sparshgarg23
sparshgarg23
@vchoutas would it be possible to give an update on how to resolve this?
In SMPL paper,pose prior is defined as max mixture,the get_mean is implemented in that.
@mikel-brostrom could you please elaborate on how the sources.txt 's format is. i am assuming by streams you are referring to the object being viewed from different cameras?
@sh7jacobi where did you find the ATSS,is it the balanced_positive_negative_sampler.py
@athn-nik ,I am having the same issue in my case I tried on a youtube video however I noticed in the final result,the initial model fit was consistent but after...
@athn-nik hi,I tried running on another video which involved side-view,seems that the leg-shaking /jitter happens in frames that are being viewed from the side.Although in this case the shaking/deformation wasn't...
@danielzhangau just wanted to follow up ,did you set the following options to true ``` _C.TRAIN.ENC_SEG_ONLY = True _C.TRAIN.DRIVABLE_ONLY = True ```
Resolved this as follows on colab clone yolop directory cd yolop and then follow the below steps ``` !pip install torch==1.9.0+cu102 torchvision==0.10.0+cu102 torchaudio===0.9.0 -f https://download.pytorch.org/whl/torch_stable.html !pip install -r requirements.txt ```
ok will look into it thanks,one last thing can I use the output of ROMP as an intialization for SMPL-X. Also,apart from SMPL-X,is there any other work that deals with...
would appreciate it if either @junyanz or @taesungp could give some feedback.