search

skyhehe123 / SA-SSD

SA-SSD: Structure Aware Single-stage 3D Object Detection from Point Cloud (CVPR 2020)
493 stars 106 forks source link

RuntimeError: Expected object of backend CUDA but got backend CPU for sequence element 1 in sequence argument at position #1 'tensors' #72

Open Rajat-Mehta opened 4 years ago

Rajat-Mehta commented 4 years ago

I am not able to train the model, getting error related to CUDA. 

python train.py configs/car_cfg.py 
2020-09-29 16:35:43,686 - INFO - Distributed training: False
2020-09-29 16:35:43,686 - INFO - Set random seed to 0
[40, 1600, 1408]
load 14357 Car database infos
After filter database:
load 10520 Car database infos
2020-09-29 16:35:47,934 - INFO - **********************Start training**********************
/home/rajat/Desktop/Radspot/Lidar-object-detection/SA-SSD/mmdet/core/bbox3d/geometry.py:76: NumbaWarning: 
Compilation is falling back to object mode WITH looplifting enabled because Function "corner_to_surfaces_3d" failed type inference due to: No implementation of function Function(<built-in function array>) found for signature:

 >>> array(list(list(array(float32, 2d, A))<iv=None>)<iv=None>)

There are 2 candidate implementations:
  - Of which 2 did not match due to:
  Overload in function 'array': File: numba/core/typing/npydecl.py: Line 482.
    With argument(s): '(list(list(array(float32, 2d, A))<iv=None>)<iv=None>)':
   Rejected as the implementation raised a specific error:
     TypingError: array(float32, 2d, A) not allowed in a homogeneous sequence
  raised from /home/rajat/Desktop/Radspot/Lidar-object-detection/SA-SSD/venv/lib/python3.6/site-packages/numba/core/typing/npydecl.py:449

During: resolving callee type: Function(<built-in function array>)
During: typing of call at /home/rajat/Desktop/Radspot/Lidar-object-detection/SA-SSD/mmdet/core/bbox3d/geometry.py (93)

File "mmdet/core/bbox3d/geometry.py", line 93:
def corner_to_surfaces_3d(corners):
    <source elided>
        [corners[:, 0], corners[:, 4], corners[:, 5], corners[:, 1]],
        [corners[:, 3], corners[:, 2], corners[:, 6], corners[:, 7]],
        ^

  @numba.jit(nopython=False)
2020-09-29 16:35:52,047 - INFO - finding looplift candidates
/home/rajat/Desktop/Radspot/Lidar-object-detection/SA-SSD/mmdet/core/bbox3d/geometry.py:76: NumbaWarning: 
Compilation is falling back to object mode WITH looplifting enabled because Function "corner_to_surfaces_3d" failed type inference due to: No implementation of function Function(<built-in function array>) found for signature:

 >>> array(list(list(array(float32, 2d, A))<iv=None>)<iv=None>)

There are 2 candidate implementations:
  - Of which 2 did not match due to:
  Overload in function 'array': File: numba/core/typing/npydecl.py: Line 482.
    With argument(s): '(list(list(array(float32, 2d, A))<iv=None>)<iv=None>)':
   Rejected as the implementation raised a specific error:
     TypingError: array(float32, 2d, A) not allowed in a homogeneous sequence
  raised from /home/rajat/Desktop/Radspot/Lidar-object-detection/SA-SSD/venv/lib/python3.6/site-packages/numba/core/typing/npydecl.py:449

During: resolving callee type: Function(<built-in function array>)
During: typing of call at /home/rajat/Desktop/Radspot/Lidar-object-detection/SA-SSD/mmdet/core/bbox3d/geometry.py (93)

File "mmdet/core/bbox3d/geometry.py", line 93:
def corner_to_surfaces_3d(corners):
    <source elided>
        [corners[:, 0], corners[:, 4], corners[:, 5], corners[:, 1]],
        [corners[:, 3], corners[:, 2], corners[:, 6], corners[:, 7]],
        ^

  @numba.jit(nopython=False)
2020-09-29 16:35:52,101 - INFO - finding looplift candidates
/home/rajat/Desktop/Radspot/Lidar-object-detection/SA-SSD/mmdet/core/bbox3d/geometry.py:76: NumbaWarning: 
Compilation is falling back to object mode WITH looplifting enabled because Function "corner_to_surfaces_3d" failed type inference due to: No implementation of function Function(<built-in function array>) found for signature:

 >>> array(list(list(array(float32, 2d, A))<iv=None>)<iv=None>)

There are 2 candidate implementations:
  - Of which 2 did not match due to:
  Overload in function 'array': File: numba/core/typing/npydecl.py: Line 482.
    With argument(s): '(list(list(array(float32, 2d, A))<iv=None>)<iv=None>)':
   Rejected as the implementation raised a specific error:
     TypingError: array(float32, 2d, A) not allowed in a homogeneous sequence
  raised from /home/rajat/Desktop/Radspot/Lidar-object-detection/SA-SSD/venv/lib/python3.6/site-packages/numba/core/typing/npydecl.py:449

During: resolving callee type: Function(<built-in function array>)
During: typing of call at /home/rajat/Desktop/Radspot/Lidar-object-detection/SA-SSD/mmdet/core/bbox3d/geometry.py (93)

File "mmdet/core/bbox3d/geometry.py", line 93:
def corner_to_surfaces_3d(corners):
    <source elided>
        [corners[:, 0], corners[:, 4], corners[:, 5], corners[:, 1]],
        [corners[:, 3], corners[:, 2], corners[:, 6], corners[:, 7]],
        ^

