Error when use torch.jit.trace

[NickYangMin]

/home/yangmin/deeplearning/pytorch/detections/mmdetection_ym/mmdet/models/detectors/base.py:71: TracerWarning: Converting a tensor to a Python boolean might cause the trace to be incorrect. We can't record the data flow of Python values, so this value will be treated as a constant in the future. This means that the trace might not generalize to other inputs!
assert imgs_per_gpu == 1
/home/yangmin/deeplearning/pytorch/detections/mmdetection_ym/mmdet/core/anchor/anchor_generator.py:46: TracerWarning: Converting a tensor to a Python index might cause the trace to be incorrect. We can't record the data flow of Python values, so this value will be treated as a constant in the future. This means that the trace might not generalize to other inputs!
xx = x.repeat(len(y))
/home/yangmin/deeplearning/pytorch/detections/mmdetection_ym/mmdet/core/anchor/anchor_generator.py:47: TracerWarning: Converting a tensor to a Python index might cause the trace to be incorrect. We can't record the data flow of Python values, so this value will be treated as a constant in the future. This means that the trace might not generalize to other inputs!
yy = y.view(-1, 1).repeat(1, len(x)).view(-1)
/home/yangmin/deeplearning/pytorch/detections/mmdetection_ym/mmdet/models/anchor_heads/rpn_head.py:67: TracerWarning: Converting a tensor to a Python boolean might cause the trace to be incorrect. We can't record the data flow of Python values, so this value will be treated as a constant in the future. This means that the trace might not generalize to other inputs!
assert rpn_cls_score.size()[-2:] == rpn_bbox_pred.size()[-2:]
/home/yangmin/deeplearning/pytorch/detections/mmdetection_ym/mmdet/models/anchor_heads/rpn_head.py:77: TracerWarning: Converting a tensor to a Python boolean might cause the trace to be incorrect. We can't record the data flow of Python values, so this value will be treated as a constant in the future. This means that the trace might not generalize to other inputs!
if cfg.nms_pre > 0 and scores.shape[0] > cfg.nms_pre:
/home/yangmin/deeplearning/pytorch/detections/mmdetection_ym/mmdet/ops/nms/nms_wrapper.py:39: TracerWarning: Converting a tensor to a Python boolean might cause the trace to be incorrect. We can't record the data flow of Python values, so this value will be treated as a constant in the future. This means that the trace might not generalize to other inputs!
if dets_th.shape[0] == 0:
/home/yangmin/deeplearning/pytorch/detections/mmdetection_ym/mmdet/models/anchor_heads/rpn_head.py:101: TracerWarning: Converting a tensor to a Python boolean might cause the trace to be incorrect. We can't record the data flow of Python values, so this value will be treated as a constant in the future. This means that the trace might not generalize to other inputs!
num = min(cfg.max_num, proposals.shape[0])
/home/yangmin/deeplearning/pytorch/detections/mmdetection_ym/mmdet/core/bbox/transforms.py:118: TracerWarning: Converting a tensor to a Python boolean might cause the trace to be incorrect. We can't record the data flow of Python values, so this value will be treated as a constant in the future. This means that the trace might not generalize to other inputs!
if bboxes.size(0) > 0:
/home/yangmin/deeplearning/pytorch/detections/mmdetection_ym/mmdet/models/roi_extractors/single_level.py:81: TracerWarning: Converting a tensor to a Python index might cause the trace to be incorrect. We can't record the data flow of Python values, so this value will be treated as a constant in the future. This means that the trace might not generalize to other inputs!
out_size, out_size).fill_(0)
/home/yangmin/deeplearning/pytorch/detections/mmdetection_ym/mmdet/models/roi_extractors/single_level.py:84: TracerWarning: Converting a tensor to a Python boolean might cause the trace to be incorrect. We can't record the data flow of Python values, so this value will be treated as a constant in the future. This means that the trace might not generalize to other inputs!
if inds.any():
/home/yangmin/deeplearning/pytorch/detections/mmdetection_ym/mmdet/models/bbox_heads/bbox_head.py:186: TracerWarning: Converting a tensor to a Python boolean might cause the trace to be incorrect. We can't record the data flow of Python values, so this value will be treated as a constant in the future. This means that the trace might not generalize to other inputs!
