Strange Problem

❓ Questions and Help

Traceback (most recent call last): File "webcam.py", line 80, in main() File "webcam.py", line 71, in main composite = coco_demo.run_on_opencv_image(img) File "/media/wjl/New/maskrcnn-benchmark/demo/predictor.py", line 171, in run_on_opencv_image predictions = self.compute_prediction(image) File "/media/wjl/New/maskrcnn-benchmark/demo/predictor.py", line 202, in compute_prediction predictions = self.model(image_list) File "/usr/local/lib/python3.6/dist-packages/torch/nn/modules/module.py", line 489, in call result = self.forward(*input, **kwargs) File "/usr/local/lib/python3.6/dist-packages/maskrcnn_benchmark-0.1-py3.6-linux-x86_64.egg/maskrcnn_benchmark/modeling/detector/generalized_rcnn.py", line 50, in forward proposals, proposal_losses = self.rpn(images, features, targets) File "/usr/local/lib/python3.6/dist-packages/torch/nn/modules/module.py", line 489, in call result = self.forward(*input, **kwargs) File "/usr/local/lib/python3.6/dist-packages/maskrcnn_benchmark-0.1-py3.6-linux-x86_64.egg/maskrcnn_benchmark/modeling/rpn/rpn.py", line 102, in forward return self._forward_test(anchors, objectness, rpn_box_regression) File "/usr/local/lib/python3.6/dist-packages/maskrcnn_benchmark-0.1-py3.6-linux-x86_64.egg/maskrcnn_benchmark/modeling/rpn/rpn.py", line 128, in _forward_test boxes = self.box_selector_test(anchors, objectness, rpn_box_regression) File "/usr/local/lib/python3.6/dist-packages/torch/nn/modules/module.py", line 489, in call result = self.forward(*input, **kwargs) File "/usr/local/lib/python3.6/dist-packages/maskrcnn_benchmark-0.1-py3.6-linux-x86_64.egg/maskrcnn_benchmark/modeling/rpn/inference.py", line 138, in forward sampled_boxes.append(self.forward_for_single_feature_map(a, o, b)) File "/usr/local/lib/python3.6/dist-packages/maskrcnn_benchmark-0.1-py3.6-linux-x86_64.egg/maskrcnn_benchmark/modeling/rpn/inference.py", line 118, in forward_for_single_feature_map score_field="objectness", File "/usr/local/lib/python3.6/dist-packages/maskrcnn_benchmark-0.1-py3.6-linux-x86_64.egg/maskrcnn_benchmark/structures/boxlist_ops.py", line 27, in boxlist_nms keep = _box_nms(boxes, score, nms_thresh) RuntimeError: Dimension out of range (expected to be in range of [-2, 1], but got 2) (maybe_wrap_dim at /media/wjl/New/maskrcnn-benchmark/pytorch/c10/core/WrapDimMinimal.h:18) frame #0: c10::Error::Error(c10::SourceLocation, std::__cxx11::basic_string<char, std::char_traits, std::allocator > const&) + 0x6c (0x7fc2942a37fc in /usr/local/lib/python3.6/dist-packages/torch/lib/libc10.so) frame #1: + 0x5d9bc3 (0x7fc294d19bc3 in /usr/local/lib/python3.6/dist-packages/torch/lib/libcaffe2.so) frame #2: at::native::min_out(at::Tensor&, at::Tensor&, at::Tensor const&, long, bool) + 0x66 (0x7fc294d1d366 in /usr/local/lib/python3.6/dist-packages/torch/lib/libcaffe2.so) frame #3: at::native::min(at::Tensor const&, long, bool) + 0xdd (0x7fc294d1d7fd in /usr/local/lib/python3.6/dist-packages/torch/lib/libcaffe2.so) frame #4: at::TypeDefault::min(at::Tensor const&, long, bool) const + 0x91 (0x7fc294f3a191 in /usr/local/lib/python3.6/dist-packages/torch/lib/libcaffe2.so) frame #5: torch::autograd::VariableType::min(at::Tensor const&, long, bool) const + 0x252 (0x7fc29765f022 in /usr/local/lib/python3.6/dist-packages/torch/lib/libtorch.so.1) frame #6: at::native::argmin(at::Tensor const&, long, bool) + 0x4d (0x7fc294d1b84d in /usr/local/lib/python3.6/dist-packages/torch/lib/libcaffe2.so) frame #7: at::TypeDefault::argmin(at::Tensor const&, long, bool) const + 0x91 (0x7fc294f318d1 in /usr/local/lib/python3.6/dist-packages/torch/lib/libcaffe2.so) frame #8: torch::autograd::VariableType::argmin(at::Tensor const&, long, bool) const + 0x16a (0x7fc29761785a in /usr/local/lib/python3.6/dist-packages/torch/lib/libtorch.so.1) frame #9: at::native::_argmin(at::Tensor const&, long, bool) + 0x48 (0x7fc294d19f18 in /usr/local/lib/python3.6/dist-packages/torch/lib/libcaffe2.so) frame #10: at::TypeDefault::_argmin(at::Tensor const&, long, bool) const + 0x91 (0x7fc294f31ac1 in /usr/local/lib/python3.6/dist-packages/torch/lib/libcaffe2.so) frame #11: torch::autograd::VariableType::_argmin(at::Tensor const&, long, bool) const + 0x16a (0x7fc297615f9a in /usr/local/lib/python3.6/dist-packages/torch/lib/libtorch.so.1) frame #12: nms(at::Tensor const&, at::Tensor const&, float) + 0xc7 (0x7fc26b0a9bb7 in /usr/local/lib/python3.6/dist-packages/maskrcnn_benchmark-0.1-py3.6-linux-x86_64.egg/maskrcnn_benchmark/_C.cpython-36m-x86_64-linux-gnu.so) frame #13: + 0x20a78 (0x7fc26b0b5a78 in /usr/local/lib/python3.6/dist-packages/maskrcnn_benchmark-0.1-py3.6-linux-x86_64.egg/maskrcnn_benchmark/_C.cpython-36m-x86_64-linux-gnu.so) frame #14: + 0x1dd4c (0x7fc26b0b2d4c in /usr/local/lib/python3.6/dist-packages/maskrcnn_benchmark-0.1-py3.6-linux-x86_64.egg/maskrcnn_benchmark/_C.cpython-36m-x86_64-linux-gnu.so) frame #16: python3() [0x54ffe4] frame #18: python3() [0x54fbe1] frame #19: python3() [0x54fe6d] frame #21: python3() [0x54f0e8] frame #22: python3() [0x550116] frame #24: python3() [0x54fbe1] frame #29: python3() [0x54fbe1] frame #33: python3() [0x4e0e9b] frame #35: python3() [0x54fd37] frame #37: python3() [0x54f0e8] frame #38: python3() [0x550116] frame #40: python3() [0x54fbe1] frame #45: python3() [0x54fbe1] frame #49: python3() [0x4e0e9b] frame #51: python3() [0x54fd37] frame #53: python3() [0x54fbe1] frame #58: python3() [0x54fbe1] frame #62: python3() [0x4e0e9b]

Python 3.6 Cuda10.0 Pytorch 1.0 Ubuntu 18.04 Gcc 7