  @numba.jit(nopython=False)
2020-09-29 16:35:52,233 - INFO - finding looplift candidates
/home/rajat/Desktop/Radspot/Lidar-object-detection/SA-SSD/mmdet/core/bbox3d/geometry.py:76: NumbaWarning: 
Compilation is falling back to object mode WITH looplifting enabled because Function "corner_to_surfaces_3d" failed type inference due to: No implementation of function Function(<built-in function array>) found for signature:

 >>> array(list(list(array(float32, 2d, A))<iv=None>)<iv=None>)

There are 2 candidate implementations:
  - Of which 2 did not match due to:
  Overload in function 'array': File: numba/core/typing/npydecl.py: Line 482.
    With argument(s): '(list(list(array(float32, 2d, A))<iv=None>)<iv=None>)':
   Rejected as the implementation raised a specific error:
     TypingError: array(float32, 2d, A) not allowed in a homogeneous sequence
  raised from /home/rajat/Desktop/Radspot/Lidar-object-detection/SA-SSD/venv/lib/python3.6/site-packages/numba/core/typing/npydecl.py:449

During: resolving callee type: Function(<built-in function array>)
During: typing of call at /home/rajat/Desktop/Radspot/Lidar-object-detection/SA-SSD/mmdet/core/bbox3d/geometry.py (93)

File "mmdet/core/bbox3d/geometry.py", line 93:
def corner_to_surfaces_3d(corners):
    <source elided>
        [corners[:, 0], corners[:, 4], corners[:, 5], corners[:, 1]],
        [corners[:, 3], corners[:, 2], corners[:, 6], corners[:, 7]],
        ^

  @numba.jit(nopython=False)
2020-09-29 16:35:52,427 - INFO - finding looplift candidates
/home/rajat/Desktop/Radspot/Lidar-object-detection/SA-SSD/venv/lib/python3.6/site-packages/numba/core/object_mode_passes.py:178: NumbaWarning: Function "corner_to_surfaces_3d" was compiled in object mode without forceobj=True.

File "mmdet/core/bbox3d/geometry.py", line 77:
@numba.jit(nopython=False)
def corner_to_surfaces_3d(corners):
^

  state.func_ir.loc))
/home/rajat/Desktop/Radspot/Lidar-object-detection/SA-SSD/venv/lib/python3.6/site-packages/numba/core/object_mode_passes.py:188: NumbaDeprecationWarning: 
Fall-back from the nopython compilation path to the object mode compilation path has been detected, this is deprecated behaviour.

For more information visit https://numba.pydata.org/numba-doc/latest/reference/deprecation.html#deprecation-of-object-mode-fall-back-behaviour-when-using-jit

File "mmdet/core/bbox3d/geometry.py", line 77:
@numba.jit(nopython=False)
def corner_to_surfaces_3d(corners):
^

  state.func_ir.loc))
/home/rajat/Desktop/Radspot/Lidar-object-detection/SA-SSD/venv/lib/python3.6/site-packages/numba/core/object_mode_passes.py:178: NumbaWarning: Function "corner_to_surfaces_3d" was compiled in object mode without forceobj=True.

File "mmdet/core/bbox3d/geometry.py", line 77:
@numba.jit(nopython=False)
def corner_to_surfaces_3d(corners):
^

  state.func_ir.loc))
/home/rajat/Desktop/Radspot/Lidar-object-detection/SA-SSD/venv/lib/python3.6/site-packages/numba/core/object_mode_passes.py:188: NumbaDeprecationWarning: 
Fall-back from the nopython compilation path to the object mode compilation path has been detected, this is deprecated behaviour.

For more information visit https://numba.pydata.org/numba-doc/latest/reference/deprecation.html#deprecation-of-object-mode-fall-back-behaviour-when-using-jit

File "mmdet/core/bbox3d/geometry.py", line 77:
@numba.jit(nopython=False)
def corner_to_surfaces_3d(corners):
^

  state.func_ir.loc))
/home/rajat/Desktop/Radspot/Lidar-object-detection/SA-SSD/venv/lib/python3.6/site-packages/numba/core/object_mode_passes.py:178: NumbaWarning: Function "corner_to_surfaces_3d" was compiled in object mode without forceobj=True.

File "mmdet/core/bbox3d/geometry.py", line 77:
@numba.jit(nopython=False)
def corner_to_surfaces_3d(corners):
^

  state.func_ir.loc))
/home/rajat/Desktop/Radspot/Lidar-object-detection/SA-SSD/venv/lib/python3.6/site-packages/numba/core/object_mode_passes.py:188: NumbaDeprecationWarning: 
Fall-back from the nopython compilation path to the object mode compilation path has been detected, this is deprecated behaviour.

For more information visit https://numba.pydata.org/numba-doc/latest/reference/deprecation.html#deprecation-of-object-mode-fall-back-behaviour-when-using-jit

File "mmdet/core/bbox3d/geometry.py", line 77:
@numba.jit(nopython=False)
def corner_to_surfaces_3d(corners):
^

  state.func_ir.loc))
/home/rajat/Desktop/Radspot/Lidar-object-detection/SA-SSD/venv/lib/python3.6/site-packages/numba/core/object_mode_passes.py:178: NumbaWarning: Function "corner_to_surfaces_3d" was compiled in object mode without forceobj=True.

File "mmdet/core/bbox3d/geometry.py", line 77:
@numba.jit(nopython=False)
def corner_to_surfaces_3d(corners):
^

  state.func_ir.loc))
/home/rajat/Desktop/Radspot/Lidar-object-detection/SA-SSD/venv/lib/python3.6/site-packages/numba/core/object_mode_passes.py:188: NumbaDeprecationWarning: 
Fall-back from the nopython compilation path to the object mode compilation path has been detected, this is deprecated behaviour.