assert rois.size(1) == 4 or rois.size(1) == 5
/home/yangmin/deeplearning/pytorch/detections/mmdetection_ym/mmdet/models/bbox_heads/bbox_head.py:192: TracerWarning: Converting a tensor to a Python boolean might cause the trace to be incorrect. We can't record the data flow of Python values, so this value will be treated as a constant in the future. This means that the trace might not generalize to other inputs!
assert bbox_pred.size(1) == 4
/home/yangmin/deeplearning/pytorch/detections/mmdetection_ym/mmdet/models/bbox_heads/bbox_head.py:194: TracerWarning: Converting a tensor to a Python boolean might cause the trace to be incorrect. We can't record the data flow of Python values, so this value will be treated as a constant in the future. This means that the trace might not generalize to other inputs!
if rois.size(1) == 4:
/home/yangmin/deeplearning/pytorch/detections/mmdetection_ym/mmdet/core/post_processing/bbox_nms.py:27: TracerWarning: Converting a tensor to a Python index might cause the trace to be incorrect. We can't record the data flow of Python values, so this value will be treated as a constant in the future. This means that the trace might not generalize to other inputs!
for i in range(1, num_classes):
/home/yangmin/deeplearning/pytorch/detections/mmdetection_ym/mmdet/core/post_processing/bbox_nms.py:29: TracerWarning: Converting a tensor to a Python boolean might cause the trace to be incorrect. We can't record the data flow of Python values, so this value will be treated as a constant in the future. This means that the trace might not generalize to other inputs!
if not cls_inds.any():
/home/yangmin/deeplearning/pytorch/detections/mmdetection_ym/mmdet/core/post_processing/bbox_nms.py:32: TracerWarning: Converting a tensor to a Python boolean might cause the trace to be incorrect. We can't record the data flow of Python values, so this value will be treated as a constant in the future. This means that the trace might not generalize to other inputs!
if multi_bboxes.shape[1] == 4:
/home/yangmin/deeplearning/pytorch/detections/mmdetection_ym/mmdet/core/post_processing/bbox_nms.py:46: TracerWarning: Converting a tensor to a Python boolean might cause the trace to be incorrect. We can't record the data flow of Python values, so this value will be treated as a constant in the future. This means that the trace might not generalize to other inputs!
if bboxes.shape[0] > max_num:
/home/yangmin/deeplearning/pytorch/detections/mmdetection_ym/mmdet/core/bbox/transforms.py:149: TracerWarning: Converting a tensor to a Python boolean might cause the trace to be incorrect. We can't record the data flow of Python values, so this value will be treated as a constant in the future. This means that the trace might not generalize to other inputs!
if bboxes.shape[0] == 0:
/home/yangmin/deeplearning/pytorch/detections/mmdetection_ym/mmdet/core/bbox/transforms.py:154: TracerWarning: Converting a tensor to a NumPy array might cause the trace to be incorrect. We can't record the data flow of Python values, so this value will be treated as a constant in the future. This means that the trace might not generalize to other inputs!
bboxes = bboxes.cpu().detach().numpy()
/home/yangmin/deeplearning/pytorch/detections/mmdetection_ym/mmdet/core/bbox/transforms.py:155: TracerWarning: Converting a tensor to a NumPy array might cause the trace to be incorrect. We can't record the data flow of Python values, so this value will be treated as a constant in the future. This means that the trace might not generalize to other inputs!
labels = labels.cpu().detach().numpy()
/home/yangmin/deeplearning/pytorch/detections/mmdetection_ym/mmdet/models/detectors/cascade_rcnn.py:330: TracerWarning: torch.Tensor results are registered as constants in the trace. You can safely ignore this warning if you use this function to create tensors out of constant variables that would be the same every time you call this function. In any other case, this might cause the trace to be incorrect.
