Clarification of loss

[pangyyyyy]

Dear authors, thanks for the great work! In your paper, you mentioned that L1 loss was applied to vertices, 3d joints and 2d joints in section 4.3: Training details.

To be specific, we apply L1 loss to 3D mesh vertices and body joints. We also apply L1 loss to 2D projected body joints to improve the align- ment between the image and the reconstructed mesh.

However, I noticed that MSE was applied to 2D and 3D joints in your code:

MeshGraphormer/src/tools/run_gphmer_bodymesh.py

Lines 168 to 171 in 1c489e3

	# define loss function (criterion) and optimizer
	criterion_2d_keypoints = torch.nn.MSELoss(reduction='none').cuda(args.device)
	criterion_keypoints = torch.nn.MSELoss(reduction='none').cuda(args.device)
	criterion_vertices = torch.nn.L1Loss().cuda(args.device)

I was wondering which loss did you use? And what is the loss used in the provided pretrained model?

Thank you!

[kevinlin311tw]

Please follow the code. Thank you.