If I only want to evaluate this motionGPT, do I need to build Humanml3D as well

[LiJianmo]

When I run:
python demo.py --cfg ./configs/config_h3d_stage3.yaml --example ./demos/t2m.txt
to evaluate.
I always have the error:
FileNotFoundError: [Errno 2] No such file or directory: 'datasets/humanml3d\test.txt'

do I need to build humanml3d dataset according to the instruction from its github

[WILLOSCAR]

May I ask if you have already solved the problem? I would appreciate if you could provide a specific solution!

[lijiaxing0213]

It seems building the complete humanml3d dataset is necessary. Before I built it, I encountered a ValueError: not enough values to unpack (expected 2, got 0) error. However, it ran smoothly after building it.

[andyl-flwls]

datasets/humanl3d must contain all the data files for the dataloader to work. As a result, you need to go to https://github.com/EricGuo5513/HumanML3D for all data preprocessing to obtain them.

The structure of the datasets directory should look like this:

.
└── humanml3d
├── Mean.npy
├── Std.npy
├── all.txt
├── new_joint_vecs
├── new_joints
├── test.txt
├── texts
├── texts.zip
├── tmp
├── train.txt
├── train_val.txt
└── val.txt

new_joint_vecs and new_joints must be there to make this work