return torch.Tensor(results[0])
/pytorch/aten/src/ATen/native/cuda/IndexKernel.cu:53: lambda ->auto::operator()(int)->auto: block: [0,0,0], thread: [96,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/IndexKernel.cu:53: lambda ->auto::operator()(int)->auto: block: [0,0,0], thread: [97,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/IndexKernel.cu:53: lambda ->auto::operator()(int)->auto: block: [0,0,0], thread: [100,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/IndexKernel.cu:53: lambda ->auto::operator()(int)->auto: block: [0,0,0], thread: [101,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/IndexKernel.cu:53: lambda ->auto::operator()(int)->auto: block: [0,0,0], thread: [104,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/IndexKernel.cu:53: lambda ->auto::operator()(int)->auto: block: [0,0,0], thread: [105,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/IndexKernel.cu:53: lambda ->auto::operator()(int)->auto: block: [0,0,0], thread: [108,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/IndexKernel.cu:53: lambda ->auto::operator()(int)->auto: block: [0,0,0], thread: [109,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/IndexKernel.cu:53: lambda ->auto::operator()(int)->auto: block: [0,0,0], thread: [112,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/IndexKernel.cu:53: lambda ->auto::operator()(int)->auto: block: [0,0,0], thread: [113,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/IndexKernel.cu:53: lambda ->auto::operator()(int)->auto: block: [0,0,0], thread: [116,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/IndexKernel.cu:53: lambda ->auto::operator()(int)->auto: block: [0,0,0], thread: [117,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/IndexKernel.cu:53: lambda ->auto::operator()(int)->auto: block: [0,0,0], thread: [120,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/IndexKernel.cu:53: lambda ->auto::operator()(int)->auto: block: [0,0,0], thread: [121,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/IndexKernel.cu:53: lambda ->auto::operator()(int)->auto: block: [0,0,0], thread: [124,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/IndexKernel.cu:53: lambda ->auto::operator()(int)->auto: block: [0,0,0], thread: [125,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/IndexKernel.cu:53: lambda ->auto::operator()(int)->auto: 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:53: lambda ->auto::operator()(int)->auto: 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:53: lambda ->auto::operator()(int)->auto: 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:53: lambda ->auto::operator()(int)->auto: 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:53: lambda ->auto::operator()(int)->auto: 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:53: lambda ->auto::operator()(int)->auto: 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:53: lambda ->auto::operator()(int)->auto: 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:53: lambda ->auto::operator()(int)->auto: 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:53: lambda ->auto::operator()(int)->auto: 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:53: lambda ->auto::operator()(int)->auto: 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:53: lambda ->auto::operator()(int)->auto: 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:53: lambda ->auto::operator()(int)->auto: 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:53: lambda ->auto::operator()(int)->auto: 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:53: lambda ->auto::operator()(int)->auto: 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:53: lambda ->auto::operator()(int)->auto: 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:53: lambda ->auto::operator()(int)->auto: 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:53: lambda ->auto::operator()(int)->auto: 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:53: lambda ->auto::operator()(int)->auto: block: [0,0,0], thread: [39,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/IndexKernel.cu:53: lambda ->auto::operator()(int)->auto: block: [0,0,0], thread: [40,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/IndexKernel.cu:53: