Sagaf Youssouf comments

Results 17 comments of


                                            Sagaf Youssouf

pyrender: Failed rendering frame

Thanks guys, I can see the meshes with online 3D viewer. I'm using Linux machine, is there a solution to render the sequence video.

RuntimeError: Given groups=1, weight of size [400, 256, 1, 1], expected input[64, 3, 1, 1] to have 256 channels, but got 3 channels instead

Try using single GPU to see : CUDA_VISIBLE_DEVICES=0 mmskl configs/recognition/st_gcn_aaai18/ntu-rgbd-xsub/test.yaml

Accuracy Issue

Did you find a solution to your problem ?

Can not find Openpose Python API.

Hi, I'm using ubuntu18.04 I'm getting the same error, I installed open pose and choose the option "BUILD_PYTHON" in cmake-gui and command line but still getting the same error don't...

Re: Custom Dataset Training

Same @SikhaS issue how did you resolve this problem ?

Re: Custom Dataset Training

@gohjiayi in `legday.py` don't forget to set N=1 also. Don't know where come from your error but in my opinion there is a mismatch between your processing .csv file with...

I used this [repo](https://github.com/LZQthePlane/Online-Realtime-Action-Recognition-based-on-OpenPose) to generate 36 point and concatenate skeleton data in sequence frame on a csv file with a script to have 36*2 points. See here [here](https://stackoverflow.com/questions/53183865/unknown-initializer-glorotuniform-when-loading-keras-model), it...

Testing realtime demo on ST-GCN project with a mmskeleton trained model

@mejdidallel can you show us modification details on mmcv to run on real time? Did you use the st-gcn demo file trun on real time ?

PoseNet from Google

Looking forward