For more information visit https://numba.pydata.org/numba-doc/latest/reference/deprecation.html#deprecation-of-object-mode-fall-back-behaviour-when-using-jit

File "mmdet/core/bbox3d/geometry.py", line 77:
@numba.jit(nopython=False)
def corner_to_surfaces_3d(corners):
^

  state.func_ir.loc))
2020-09-29 16:35:57,678 - INFO - finding looplift candidates
2020-09-29 16:35:57,885 - INFO - finding looplift candidates
2020-09-29 16:35:57,996 - INFO - finding looplift candidates
2020-09-29 16:35:58,443 - INFO - finding looplift candidates
/home/rajat/Desktop/Radspot/Lidar-object-detection/SA-SSD/mmdet/core/bbox3d/geometry.py:189: NumbaWarning: 
Compilation is falling back to object mode WITH looplifting enabled because Function "points_in_convex_polygon_3d_jit" failed type inference due to: Invalid use of type(CPUDispatcher(<function surface_equ_3d_jit at 0x7fc6e88a7158>)) with parameters (array(float32, 4d, A))

During: resolving callee type: type(CPUDispatcher(<function surface_equ_3d_jit at 0x7fc6e88a7158>))
During: typing of call at /home/rajat/Desktop/Radspot/Lidar-object-detection/SA-SSD/mmdet/core/bbox3d/geometry.py (210)

File "mmdet/core/bbox3d/geometry.py", line 210:
def points_in_convex_polygon_3d_jit(points,
    <source elided>
        num_surfaces = np.full((num_polygons,), 9999999, dtype=np.int64)
    normal_vec, d = surface_equ_3d_jit(polygon_surfaces[:, :, :3, :])
    ^

  @numba.jit(nopython=False)
2020-09-29 16:35:58,572 - INFO - finding looplift candidates
/home/rajat/Desktop/Radspot/Lidar-object-detection/SA-SSD/mmdet/core/bbox3d/geometry.py:189: NumbaWarning: 
Compilation is falling back to object mode WITHOUT looplifting enabled because Function "points_in_convex_polygon_3d_jit" failed type inference due to: cannot determine Numba type of <class 'numba.core.dispatcher.LiftedLoop'>

File "mmdet/core/bbox3d/geometry.py", line 215:
def points_in_convex_polygon_3d_jit(points,
    <source elided>
    sign = 0.0
    for i in range(num_points):
    ^

  @numba.jit(nopython=False)
/home/rajat/Desktop/Radspot/Lidar-object-detection/SA-SSD/mmdet/core/bbox3d/geometry.py:189: NumbaWarning: 
Compilation is falling back to object mode WITH looplifting enabled because Function "points_in_convex_polygon_3d_jit" failed type inference due to: Invalid use of type(CPUDispatcher(<function surface_equ_3d_jit at 0x7fc6e88a7158>)) with parameters (array(float32, 4d, A))

During: resolving callee type: type(CPUDispatcher(<function surface_equ_3d_jit at 0x7fc6e88a7158>))
During: typing of call at /home/rajat/Desktop/Radspot/Lidar-object-detection/SA-SSD/mmdet/core/bbox3d/geometry.py (210)

File "mmdet/core/bbox3d/geometry.py", line 210:
def points_in_convex_polygon_3d_jit(points,
    <source elided>
        num_surfaces = np.full((num_polygons,), 9999999, dtype=np.int64)
    normal_vec, d = surface_equ_3d_jit(polygon_surfaces[:, :, :3, :])
    ^

  @numba.jit(nopython=False)
2020-09-29 16:35:58,797 - INFO - finding looplift candidates
/home/rajat/Desktop/Radspot/Lidar-object-detection/SA-SSD/mmdet/core/bbox3d/geometry.py:189: NumbaWarning: 
Compilation is falling back to object mode WITHOUT looplifting enabled because Function "points_in_convex_polygon_3d_jit" failed type inference due to: cannot determine Numba type of <class 'numba.core.dispatcher.LiftedLoop'>

File "mmdet/core/bbox3d/geometry.py", line 215:
def points_in_convex_polygon_3d_jit(points,
    <source elided>
    sign = 0.0
    for i in range(num_points):
    ^

  @numba.jit(nopython=False)
/home/rajat/Desktop/Radspot/Lidar-object-detection/SA-SSD/mmdet/core/bbox3d/geometry.py:189: NumbaWarning: 
Compilation is falling back to object mode WITH looplifting enabled because Function "points_in_convex_polygon_3d_jit" failed type inference due to: Invalid use of type(CPUDispatcher(<function surface_equ_3d_jit at 0x7fc6e88a7158>)) with parameters (array(float32, 4d, A))

During: resolving callee type: type(CPUDispatcher(<function surface_equ_3d_jit at 0x7fc6e88a7158>))
During: typing of call at /home/rajat/Desktop/Radspot/Lidar-object-detection/SA-SSD/mmdet/core/bbox3d/geometry.py (210)

File "mmdet/core/bbox3d/geometry.py", line 210:
def points_in_convex_polygon_3d_jit(points,
    <source elided>
        num_surfaces = np.full((num_polygons,), 9999999, dtype=np.int64)
    normal_vec, d = surface_equ_3d_jit(polygon_surfaces[:, :, :3, :])
    ^

  @numba.jit(nopython=False)
2020-09-29 16:35:59,075 - INFO - finding looplift candidates
/home/rajat/Desktop/Radspot/Lidar-object-detection/SA-SSD/mmdet/core/bbox3d/geometry.py:189: NumbaWarning: 
Compilation is falling back to object mode WITHOUT looplifting enabled because Function "points_in_convex_polygon_3d_jit" failed type inference due to: cannot determine Numba type of <class 'numba.core.dispatcher.LiftedLoop'>

File "mmdet/core/bbox3d/geometry.py", line 215:
def points_in_convex_polygon_3d_jit(points,
    <source elided>
    sign = 0.0
    for i in range(num_points):
    ^

  @numba.jit(nopython=False)
/home/rajat/Desktop/Radspot/Lidar-object-detection/SA-SSD/venv/lib/python3.6/site-packages/numba/core/object_mode_passes.py:178: NumbaWarning: Function "points_in_convex_polygon_3d_jit" was compiled in object mode without forceobj=True, but has lifted loops.

