Zhaojiang Liu
Zhaojiang Liu
Yeah, i get the 10—18 fps by using yolov3 and 20—25 FPS by using yolov3—tiny ---Original--- From: "Asad"
the question may lie in the size of the input video and which type gpu you run the demo in. if my memory serves me well，i input the video of...
you can try to change to resize your input video,by which fps will be a little faster. i have run the demo with the input video of 1980*1080, the fps...
> to do with the detector? I tried with YoloV5 and got a faster tracking result. Detecting the object is the first step for tracking. Faster detector is of help...
> hello, you can spin up a determined shell and use VSCode "remote ssh" feature to work with it as if it's a remote server: https://docs.determined.ai/latest/interfaces/ide-integration.html#visual-studio-code > > we don't...
Add the guidance like mmdetection to verify the installation of detrex is correct or not.
> You should change the BN configurations at [here](https://github.com/JeffWang987/OpenOccupancy/blob/a97019a31b968e25206472eb28d10ee0ec0ab9b5/projects/configs/baselines/CAM-R50_img1600_128x128x10.py#L80) (SyncBN-->BN) Change the config as you advise and then encounter the same problem ''ValueError: expected 4D input (got 2D input)'' as...
Modiffying the code (SyncBN --> BN) doesn't work for me, which will raise error ValueError: expected 4D input (got 2D input) Actually, there is no need to modify the code...
In the [issue](https://github.com/JeffWang987/OpenOccupancy/issues/19), it seems like occupancy gt lie in lidar coordinate system. I am a new comer for OpenOccupancy. I am not sure what causes the outcome between occupancy...
You are right. You can check that the type of gt you load is "int"......