lambda ->auto::operator()(int)->auto: block: [0,0,0], thread: [41,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/IndexKernel.cu:53: lambda ->auto::operator()(int)->auto: block: [0,0,0], thread: [42,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/IndexKernel.cu:53: lambda ->auto::operator()(int)->auto: block: [0,0,0], thread: [43,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/IndexKernel.cu:53: lambda ->auto::operator()(int)->auto: block: [0,0,0], thread: [44,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/IndexKernel.cu:53: lambda ->auto::operator()(int)->auto: block: [0,0,0], thread: [45,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/IndexKernel.cu:53: lambda ->auto::operator()(int)->auto: block: [0,0,0], thread: [48,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/IndexKernel.cu:53: lambda ->auto::operator()(int)->auto: block: [0,0,0], thread: [49,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/IndexKernel.cu:53: lambda ->auto::operator()(int)->auto: block: [0,0,0], thread: [52,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/IndexKernel.cu:53: lambda ->auto::operator()(int)->auto: block: [0,0,0], thread: [53,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/IndexKernel.cu:53: lambda ->auto::operator()(int)->auto: block: [0,0,0], thread: [56,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/IndexKernel.cu:53: lambda ->auto::operator()(int)->auto: block: [0,0,0], thread: [57,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/IndexKernel.cu:53: lambda ->auto::operator()(int)->auto: block: [0,0,0], thread: [60,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/IndexKernel.cu:53: lambda ->auto::operator()(int)->auto: block: [0,0,0], thread: [61,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/IndexKernel.cu:53: lambda ->auto::operator()(int)->auto: block: [0,0,0], thread: [64,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/IndexKernel.cu:53: lambda ->auto::operator()(int)->auto: block: [0,0,0], thread: [65,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/IndexKernel.cu:53: lambda ->auto::operator()(int)->auto: block: [0,0,0], thread: [68,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/IndexKernel.cu:53: lambda ->auto::operator()(int)->auto: block: [0,0,0], thread: [69,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/IndexKernel.cu:53: lambda ->auto::operator()(int)->auto: block: [0,0,0], thread: [72,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/IndexKernel.cu:53: lambda ->auto::operator()(int)->auto: block: [0,0,0], thread: [73,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/IndexKernel.cu:53: lambda ->auto::operator()(int)->auto: block: [0,0,0], thread: [77,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/IndexKernel.cu:53: lambda ->auto::operator()(int)->auto: block: [0,0,0], thread: [79,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/IndexKernel.cu:53: lambda ->auto::operator()(int)->auto: block: [0,0,0], thread: [80,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/IndexKernel.cu:53: lambda ->auto::operator()(int)->auto: block: [0,0,0], thread: [81,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/IndexKernel.cu:53: lambda ->auto::operator()(int)->auto: block: [0,0,0], thread: [82,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/IndexKernel.cu:53: lambda ->auto::operator()(int)->auto: block: [0,0,0], thread: [83,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/IndexKernel.cu:53: lambda ->auto::operator()(int)->auto: block: [0,0,0], thread: [84,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/IndexKernel.cu:53: lambda ->auto::operator()(int)->auto: block: [0,0,0], thread: [86,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/IndexKernel.cu:53: lambda ->auto::operator()(int)->auto: block: [0,0,0], thread: [87,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/IndexKernel.cu:53: lambda ->auto::operator()(int)->auto: block: [0,0,0], thread: [88,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/IndexKernel.cu:53: lambda ->auto::operator()(int)->auto: block: [0,0,0], thread: [89,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/IndexKernel.cu:53: lambda ->auto::operator()(int)->auto: block: [0,0,0], thread: [92,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed.
