jiaqiAA

I meet the same warning, have you solved it?

Now we support ExPose inference, and you can find more details in the `demo/estimate_smplx.py`. After you have downloaded the required files (described in the [README](https://github.com/jiaqiAA/mmhuman3d/tree/main/configs/expose)), use `python demo/estimate_smplx.py --single_person_demo` to...

Hi, I think it norm wav beform extract wavlm feature, the code is `cmd = ['ffmpeg-normalize', wav_file, '-o', normalize_wav_path, '-ar', '16000']` in [here](https://github.com/YoungSeng/DiffuseStyleGesture/blob/DiffuseStyleGesturePlus/main/mydiffusion_zeggs/zeggs_data_to_lmdb.py#L133). But it is different from the [code](https://github.com/YoungSeng/DiffuseStyleGesture/blob/DiffuseStyleGesturePlus/BEAT-TWH-main/process/process_BEAT_bvh.py#L161),...

The dimension of the skeletal data is (T, 64, 3). However, you mentioned there are 61 skeleton names. Could you please clarify what the other 3 skeletal names are?