File "mmdet/core/bbox3d/geometry.py", line 205:
def points_in_convex_polygon_3d_jit(points,
    <source elided>
    """
    max_num_surfaces, max_num_points_of_surface = polygon_surfaces.shape[1:3]
    ^

  state.func_ir.loc))
/home/rajat/Desktop/Radspot/Lidar-object-detection/SA-SSD/venv/lib/python3.6/site-packages/numba/core/object_mode_passes.py:188: NumbaDeprecationWarning: 
Fall-back from the nopython compilation path to the object mode compilation path has been detected, this is deprecated behaviour.

For more information visit https://numba.pydata.org/numba-doc/latest/reference/deprecation.html#deprecation-of-object-mode-fall-back-behaviour-when-using-jit

File "mmdet/core/bbox3d/geometry.py", line 205:
def points_in_convex_polygon_3d_jit(points,
    <source elided>
    """
    max_num_surfaces, max_num_points_of_surface = polygon_surfaces.shape[1:3]
    ^

  state.func_ir.loc))
/home/rajat/Desktop/Radspot/Lidar-object-detection/SA-SSD/venv/lib/python3.6/site-packages/numba/core/object_mode_passes.py:178: NumbaWarning: Function "points_in_convex_polygon_3d_jit" was compiled in object mode without forceobj=True, but has lifted loops.

File "mmdet/core/bbox3d/geometry.py", line 205:
def points_in_convex_polygon_3d_jit(points,
    <source elided>
    """
    max_num_surfaces, max_num_points_of_surface = polygon_surfaces.shape[1:3]
    ^

  state.func_ir.loc))
/home/rajat/Desktop/Radspot/Lidar-object-detection/SA-SSD/venv/lib/python3.6/site-packages/numba/core/object_mode_passes.py:188: NumbaDeprecationWarning: 
Fall-back from the nopython compilation path to the object mode compilation path has been detected, this is deprecated behaviour.

For more information visit https://numba.pydata.org/numba-doc/latest/reference/deprecation.html#deprecation-of-object-mode-fall-back-behaviour-when-using-jit

File "mmdet/core/bbox3d/geometry.py", line 205:
def points_in_convex_polygon_3d_jit(points,
    <source elided>
    """
    max_num_surfaces, max_num_points_of_surface = polygon_surfaces.shape[1:3]
    ^

  state.func_ir.loc))
/home/rajat/Desktop/Radspot/Lidar-object-detection/SA-SSD/mmdet/core/bbox3d/geometry.py:189: NumbaWarning: 
Compilation is falling back to object mode WITH looplifting enabled because Function "points_in_convex_polygon_3d_jit" failed type inference due to: Invalid use of type(CPUDispatcher(<function surface_equ_3d_jit at 0x7fc6e88a7158>)) with parameters (array(float32, 4d, A))

During: resolving callee type: type(CPUDispatcher(<function surface_equ_3d_jit at 0x7fc6e88a7158>))
During: typing of call at /home/rajat/Desktop/Radspot/Lidar-object-detection/SA-SSD/mmdet/core/bbox3d/geometry.py (210)

File "mmdet/core/bbox3d/geometry.py", line 210:
def points_in_convex_polygon_3d_jit(points,
    <source elided>
        num_surfaces = np.full((num_polygons,), 9999999, dtype=np.int64)
    normal_vec, d = surface_equ_3d_jit(polygon_surfaces[:, :, :3, :])
    ^

  @numba.jit(nopython=False)
2020-09-29 16:35:59,360 - INFO - finding looplift candidates
/home/rajat/Desktop/Radspot/Lidar-object-detection/SA-SSD/mmdet/core/bbox3d/geometry.py:189: NumbaWarning: 
Compilation is falling back to object mode WITHOUT looplifting enabled because Function "points_in_convex_polygon_3d_jit" failed type inference due to: cannot determine Numba type of <class 'numba.core.dispatcher.LiftedLoop'>

File "mmdet/core/bbox3d/geometry.py", line 215:
def points_in_convex_polygon_3d_jit(points,
    <source elided>
    sign = 0.0
    for i in range(num_points):
    ^

  @numba.jit(nopython=False)
/home/rajat/Desktop/Radspot/Lidar-object-detection/SA-SSD/venv/lib/python3.6/site-packages/numba/core/object_mode_passes.py:178: NumbaWarning: Function "points_in_convex_polygon_3d_jit" was compiled in object mode without forceobj=True, but has lifted loops.

File "mmdet/core/bbox3d/geometry.py", line 205:
def points_in_convex_polygon_3d_jit(points,
    <source elided>
    """
    max_num_surfaces, max_num_points_of_surface = polygon_surfaces.shape[1:3]
    ^

  state.func_ir.loc))
/home/rajat/Desktop/Radspot/Lidar-object-detection/SA-SSD/venv/lib/python3.6/site-packages/numba/core/object_mode_passes.py:188: NumbaDeprecationWarning: 
Fall-back from the nopython compilation path to the object mode compilation path has been detected, this is deprecated behaviour.

For more information visit https://numba.pydata.org/numba-doc/latest/reference/deprecation.html#deprecation-of-object-mode-fall-back-behaviour-when-using-jit

File "mmdet/core/bbox3d/geometry.py", line 205:
def points_in_convex_polygon_3d_jit(points,
    <source elided>
    """
    max_num_surfaces, max_num_points_of_surface = polygon_surfaces.shape[1:3]
    ^

  state.func_ir.loc))
/home/rajat/Desktop/Radspot/Lidar-object-detection/SA-SSD/venv/lib/python3.6/site-packages/numba/core/object_mode_passes.py:178: NumbaWarning: Function "points_in_convex_polygon_3d_jit" was compiled in object mode without forceobj=True, but has lifted loops.

