ClassNLLCriterion.cu:105: void cunn_ClassNLLCriterion_updateOutput_kernel(Dtype *, Dtype *, Dtype *, long *, Dtype *, int, int, int, int, long) [with Dtype = float, Acctype = float]: block: [0,0,0], thread: [0,0,0] Assertion `t >= 0 && t < n_classes` failed.

[CwwwwS]

when I used this command python main.py -n1 --auto_gpu_config 0 --split val

I got

2021-06-04 21:17:23,075 initializing task Nav-v0 2021-06-04 21:17:23,083 Computing map for data/scene_datasets/gibson/Cantwell.glb num:0 Time: 00d 00h 00m 00s, num timesteps 0, FPS 0, Rewards: Losses: Time: 00d 00h 00m 01s, num timesteps 10, FPS 7, Rewards: Losses: Local Loss: 0.000, /opt/conda/conda-bld/pytorch_1565272279342/work/aten/src/THCUNN/ClassNLLCriterion.cu:105: void cunn_ClassNLLCriterion_updateOutput_kernel(Dtype *, Dtype *, Dtype *, long *, Dtype *, int, int, int, int, long) [with Dtype = float, Acctype = float]: block: [0,0,0], thread: [0,0,0] Assertion t >= 0 && t < n_classes failed. THCudaCheck FAIL file=/opt/conda/condabld/pytorch_1565272279342/work/aten/src/THCUNN/generic/ClassNLLCriterion.cu line=110 error=59 : device-side assert triggered Traceback (most recent call last): File "main.py", line 797, in main() File "main.py", line 372, in main tmp = loss(action_prob, action_target) File "/home/ad-yang/miniconda3/envs/Neural-SLAM/lib/python3.6/site-packages/torch/nn/modules/module.py", line 547, in call result = self.forward(*input, **kwargs) File "/home/ad-yang/miniconda3/envs/Neural-SLAM/lib/python3.6/site-packages/torch/nn/modules/loss.py", line 916, in forward ignore_index=self.ignore_index, reduction=self.reduction) File "/home/ad-yang/miniconda3/envs/Neural-SLAM/lib/python3.6/site-packages/torch/nn/functional.py", line 1995, in cross_entropy return nll_loss(log_softmax(input, 1), target, weight, None, ignore_index, None, reduction) File "/home/ad-yang/miniconda3/envs/Neural-SLAM/lib/python3.6/site-packages/torch/nn/functional.py", line 1824, in nll_loss ret = torch._C._nn.nll_loss(input, target, weight, _Reduction.get_enum(reduction), ignore_index) RuntimeError: cuda runtime error (59) : device-side assert triggered at /opt/conda/conda-bld/pytorch_1565272279342/work/aten/src/THCUNN/generic/ClassNLLCriterion.cu:110

I don't know how to solve this problem. Hope to get your reply.

[devendrachaplot]

This seems to be an issue with your CUDA or pytorch installation and does not seem to be related to the Neural-SLAM code.