ttxskk

Many thanks for the update. Currently, there are conflicts that need to be manually resolved.

> @ttxskk you would like me to resolve them or is it something you need to do? I hope you can resolve them directly.

Hi, this error looks like due to limited memory? I don't meet this error when running `estimate_smpl.py`.

This looks weird, I'll check it.

Hi @hsauod, can you provide more details of your installation process? This error looks weird. I reinstalled MMHuman3D following the [install.md](https://github.com/open-mmlab/mmhuman3d/blob/main/docs/install.md), but everything worked well for me.

Hi @dldaisy, thanks for you point out this. [This line](https://github.com/open-mmlab/mmhuman3d/blob/2ccdd2484353a77efe27508d207f6ae5349506ef/mmhuman3d/models/utils/inverse_kinematics.py#L135) looks like a redundant code because the element of the [children map](https://github.com/open-mmlab/mmhuman3d/blob/131ad1fb2dbee2c41bdfa334a19e01ab6130a8f3/mmhuman3d/models/body_models/smpl.py#L472) will not be -3. I have noticed that...

Hi, you can try `from mmdet.apis import inference_detector, init_detector` in your conda environment directly, it might tell you the error you are facing. From your provided environment info, I guess...

Hi @Gzzgz, for HybrIK inference, the [official code](https://github.com/Jeff-sjtu/HybrIK) has released a demo version that explicitly predicts the camera. We will add this version into MMHuman3D if the author releases all...

Sorry for replying so late. For `h36m_mean_beta.npy`, you can get it from [this page](https://github.com/open-mmlab/mmhuman3d/tree/main/configs/hybrik).

`MMCamera` depends on PyTorch3D, so if we're going to make PyTorch3D an optional install, we'd better not do it?@caizhongang @Coach257