I encountered an error while training the neural renderer

[mioyeah]

/home/lab3090/D/zhujj/Neural_Actor_Main_Code-master/fairnr/criterions/rendering_loss.py:150: UserWarning: floordiv is deprecated, and its behavior will change in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values. To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'), or for actual floor division, use torch.div(a, b, rounding_mode='floor').
flatten_index = (flatten_uv[:,:,0] // h + flatten_uv[:,:,1] // w * W).long()
../aten/src/ATen/native/cuda/ScatterGatherKernel.cu:144: operator(): block: [2,0,0], thread: [64,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
../aten/src/ATen/native/cuda/ScatterGatherKernel.cu:144: operator(): block: [2,0,0], thread: [65,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
../aten/src/ATen/native/cuda/ScatterGatherKernel.cu:144: operator(): block: [2,0,0], thread: [66,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
n/src/ATen/native/cuda/ScatterGatherKernel.cu:144: operator(): block: [0,0,0], thread: [63,0,0] Assertion idx_dim >= 0 && idx_dim < index_size && "index out of bounds" failed.
Traceback (most recent call last):
File "/home/lab3090/D/zhujj/Neural_Actor_Main_Code-master/train.py", line 32, in
cli_main()
File "/home/lab3090/D/zhujj/Neural_Actor_Main_Code-master/fairnr_cli/train.py", line 378, in cli_main
main(args)
File "/home/lab3090/D/zhujj/Neural_Actor_Main_Code-master/fairnr_cli/train.py", line 107, in main
should_end_training = train(args, trainer, task, epoch_itr)
File "/home/lab3090/anaconda3/envs/neuralactor/lib/python3.8/contextlib.py", line 75, in inner
return func(*args, **kwds)
File "/home/lab3090/D/zhujj/Neural_Actor_Main_Code-master/fairnr_cli/train.py", line 184, in train
log_output = trainer.train_step(samples)
File "/home/lab3090/anaconda3/envs/neuralactor/lib/python3.8/contextlib.py", line 75, in inner
return func(*args, **kwds)
File "/home/lab3090/D/zhujj/Neural_Actor_Main_Code-master/fairseq-stable/fairseq/trainer.py", line 457, in train_step
raise e
File "/home/lab3090/D/zhujj/Neural_Actor_Main_Code-master/fairseq-stable/fairseq/trainer.py", line 425, in train_step
loss, sample_size_i, logging_output = self.task.train_step(
File "/home/lab3090/D/zhujj/Neural_Actor_Main_Code-master/fairnr/tasks/neural_rendering.py", line 329, in train_step
return super().train_step(sample, model, criterion, optimizer, update_num, ignore_grad)
File "/home/lab3090/D/zhujj/Neural_Actor_Main_Code-master/fairseq-stable/fairseq/tasks/fairseq_task.py", line 351, in train_step
loss, sample_size, logging_output = criterion(model, sample)
File "/home/lab3090/anaconda3/envs/neuralactor/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1130, in _call_impl
return forward_call(*input, **kwargs)
File "/home/lab3090/D/zhujj/Neural_Actor_Main_Code-master/fairnr/criterions/rendering_loss.py", line 48, in forward
loss, loss_output = self.compute_loss(model, net_output, sample, reduce=reduce)
File "/home/lab3090/D/zhujj/Neural_Actor_Main_Code-master/fairnr/criterions/rendering_loss.py", line 156, in compute_loss
target_colors = target_colors.gather(2, flatten_index.unsqueeze(-1).repeat(1,1,1,3))
RuntimeError: CUDA error: device-side assert triggered
May I ask how to solve it?