data.to(self.device) AttributeError: 'dict' object has no attribute 'to'

[yucedagonurcan]

Hello All,

I am in 'dev' branch in Open3D-ML and 'master' branch in Open3D.

I wanted to try KITTI inference with PointPillars with this script:

It is surely rewrite of the example inference for Object Detection in README.

Here is the error I am getting with this code:

(3d_det) ➜ examples git:(dev) ✗ python kitti_point_pillars.py

Using the Open3D PyTorch ops with CUDA 11 may have stability issues!

We recommend to compile PyTorch from source with compile flags
'-Xcompiler -fno-gnu-unique'

or use the PyTorch wheels at
https://github.com/intel-isl/open3d_downloads/releases/tag/torch1.7.1

Ignore this message if PyTorch has been compiled with the aforementioned
flags.

See isl-org/Open3D#3324 and
pytorch/pytorch#52663 for more information on this
problem.

---

INFO - 2021-05-25 18:14:00,578 - object_detection - Loading checkpoint ./logs/pointpillars_kitti_202012221652utc.pth
INFO - 2021-05-25 18:14:00,620 - kitti - Found 7518 pointclouds for test
Traceback (most recent call last):
File "kitti_point_pillars.py", line 30, in
result = pipeline.run_inference(data)
File "/home/onur/miniconda3/envs/3d_det/lib/python3.6/site-packages/open3d/_ml3d/torch/pipelines/object_detection.py", line 62, in run_inference
data.to(self.device)
AttributeError: 'dict' object has no attribute 'to'

- Okay, I commented out the result = pipeline.run_inference(data) line and tried again since run_test function will create ConcatBatcher and then moves the object to the cuda (run_inference gets a dictionary and tries to move it to cuda that's why the earlier error occurs.). I thought it would be fine but there is another error that I am not quite sure if it is about Open3D or torch or my CUDA:

(3d_det) ➜ examples git:(dev) ✗ python kitti_point_pillars.py

---

Using the Open3D PyTorch ops with CUDA 11 may have stability issues!

We recommend to compile PyTorch from source with compile flags
'-Xcompiler -fno-gnu-unique'

or use the PyTorch wheels at
https://github.com/intel-isl/open3d_downloads/releases/tag/torch1.7.1

Ignore this message if PyTorch has been compiled with the aforementioned
flags.

See isl-org/Open3D#3324 and
pytorch/pytorch#52663 for more information on this
problem.

