaits
https://gamma.umd.edu/step
MIT License
69 stars 12 forks source link

Using a 2D dataset instead of a 3D dataset #10

Closed AndreyGalitsin closed 3 years ago

AndreyGalitsin commented 3 years ago

Dear Uttaran, I want to use a 2D pose dataset instaed of a 3D, that you use in this work. Tell me please what does 'in_channels' there https://github.com/UttaranB127/STEP/blob/master/classifier_stgcn_real_only/net/classifier.py#L19 mean?

Is it responsible for 3 (RGB) image channels or it is about 3 dimensional input data and if I want to use a 2D dataset, I have to set in_channels=2?

UttaranB127 commented 3 years ago

Yes, it refers to three-dimensional input data. In order to use 2D input, you can change in_channels to 2, and the input would two-dimensional joint locations (could be either image space or metric space).

AndreyGalitsin commented 3 years ago

I understand, thank you so much!