Ilya Basharov

@HuangJunJie2017 @ZwwWayne plz help me with readthedocs build failed problem. I dont know what to do with this

@wkentaro ok, but it did not work for me. Strange

@wkentaro please see this PR #210

@EchoAmor instance DB mean Database for Instance Segmentation for Spatial Embedding Training (Kitti INStanse dataset). What about weights - I have a different situation, mentioned there https://github.com/detectRecog/PointTrack/issues/13

@EchoAmor @phj128, Did u carefully examine the 13th track, which consists of much more pedestrians than cars? so, your model often makes mistakes on this track. Look at precision metric,...

@EchoAmor How did you achieve such results ? Here https://github.com/detectRecog/PointTrack/issues/15 you wrote that u have lower results.

@eng100200, please read the description carefully. The author said : 'YOLOv3 and darknet53 without original darknet cfg parser.' So, the answer to your qv is no, this is his own...

@ethanweber I think now `VisibilityField` class name is too common. There are many papers that using `VisibilityField` too, so it would be better to distinguish them in this framework

> > @ethanweber I think now `VisibilityField` class name is too common. There are many papers that using `VisibilityField` too, so it would be better to distinguish them in this...

@tancik I've posted renders and metrics. Im using `torch_scatter` twice. I can replace `scale_featurization` via [torch.scatter_reduce](https://pytorch.org/docs/stable/generated/torch.Tensor.scatter_reduce_.html#torch.Tensor.scatter_reduce_) but for `regularize_hash_pyramid` it does not have backward pass. Maybe @jkulhanek has some comments...