---

INFO - 2021-05-25 18:21:21,330 - object_detection - Loading checkpoint ./logs/pointpillars_kitti_202012221652utc.pth
INFO - 2021-05-25 18:21:21,375 - kitti - Found 7518 pointclouds for test
INFO - 2021-05-25 18:21:21,381 - object_detection - DEVICE : cuda
INFO - 2021-05-25 18:21:21,381 - object_detection - Logging in file : ./logs/PointPillars_KITTI_torch/log_test_2021-05-25_18:21:21.txt
INFO - 2021-05-25 18:21:21,381 - kitti - Found 7518 pointclouds for test
INFO - 2021-05-25 18:21:21,382 - object_detection - Initializing from scratch.
INFO - 2021-05-25 18:21:21,382 - object_detection - DEVICE : cuda
INFO - 2021-05-25 18:21:21,382 - object_detection - Logging in file : ./logs/PointPillars_KITTI_torch/log_valid_2021-05-25_18:21:21.txt
INFO - 2021-05-25 18:21:21,382 - kitti - Found 3769 pointclouds for validation
INFO - 2021-05-25 18:21:21,382 - object_detection - Started validation
validation: 0%| | 0/3769 [00:00<?, ?it/s]/pytorch/aten/src/ATen/native/cuda/IndexKernel.cu:142: operator(): block: [0,0,0], thread: [0,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/IndexKernel.cu:142: operator(): block: [0,0,0], thread: [1,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/IndexKernel.cu:142: operator(): block: [0,0,0], thread: [2,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/IndexKernel.cu:142: operator(): block: [0,0,0], thread: [3,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/IndexKernel.cu:142: operator(): block: [0,0,0], thread: [4,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/IndexKernel.cu:142: operator(): block: [0,0,0], thread: [5,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/IndexKernel.cu:142: operator(): block: [0,0,0], thread: [6,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/IndexKernel.cu:142: operator(): block: [0,0,0], thread: [7,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/IndexKernel.cu:142: operator(): block: [0,0,0], thread: [8,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/IndexKernel.cu:142: operator(): block: [0,0,0], thread: [9,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/IndexKernel.cu:142: operator(): block: [0,0,0], thread: [10,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/IndexKernel.cu:142: operator(): block: [0,0,0], thread: [11,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/IndexKernel.cu:142: operator(): block: [0,0,0], thread: [12,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/IndexKernel.cu:142: operator(): block: [0,0,0], thread: [13,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/IndexKernel.cu:142: operator(): block: [0,0,0], thread: [14,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/IndexKernel.cu:142: operator(): block: [0,0,0], thread: [15,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/IndexKernel.cu:142: operator(): block: [0,0,0], thread: [16,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/IndexKernel.cu:142: operator(): block: [0,0,0], thread: [17,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/IndexKernel.cu:142: operator(): block: [0,0,0], thread: [18,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/IndexKernel.cu:142: operator(): block: [0,0,0], thread: [19,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/IndexKernel.cu:142: operator(): block: [0,0,0], thread: [20,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/IndexKernel.cu:142: operator(): block: [0,0,0], thread: [21,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/IndexKernel.cu:142: operator(): block: [0,0,0], thread: [22,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/IndexKernel.cu:142: operator(): block: [0,0,0], thread: [23,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/IndexKernel.cu:142: operator(): block: [0,0,0], thread: [24,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/IndexKernel.cu:142: operator(): block: [0,0,0], thread: [25,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/IndexKernel.cu:142: operator(): block: [0,0,0], thread: [26,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/IndexKernel.cu:142: operator(): block: [0,0,0], thread: [27,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/IndexKernel.cu:142: operator(): block: [0,0,0], thread: [28,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/IndexKernel.cu:142: operator(): block: [0,0,0], thread: [29,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/IndexKernel.cu:142: operator(): block: [0,0,0], thread: [30,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/IndexKernel.cu:142: operator(): block: [0,0,0], thread: [31,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed.
validation: 0%| | 0/3769 [00:00<?, ?it/s]
Traceback (most recent call last):
File "kitti_point_pillars.py", line 33, in
pipeline.run_test()
File "/home/onur/miniconda3/envs/3d_det/lib/python3.6/site-packages/open3d/_ml3d/torch/pipelines/object_detection.py", line 107, in run_test
self.run_valid()
File "/home/onur/miniconda3/envs/3d_det/lib/python3.6/site-packages/open3d/_ml3d/torch/pipelines/object_detection.py", line 165, in run_valid
results = model(data)
File "/home/onur/.local/lib/python3.6/site-packages/torch/nn/modules/module.py", line 889, in _call_impl
result = self.forward(*input, **kwargs)
File "/home/onur/miniconda3/envs/3d_det/lib/python3.6/site-packages/open3d/_ml3d/torch/models/point_pillars.py", line 133, in forward
x = self.extract_feats(inputs)
File "/home/onur/miniconda3/envs/3d_det/lib/python3.6/site-packages/open3d/_ml3d/torch/models/point_pillars.py", line 108, in extract_feats
x = self.middle_encoder(voxel_features, coors, batch_size)
File "/home/onur/.local/lib/python3.6/site-packages/torch/nn/modules/module.py", line 889, in _call_impl
result = self.forward(*input, **kwargs)
File "/home/onur/miniconda3/envs/3d_det/lib/python3.6/site-packages/open3d/_ml3d/torch/models/point_pillars.py", line 619, in forward
voxels = voxel_features[batch_mask, :]
RuntimeError: CUDA error: device-side assert triggered

I am quite beginner to codebase as you can understand. What am I missing here?

Have a great day.

[yucedagonurcan]

Fixed with new version

[ghost]

Hi, we are having the same issue as your last error message. Could you please clarify what new version and steps helped you fix it?