陌尘小小

Results 5 comments of 陌尘小小

我也出现了同样的内存错误,单人姿态估计运行没问题, 但是多人视频时间过长会报错,python被kill掉了; “**demo/estimate_smpl.py**”的第**394**行出现问题: verts = smooth_process(verts, smooth_type=args.smooth_type) 进入“mmhuman3d/utils/**demo_utils.py**“的**smooth_process()**”,在**352**行: if x.ndim == 4: for i in range(x.shape[1]): x[:, i] = smooth_func(x[:, i]) 这里占用了大量的内存。 (**减小时间和人数**)我把10秒的多人视频变成5秒才运行**成功**,但是这个for循环速度特别慢,特别慢

For the problem of a single 3090 memory explosion, can I use two 3090s in parallel training? It appears that the source code does not provide parallel training?

> I successfully deployed BF16 (with a display of 26GB of VRAM), but after encountering an issue with the UseSR interaction input, the VRAM was running low. I am using...

作者的Readme在安装mmcv-full和mmsegmentation是错误的。 - [ ] 我更换了cuda=11.3和pytorch=1.10的版本,使用了如下命令安装: conda install pytorch==1.10.0 torchvision==0.11.0 torchaudio==0.10.0 cudatoolkit=11.3 -c pytorch -c conda-forge - [ ] mmcv-full使用了1.7.0的高版本: pip install mmcv-full==1.7.0 -f https://download.openmmlab.com/mmcv/dist/cu113/torch1.10/index.html - [ ] mmsegmentation使用了0.3.0的版本 pip install...

> > 作者的Readme在安装mmcv-full和mmsegmentation并不适合每一个人。 > > > > * [ ] 我更换了cuda=11.3和PyTorch=1.10的版本,使用了如下命令安装: conda install pytorch==1.10.0 Torchvision==0.11.0 Torchaudio==0.10.0 cudatoolkit=11.3 -c pytorch -c conda-forge > > * [ ] mmcv-full使用了1.7.0的高版本: pip install mmcv-full==1.7.0...