/pytorch/aten/src/ATen/native/cuda/IndexKernel.cu:53: lambda ->auto::operator()(int)->auto: block: [0,0,0], thread: [93,0,0] Assertion index >= -sizes[i] && index < sizes[i] && "index out of bounds" failed.
Traceback (most recent call last):
File "/home/yangmin/.local/lib/python3.5/site-packages/torch/jit/init.py", line 500, in run_mod_and_filter_tensor_outputs
outs = wrap_retval(mod(*_clone_inputs(inputs)))
File "/home/yangmin/.local/lib/python3.5/site-packages/torch/nn/modules/module.py", line 489, in call
result = self.forward(*input, **kwargs)
File "/home/yangmin/.local/lib/python3.5/site-packages/torch/jit/init.py", line 1347, in forward
return self.get_method('forward')(*args, **kwargs)
RuntimeError:
CUDA error: device-side assert triggered (copy_from_cpu at /pytorch/aten/src/ATen/native/cuda/Copy.cu:178)
frame #0: std::function<std::string ()>::operator()() const + 0x11 (0x7f876bbe3021 in /home/yangmin/.local/lib/python3.5/site-packages/torch/lib/libc10.so)
frame #1: c10::Error::Error(c10::SourceLocation, std::string const&) + 0x2a (0x7f876bbe28ea in /home/yangmin/.local/lib/python3.5/site-packages/torch/lib/libc10.so)
frame #2: (anonymous namespace)::copy_from_cpu(at::Tensor&, at::Tensor const&) + 0x4ab (0x7f87201a1aab in /home/yangmin/.local/lib/python3.5/site-packages/torch/lib/libcaffe2_gpu.so)
frame #3: void (anonymous namespace)::copy__cuda(at::Tensor&, at::Tensor const&, bool) + 0xd35 (0x7f8720238a75 in /home/yangmin/.local/lib/python3.5/site-packages/torch/lib/libcaffe2_gpu.so)
frame #4: at::native::s_copy__cuda(at::Tensor&, at::Tensor const&, bool) + 0x225 (0x7f87201a1e65 in /home/yangmin/.local/lib/python3.5/site-packages/torch/lib/libcaffe2_gpu.so)
frame #5: at::CUDAFloatType::s_copy(at::Tensor&, at::Tensor const&, bool) const + 0x62 (0x7f871f124342 in /home/yangmin/.local/lib/python3.5/site-packages/torch/lib/libcaffe2_gpu.so)
frame #6: torch::autograd::VariableType::s_copy(at::Tensor&, at::Tensor const&, bool) const + 0x9f2 (0x7f8761d6e0a2 in /home/yangmin/.local/lib/python3.5/site-packages/torch/lib/libtorch.so.1)
frame #7: at::TypeDefault::copy(at::Tensor&, at::Tensor const&, bool) const + 0x108 (0x7f8714a25ed8 in /home/yangmin/.local/lib/python3.5/site-packages/torch/lib/libcaffe2.so)
frame #8: at::TypeDefault::copy(at::Tensor const&, bool, c10::optionalc10::Device) const + 0x322 (0x7f87149edf42 in /home/yangmin/.local/lib/python3.5/site-packages/torch/lib/libcaffe2.so)
frame #9: + 0x977f47 (0x7f8714813f47 in /home/yangmin/.local/lib/python3.5/site-packages/torch/lib/libcaffe2.so)
frame #10: at::native::to(at::Tensor const&, c10::Device, c10::ScalarType, bool, bool) + 0x4c8 (0x7f8714816958 in /home/yangmin/.local/lib/python3.5/site-packages/torch/lib/libcaffe2.so)
frame #11: at::TypeDefault::to(at::Tensor const&, c10::Device, c10::ScalarType, bool, bool) const + 0x1b (0x7f87149b451b in /home/yangmin/.local/lib/python3.5/site-packages/torch/lib/libcaffe2.so)
frame #12: torch::autograd::VariableType::to(at::Tensor const&, c10::Device, c10::ScalarType, bool, bool) const + 0x18c (0x7f8761ca3e4c in /home/yangmin/.local/lib/python3.5/site-packages/torch/lib/libtorch.so.1)
frame #13: + 0x60c678 (0x7f8761e52678 in /home/yangmin/.local/lib/python3.5/site-packages/torch/lib/libtorch.so.1)
frame #14: + 0x672286 (0x7f8761eb8286 in /home/yangmin/.local/lib/python3.5/site-packages/torch/lib/libtorch.so.1)
frame #15: torch::jit::InterpreterState::run(std::vector<c10::IValue, std::allocatorc10::IValue >&) + 0x22 (0x7f8761eb3842 in /home/yangmin/.local/lib/python3.5/site-packages/torch/lib/libtorch.so.1)
frame #16: + 0x65c6ac (0x7f8761ea26ac in /home/yangmin/.local/lib/python3.5/site-packages/torch/lib/libtorch.so.1)
frame #17: + 0x3c7b94 (0x7f876506eb94 in /home/yangmin/.local/lib/python3.5/site-packages/torch/lib/libtorch_python.so)
frame #18: + 0x3ac00a (0x7f876505300a in /home/yangmin/.local/lib/python3.5/site-packages/torch/lib/libtorch_python.so)
frame #19: + 0x11642e (0x7f8764dbd42e in /home/yangmin/.local/lib/python3.5/site-packages/torch/lib/libtorch_python.so)
frame #20: PyCFunction_Call + 0x77 (0x4ea137 in /usr/bin/python3.5)
frame #21: PyObject_Call + 0x47 (0x5c20e7 in /usr/bin/python3.5)