File "mmdet/core/bbox3d/geometry.py", line 205:
def points_in_convex_polygon_3d_jit(points,
    <source elided>
    """
    max_num_surfaces, max_num_points_of_surface = polygon_surfaces.shape[1:3]
    ^

  state.func_ir.loc))
/home/rajat/Desktop/Radspot/Lidar-object-detection/SA-SSD/venv/lib/python3.6/site-packages/numba/core/object_mode_passes.py:188: NumbaDeprecationWarning: 
Fall-back from the nopython compilation path to the object mode compilation path has been detected, this is deprecated behaviour.

For more information visit https://numba.pydata.org/numba-doc/latest/reference/deprecation.html#deprecation-of-object-mode-fall-back-behaviour-when-using-jit

File "mmdet/core/bbox3d/geometry.py", line 205:
def points_in_convex_polygon_3d_jit(points,
    <source elided>
    """
    max_num_surfaces, max_num_points_of_surface = polygon_surfaces.shape[1:3]
    ^

  state.func_ir.loc))
/home/rajat/Desktop/Radspot/Lidar-object-detection/SA-SSD/mmdet/core/bbox3d/geometry.py:189: NumbaWarning: 
Compilation is falling back to object mode WITH looplifting enabled because Function "points_in_convex_polygon_3d_jit" failed type inference due to: Invalid use of type(CPUDispatcher(<function surface_equ_3d_jit at 0x7fc6e88a7158>)) with parameters (array(float32, 4d, A))

During: resolving callee type: type(CPUDispatcher(<function surface_equ_3d_jit at 0x7fc6e88a7158>))
During: typing of call at /home/rajat/Desktop/Radspot/Lidar-object-detection/SA-SSD/mmdet/core/bbox3d/geometry.py (210)

File "mmdet/core/bbox3d/geometry.py", line 210:
def points_in_convex_polygon_3d_jit(points,
    <source elided>
        num_surfaces = np.full((num_polygons,), 9999999, dtype=np.int64)
    normal_vec, d = surface_equ_3d_jit(polygon_surfaces[:, :, :3, :])
    ^

  @numba.jit(nopython=False)
2020-09-29 16:36:08,609 - INFO - finding looplift candidates
/home/rajat/Desktop/Radspot/Lidar-object-detection/SA-SSD/mmdet/core/bbox3d/geometry.py:189: NumbaWarning: 
Compilation is falling back to object mode WITHOUT looplifting enabled because Function "points_in_convex_polygon_3d_jit" failed type inference due to: cannot determine Numba type of <class 'numba.core.dispatcher.LiftedLoop'>

File "mmdet/core/bbox3d/geometry.py", line 215:
def points_in_convex_polygon_3d_jit(points,
    <source elided>
    sign = 0.0
    for i in range(num_points):
    ^

  @numba.jit(nopython=False)
/home/rajat/Desktop/Radspot/Lidar-object-detection/SA-SSD/mmdet/core/bbox3d/geometry.py:189: NumbaWarning: 
Compilation is falling back to object mode WITH looplifting enabled because Function "points_in_convex_polygon_3d_jit" failed type inference due to: Invalid use of type(CPUDispatcher(<function surface_equ_3d_jit at 0x7fc6e88a7158>)) with parameters (array(float32, 4d, A))

During: resolving callee type: type(CPUDispatcher(<function surface_equ_3d_jit at 0x7fc6e88a7158>))
During: typing of call at /home/rajat/Desktop/Radspot/Lidar-object-detection/SA-SSD/mmdet/core/bbox3d/geometry.py (210)

File "mmdet/core/bbox3d/geometry.py", line 210:
def points_in_convex_polygon_3d_jit(points,
    <source elided>
        num_surfaces = np.full((num_polygons,), 9999999, dtype=np.int64)
    normal_vec, d = surface_equ_3d_jit(polygon_surfaces[:, :, :3, :])
    ^

  @numba.jit(nopython=False)
2020-09-29 16:36:08,989 - INFO - finding looplift candidates
/home/rajat/Desktop/Radspot/Lidar-object-detection/SA-SSD/mmdet/core/bbox3d/geometry.py:189: NumbaWarning: 
Compilation is falling back to object mode WITHOUT looplifting enabled because Function "points_in_convex_polygon_3d_jit" failed type inference due to: cannot determine Numba type of <class 'numba.core.dispatcher.LiftedLoop'>

File "mmdet/core/bbox3d/geometry.py", line 215:
def points_in_convex_polygon_3d_jit(points,
    <source elided>
    sign = 0.0
    for i in range(num_points):
    ^

  @numba.jit(nopython=False)
/home/rajat/Desktop/Radspot/Lidar-object-detection/SA-SSD/mmdet/core/bbox3d/geometry.py:189: NumbaWarning: 
Compilation is falling back to object mode WITH looplifting enabled because Function "points_in_convex_polygon_3d_jit" failed type inference due to: Invalid use of type(CPUDispatcher(<function surface_equ_3d_jit at 0x7fc6e88a7158>)) with parameters (array(float32, 4d, A))

During: resolving callee type: type(CPUDispatcher(<function surface_equ_3d_jit at 0x7fc6e88a7158>))
During: typing of call at /home/rajat/Desktop/Radspot/Lidar-object-detection/SA-SSD/mmdet/core/bbox3d/geometry.py (210)

File "mmdet/core/bbox3d/geometry.py", line 210:
def points_in_convex_polygon_3d_jit(points,
    <source elided>
        num_surfaces = np.full((num_polygons,), 9999999, dtype=np.int64)
    normal_vec, d = surface_equ_3d_jit(polygon_surfaces[:, :, :3, :])
    ^

  @numba.jit(nopython=False)
/home/rajat/Desktop/Radspot/Lidar-object-detection/SA-SSD/venv/lib/python3.6/site-packages/numba/core/object_mode_passes.py:178: NumbaWarning: Function "points_in_convex_polygon_3d_jit" was compiled in object mode without forceobj=True, but has lifted loops.

