During the nerf training phase, the value of local_step is incremented by one separately in the run_cuda and train_step functions.
torch-ngp/utils.py#L858torch-ngp/renderer.py#L939
Therefore, local_step will increase by 2 in each epoch, which leads to the step_counter updating only at even positions each time.
During the nerf training phase, the value of
local_stepis incremented by one separately in therun_cudaandtrain_stepfunctions. torch-ngp/utils.py#L858 torch-ngp/renderer.py#L939 Therefore,local_stepwill increase by 2 in each epoch, which leads to thestep_counterupdating only at even positions each time.