frame #22: /usr/bin/python3.5() [0x4fbfce]
frame #23: PyObject_Call + 0x47 (0x5c20e7 in /usr/bin/python3.5)
frame #24: /usr/bin/python3.5() [0x574db6]
frame #25: PyObject_Call + 0x47 (0x5c20e7 in /usr/bin/python3.5)
frame #26: PyEval_EvalFrameEx + 0x252b (0x538cab in /usr/bin/python3.5)
frame #27: PyEval_EvalCodeEx + 0x13b (0x540b0b in /usr/bin/python3.5)
frame #28: /usr/bin/python3.5() [0x4ec3f7]
frame #29: PyObject_Call + 0x47 (0x5c20e7 in /usr/bin/python3.5)
frame #30: PyEval_EvalFrameEx + 0x252b (0x538cab in /usr/bin/python3.5)
frame #31: PyEval_EvalCodeEx + 0x13b (0x540b0b in /usr/bin/python3.5)
frame #32: /usr/bin/python3.5() [0x4ec2e3]
frame #33: PyObject_Call + 0x47 (0x5c20e7 in /usr/bin/python3.5)
frame #34: /usr/bin/python3.5() [0x4fbfce]
frame #35: PyObject_Call + 0x47 (0x5c20e7 in /usr/bin/python3.5)
frame #36: /usr/bin/python3.5() [0x574db6]
frame #37: PyObject_Call + 0x47 (0x5c20e7 in /usr/bin/python3.5)
frame #38: PyEval_EvalFrameEx + 0x252b (0x538cab in /usr/bin/python3.5)
frame #39: /usr/bin/python3.5() [0x5401ef]
frame #40: PyEval_EvalFrameEx + 0x5513 (0x53bc93 in /usr/bin/python3.5)
frame #41: PyEval_EvalCodeEx + 0x87a (0x54124a in /usr/bin/python3.5)
frame #42: /usr/bin/python3.5() [0x4ec3f7]
frame #43: PyObject_Call + 0x47 (0x5c20e7 in /usr/bin/python3.5)
frame #44: PyEval_EvalFrameEx + 0x252b (0x538cab in /usr/bin/python3.5)
frame #45: /usr/bin/python3.5() [0x5401ef]
frame #46: PyEval_EvalFrameEx + 0x5513 (0x53bc93 in /usr/bin/python3.5)
frame #47: /usr/bin/python3.5() [0x53fc97]
frame #48: PyEval_EvalFrameEx + 0x50bf (0x53b83f in /usr/bin/python3.5)
frame #49: PyEval_EvalFrameEx + 0x4b14 (0x53b294 in /usr/bin/python3.5)
frame #50: /usr/bin/python3.5() [0x53fc97]
frame #51: PyEval_EvalCode + 0x1f (0x5409bf in /usr/bin/python3.5)
frame #52: /usr/bin/python3.5() [0x54a435]
frame #53: PyCFunction_Call + 0x4f (0x4ea10f in /usr/bin/python3.5)
frame #54: PyEval_EvalFrameEx + 0x81b5 (0x53e935 in /usr/bin/python3.5)
frame #55: /usr/bin/python3.5() [0x53fc97]
frame #56: PyEval_EvalFrameEx + 0x50bf (0x53b83f in /usr/bin/python3.5)
frame #57: /usr/bin/python3.5() [0x53fc97]
frame #58: PyEval_EvalFrameEx + 0x50bf (0x53b83f in /usr/bin/python3.5)
frame #59: /usr/bin/python3.5() [0x53fc97]
frame #60: PyEval_EvalCode + 0x1f (0x5409bf in /usr/bin/python3.5)
frame #61: /usr/bin/python3.5() [0x60cb42]
frame #62: PyRun_FileExFlags + 0x9a (0x60efea in /usr/bin/python3.5)
frame #63: PyRun_SimpleFileExFlags + 0x1bc (0x60f7dc in /usr/bin/python3.5)
:
operation failed in interpreter:
/home/yangmin/deeplearning/pytorch/detections/mmdetection_ym/mmdet/core/bbox/transforms.py(40): delta2bbox
/home/yangmin/deeplearning/pytorch/detections/mmdetection_ym/mmdet/models/anchor_heads/rpn_head.py(83): get_bboxes_single
/home/yangmin/deeplearning/pytorch/detections/mmdetection_ym/mmdet/models/anchor_heads/anchor_head.py(239): get_bboxes
/home/yangmin/deeplearning/pytorch/detections/mmdetection_ym/mmdet/models/detectors/test_mixins.py(10): simple_test_rpn
/home/yangmin/deeplearning/pytorch/detections/mmdetection_ym/mmdet/models/detectors/cascade_rcnn.py(216): simple_test
/home/yangmin/deeplearning/pytorch/detections/mmdetection_ym/mmdet/models/detectors/base.py(74): forward_test
/home/yangmin/deeplearning/pytorch/detections/mmdetection_ym/mmdet/models/detectors/base.py(90): forward
/home/yangmin/.local/lib/python3.5/site-packages/torch/nn/modules/module.py(477): _slow_forward
/home/yangmin/.local/lib/python3.5/site-packages/torch/nn/modules/module.py(487): call
/home/yangmin/.local/lib/python3.5/site-packages/torch/jit/init.py(636): trace
/home/yangmin/deeplearning/pytorch/detections/mmdetection_ym/tools/traced_script_module.py(164): main
/home/yangmin/deeplearning/pytorch/detections/mmdetection_ym/tools/traced_script_module.py(168):
/usr/lib/pycharm-community/helpers/pydev/_pydev_imps/_pydev_execfile.py(18): execfile
/usr/lib/pycharm-community/helpers/pydev/pydevd.py(974): run
/usr/lib/pycharm-community/helpers/pydev/pydevd.py(1596):

[soumith]

you actually have out-of-bounds indices.

[NickYangMin]

why this error only happen in function "run_mod_and_filter_tensor_outputs"?@soumith

[NickYangMin]

In trace->_check_trace->run_mod_and_filter_tensor_output @soumith