File "mmdet/core/bbox3d/geometry.py", line 205:
def points_in_convex_polygon_3d_jit(points,
    <source elided>
    """
    max_num_surfaces, max_num_points_of_surface = polygon_surfaces.shape[1:3]
    ^

  state.func_ir.loc))
/home/rajat/Desktop/Radspot/Lidar-object-detection/SA-SSD/venv/lib/python3.6/site-packages/numba/core/object_mode_passes.py:188: NumbaDeprecationWarning: 
Fall-back from the nopython compilation path to the object mode compilation path has been detected, this is deprecated behaviour.

For more information visit https://numba.pydata.org/numba-doc/latest/reference/deprecation.html#deprecation-of-object-mode-fall-back-behaviour-when-using-jit

File "mmdet/core/bbox3d/geometry.py", line 205:
def points_in_convex_polygon_3d_jit(points,
    <source elided>
    """
    max_num_surfaces, max_num_points_of_surface = polygon_surfaces.shape[1:3]
    ^

  state.func_ir.loc))
2020-09-29 16:36:09,288 - INFO - finding looplift candidates
/home/rajat/Desktop/Radspot/Lidar-object-detection/SA-SSD/mmdet/core/bbox3d/geometry.py:189: NumbaWarning: 
Compilation is falling back to object mode WITHOUT looplifting enabled because Function "points_in_convex_polygon_3d_jit" failed type inference due to: cannot determine Numba type of <class 'numba.core.dispatcher.LiftedLoop'>

File "mmdet/core/bbox3d/geometry.py", line 215:
def points_in_convex_polygon_3d_jit(points,
    <source elided>
    sign = 0.0
    for i in range(num_points):
    ^

  @numba.jit(nopython=False)
/home/rajat/Desktop/Radspot/Lidar-object-detection/SA-SSD/venv/lib/python3.6/site-packages/numba/core/object_mode_passes.py:178: NumbaWarning: Function "points_in_convex_polygon_3d_jit" was compiled in object mode without forceobj=True, but has lifted loops.

File "mmdet/core/bbox3d/geometry.py", line 205:
def points_in_convex_polygon_3d_jit(points,
    <source elided>
    """
    max_num_surfaces, max_num_points_of_surface = polygon_surfaces.shape[1:3]
    ^

  state.func_ir.loc))
/home/rajat/Desktop/Radspot/Lidar-object-detection/SA-SSD/venv/lib/python3.6/site-packages/numba/core/object_mode_passes.py:188: NumbaDeprecationWarning: 
Fall-back from the nopython compilation path to the object mode compilation path has been detected, this is deprecated behaviour.

For more information visit https://numba.pydata.org/numba-doc/latest/reference/deprecation.html#deprecation-of-object-mode-fall-back-behaviour-when-using-jit

File "mmdet/core/bbox3d/geometry.py", line 205:
def points_in_convex_polygon_3d_jit(points,
    <source elided>
    """
    max_num_surfaces, max_num_points_of_surface = polygon_surfaces.shape[1:3]
    ^

  state.func_ir.loc))
/home/rajat/Desktop/Radspot/Lidar-object-detection/SA-SSD/venv/lib/python3.6/site-packages/numba/core/object_mode_passes.py:178: NumbaWarning: Function "points_in_convex_polygon_3d_jit" was compiled in object mode without forceobj=True, but has lifted loops.

File "mmdet/core/bbox3d/geometry.py", line 205:
def points_in_convex_polygon_3d_jit(points,
    <source elided>
    """
    max_num_surfaces, max_num_points_of_surface = polygon_surfaces.shape[1:3]
    ^

  state.func_ir.loc))
/home/rajat/Desktop/Radspot/Lidar-object-detection/SA-SSD/venv/lib/python3.6/site-packages/numba/core/object_mode_passes.py:188: NumbaDeprecationWarning: 
Fall-back from the nopython compilation path to the object mode compilation path has been detected, this is deprecated behaviour.

For more information visit https://numba.pydata.org/numba-doc/latest/reference/deprecation.html#deprecation-of-object-mode-fall-back-behaviour-when-using-jit

File "mmdet/core/bbox3d/geometry.py", line 205:
def points_in_convex_polygon_3d_jit(points,
    <source elided>
    """
    max_num_surfaces, max_num_points_of_surface = polygon_surfaces.shape[1:3]
    ^

  state.func_ir.loc))
/home/rajat/Desktop/Radspot/Lidar-object-detection/SA-SSD/mmdet/core/bbox3d/geometry.py:189: NumbaWarning: 
Compilation is falling back to object mode WITH looplifting enabled because Function "points_in_convex_polygon_3d_jit" failed type inference due to: Invalid use of type(CPUDispatcher(<function surface_equ_3d_jit at 0x7fc6e88a7158>)) with parameters (array(float32, 4d, A))

During: resolving callee type: type(CPUDispatcher(<function surface_equ_3d_jit at 0x7fc6e88a7158>))
During: typing of call at /home/rajat/Desktop/Radspot/Lidar-object-detection/SA-SSD/mmdet/core/bbox3d/geometry.py (210)

