render_pkg["feature_map"] is empty

[WangJYao]

Traceback (most recent call last):
  File "train.py", line 355, in <module>
    training(lp.extract(args), op.extract(args), pp.extract(args), args.test_iterations, args.save_iterations, args.checkpoint_iterations, args.start_checkpoint)
  File "train.py", line 96, in training
    fea_loss = get_fea_loss(render_pkg["feature_map"], viewpoint_cam.feature[0]) * opt.lambda_fea
  File "G:\project\Sparse2DGS\utils\loss_utils.py", line 81, in get_fea_loss
    corr = (fea1 * fea2).sum(dim=0, keepdim=True) \
RuntimeError: The size of tensor a (0) must match the size of tensor b (8) at non-singleton dimension 0

[songsenIng]

Traceback (most recent call last):
  File "train.py", line 355, in <module>
    training(lp.extract(args), op.extract(args), pp.extract(args), args.test_iterations, args.save_iterations, args.checkpoint_iterations, args.start_checkpoint)
  File "train.py", line 96, in training
    fea_loss = get_fea_loss(render_pkg["feature_map"], viewpoint_cam.feature[0]) * opt.lambda_fea
  File "G:\project\Sparse2DGS\utils\loss_utils.py", line 81, in get_fea_loss
    corr = (fea1 * fea2).sum(dim=0, keepdim=True) \
RuntimeError: The size of tensor a (0) must match the size of tensor b (8) at non-singleton dimension 0

Hi, I have the same problem. Have you solved it?

[hsh200315]

I've solved this problem!
Installing diff_surfel_rasterization from 3DGS or 2DGS caused this problem
Installing it from Sparse2DGS fixes it