rsj007

This function is to convert disparity cost volume to depth cost volume.

The result is below, but no point cloud showing. ` warnings.warn('64-bit data types not supported for WebGL ' Renderer(camera=PerspectiveCamera(aspect=1.6, fov=90.0, position=(16.54891692206 4606, 46.15009424030715, 0.38871846990986914), projectionMatrix=(1.0, 0.0, 0.0, 0.0, 0.0, 1.0,...

Thanks! Is it 0.2m too small for visualize cars? And, which visualization tools do you use? Can you get ideal point clouds output?

Why not evaluate in the eval dataset?

@hxcai Yes, my pytorch model contains grid_sampler which is not supported by ONNX. I use Tensorrt OSS to build this custom operator as "https://github.com/TrojanXu/onnxparser-trt-plugin-sample" said. In this way, I have...

> > Hi, > > Thanks for your great work. > > Looks like gen_wts.py is not working with End-to-end.pth, and would you please provide more details on how to...

@ChenKQ @SikandAlex Hello, I wonder which platform do you convert .wts to tensorrt? Jetson devices or PC? I want to deploy the project on TX2. Can I do all the...

> Thanks for your quick reply. I can generate yolop.wts now, however, found another issue while running yolop. > > Building engine... Loading weights: yolop.wts [09/02/2021-14:42:33] [E] [TRT] (Unnamed Layer*...