File "mmdet/core/bbox3d/geometry.py", line 210:
def points_in_convex_polygon_3d_jit(points,
    <source elided>
        num_surfaces = np.full((num_polygons,), 9999999, dtype=np.int64)
    normal_vec, d = surface_equ_3d_jit(polygon_surfaces[:, :, :3, :])
    ^

  @numba.jit(nopython=False)
2020-09-29 16:36:10,435 - INFO - finding looplift candidates
/home/rajat/Desktop/Radspot/Lidar-object-detection/SA-SSD/mmdet/core/bbox3d/geometry.py:189: NumbaWarning: 
Compilation is falling back to object mode WITHOUT looplifting enabled because Function "points_in_convex_polygon_3d_jit" failed type inference due to: cannot determine Numba type of <class 'numba.core.dispatcher.LiftedLoop'>

File "mmdet/core/bbox3d/geometry.py", line 215:
def points_in_convex_polygon_3d_jit(points,
    <source elided>
    sign = 0.0
    for i in range(num_points):
    ^

  @numba.jit(nopython=False)
/home/rajat/Desktop/Radspot/Lidar-object-detection/SA-SSD/mmdet/core/point_cloud/point_augmentor.py:58: NumbaPerformanceWarning: '@' is faster on contiguous arrays, called on (array(float32, 2d, A), array(float32, 2d, C))
  points[i:i + 1, :3] = points[i:i + 1, :3] @ rot_mat_T[j]
/home/rajat/Desktop/Radspot/Lidar-object-detection/SA-SSD/venv/lib/python3.6/site-packages/numba/core/typing/npydecl.py:930: NumbaPerformanceWarning: '@' is faster on contiguous arrays, called on (array(float32, 2d, A), array(float32, 2d, C))
  warnings.warn(NumbaPerformanceWarning(msg))
/home/rajat/Desktop/Radspot/Lidar-object-detection/SA-SSD/mmdet/core/point_cloud/point_augmentor.py:58: NumbaPerformanceWarning: '@' is faster on contiguous arrays, called on (array(float32, 2d, A), array(float32, 2d, C))
  points[i:i + 1, :3] = points[i:i + 1, :3] @ rot_mat_T[j]
/home/rajat/Desktop/Radspot/Lidar-object-detection/SA-SSD/venv/lib/python3.6/site-packages/numba/core/typing/npydecl.py:930: NumbaPerformanceWarning: '@' is faster on contiguous arrays, called on (array(float32, 2d, A), array(float32, 2d, C))
  warnings.warn(NumbaPerformanceWarning(msg))
/home/rajat/Desktop/Radspot/Lidar-object-detection/SA-SSD/mmdet/core/point_cloud/point_augmentor.py:58: NumbaPerformanceWarning: '@' is faster on contiguous arrays, called on (array(float32, 2d, A), array(float32, 2d, C))
  points[i:i + 1, :3] = points[i:i + 1, :3] @ rot_mat_T[j]
/home/rajat/Desktop/Radspot/Lidar-object-detection/SA-SSD/venv/lib/python3.6/site-packages/numba/core/typing/npydecl.py:930: NumbaPerformanceWarning: '@' is faster on contiguous arrays, called on (array(float32, 2d, A), array(float32, 2d, C))
  warnings.warn(NumbaPerformanceWarning(msg))
/home/rajat/Desktop/Radspot/Lidar-object-detection/SA-SSD/venv/lib/python3.6/site-packages/numba/core/object_mode_passes.py:178: NumbaWarning: Function "points_in_convex_polygon_3d_jit" was compiled in object mode without forceobj=True, but has lifted loops.

File "mmdet/core/bbox3d/geometry.py", line 205:
def points_in_convex_polygon_3d_jit(points,
    <source elided>
    """
    max_num_surfaces, max_num_points_of_surface = polygon_surfaces.shape[1:3]
    ^

  state.func_ir.loc))
/home/rajat/Desktop/Radspot/Lidar-object-detection/SA-SSD/venv/lib/python3.6/site-packages/numba/core/object_mode_passes.py:188: NumbaDeprecationWarning: 
Fall-back from the nopython compilation path to the object mode compilation path has been detected, this is deprecated behaviour.

For more information visit https://numba.pydata.org/numba-doc/latest/reference/deprecation.html#deprecation-of-object-mode-fall-back-behaviour-when-using-jit

File "mmdet/core/bbox3d/geometry.py", line 205:
def points_in_convex_polygon_3d_jit(points,
    <source elided>
    """
    max_num_surfaces, max_num_points_of_surface = polygon_surfaces.shape[1:3]
    ^

  state.func_ir.loc))
/home/rajat/Desktop/Radspot/Lidar-object-detection/SA-SSD/mmdet/core/point_cloud/point_augmentor.py:58: NumbaPerformanceWarning: '@' is faster on contiguous arrays, called on (array(float32, 2d, A), array(float32, 2d, C))
  points[i:i + 1, :3] = points[i:i + 1, :3] @ rot_mat_T[j]
/home/rajat/Desktop/Radspot/Lidar-object-detection/SA-SSD/venv/lib/python3.6/site-packages/numba/core/typing/npydecl.py:930: NumbaPerformanceWarning: '@' is faster on contiguous arrays, called on (array(float32, 2d, A), array(float32, 2d, C))
  warnings.warn(NumbaPerformanceWarning(msg))
/home/rajat/Desktop/Radspot/Lidar-object-detection/SA-SSD/mmdet/core/bbox3d/geometry.py:229: NumbaWarning: 
Compilation is falling back to object mode WITH looplifting enabled because Function "points_in_convex_polygon_jit" failed type inference due to: No implementation of function Function(<built-in function getitem>) found for signature:

 >>> getitem(array(float32, 3d, C), Tuple(slice<a:b>, list(int64)<iv=None>, slice<a:b>))

