This repository is an official PyTorch implementation of the paper "Learnable Triangulation of Human Pose" (ICCV 2019, oral). Proposed method archives state-of-the-art results in multi-view 3D human pose estimation!
When trying to train your model from scratch, I notice that, during 1st epoch, RAM usage starts from < 10GB and then goes up to > 90 GB till out of memory. Observed in both algebraic and volumetric approach, which is weird.
When trying to train your model from scratch, I notice that, during 1st epoch, RAM usage starts from < 10GB and then goes up to > 90 GB till out of memory. Observed in both algebraic and volumetric approach, which is weird.