There are 22 candidate implementations:
   - Of which 20 did not match due to:
   Overload of function 'getitem': File: <numerous>: Line N/A.
     With argument(s): '(array(float32, 3d, C), Tuple(slice<a:b>, list(int64)<iv=None>, slice<a:b>))':
    No match.
   - Of which 2 did not match due to:
   Overload in function 'GetItemBuffer.generic': File: numba/core/typing/arraydecl.py: Line 162.
     With argument(s): '(array(float32, 3d, C), Tuple(slice<a:b>, list(int64)<iv=None>, slice<a:b>))':
    Rejected as the implementation raised a specific error:
      TypeError: unsupported array index type list(int64)<iv=None> in Tuple(slice<a:b>, list(int64)<iv=None>, slice<a:b>)
  raised from /home/rajat/Desktop/Radspot/Lidar-object-detection/SA-SSD/venv/lib/python3.6/site-packages/numba/core/typing/arraydecl.py:69

During: typing of intrinsic-call at /home/rajat/Desktop/Radspot/Lidar-object-detection/SA-SSD/mmdet/core/bbox3d/geometry.py (245)

File "mmdet/core/bbox3d/geometry.py", line 245:
def points_in_convex_polygon_jit(points, polygon, clockwise=True):
    <source elided>
        vec1 = polygon - polygon[:, [num_points_of_polygon - 1] +
                                    list(range(num_points_of_polygon - 1)), :]
                                    ^

  @numba.jit
2020-09-29 16:36:14,107 - INFO - finding looplift candidates
/home/rajat/Desktop/Radspot/Lidar-object-detection/SA-SSD/mmdet/core/bbox3d/geometry.py:229: NumbaWarning: 
Compilation is falling back to object mode WITHOUT looplifting enabled because Function "points_in_convex_polygon_jit" failed type inference due to: cannot determine Numba type of <class 'numba.core.dispatcher.LiftedLoop'>

File "mmdet/core/bbox3d/geometry.py", line 253:
def points_in_convex_polygon_jit(points, polygon, clockwise=True):
    <source elided>
    cross = 0.0
    for i in range(num_points):
    ^

  @numba.jit
/home/rajat/Desktop/Radspot/Lidar-object-detection/SA-SSD/mmdet/core/bbox3d/geometry.py:229: NumbaWarning: 
Compilation is falling back to object mode WITH looplifting enabled because Function "points_in_convex_polygon_jit" failed type inference due to: No implementation of function Function(<built-in function getitem>) found for signature:

 >>> getitem(array(float32, 3d, C), Tuple(slice<a:b>, list(int64)<iv=None>, slice<a:b>))

There are 22 candidate implementations:
   - Of which 20 did not match due to:
   Overload of function 'getitem': File: <numerous>: Line N/A.
     With argument(s): '(array(float32, 3d, C), Tuple(slice<a:b>, list(int64)<iv=None>, slice<a:b>))':
    No match.
   - Of which 2 did not match due to:
   Overload in function 'GetItemBuffer.generic': File: numba/core/typing/arraydecl.py: Line 162.
     With argument(s): '(array(float32, 3d, C), Tuple(slice<a:b>, list(int64)<iv=None>, slice<a:b>))':
    Rejected as the implementation raised a specific error:
      TypeError: unsupported array index type list(int64)<iv=None> in Tuple(slice<a:b>, list(int64)<iv=None>, slice<a:b>)
  raised from /home/rajat/Desktop/Radspot/Lidar-object-detection/SA-SSD/venv/lib/python3.6/site-packages/numba/core/typing/arraydecl.py:69

During: typing of intrinsic-call at /home/rajat/Desktop/Radspot/Lidar-object-detection/SA-SSD/mmdet/core/bbox3d/geometry.py (245)

File "mmdet/core/bbox3d/geometry.py", line 245:
def points_in_convex_polygon_jit(points, polygon, clockwise=True):
    <source elided>
        vec1 = polygon - polygon[:, [num_points_of_polygon - 1] +
                                    list(range(num_points_of_polygon - 1)), :]
                                    ^

  @numba.jit
2020-09-29 16:36:14,582 - INFO - finding looplift candidates
/home/rajat/Desktop/Radspot/Lidar-object-detection/SA-SSD/mmdet/core/bbox3d/geometry.py:229: NumbaWarning: 
Compilation is falling back to object mode WITHOUT looplifting enabled because Function "points_in_convex_polygon_jit" failed type inference due to: cannot determine Numba type of <class 'numba.core.dispatcher.LiftedLoop'>

File "mmdet/core/bbox3d/geometry.py", line 253:
def points_in_convex_polygon_jit(points, polygon, clockwise=True):
    <source elided>
    cross = 0.0
    for i in range(num_points):
    ^

  @numba.jit
/home/rajat/Desktop/Radspot/Lidar-object-detection/SA-SSD/venv/lib/python3.6/site-packages/numba/core/object_mode_passes.py:178: NumbaWarning: Function "points_in_convex_polygon_jit" was compiled in object mode without forceobj=True, but has lifted loops.

File "mmdet/core/bbox3d/geometry.py", line 240:
def points_in_convex_polygon_jit(points, polygon, clockwise=True):
    <source elided>
    # first convert polygon to directed lines
    num_points_of_polygon = polygon.shape[1]
    ^

  state.func_ir.loc))
/home/rajat/Desktop/Radspot/Lidar-object-detection/SA-SSD/venv/lib/python3.6/site-packages/numba/core/object_mode_passes.py:188: NumbaDeprecationWarning: 
Fall-back from the nopython compilation path to the object mode compilation path has been detected, this is deprecated behaviour.

For more information visit https://numba.pydata.org/numba-doc/latest/reference/deprecation.html#deprecation-of-object-mode-fall-back-behaviour-when-using-jit

File "mmdet/core/bbox3d/geometry.py", line 240:
def points_in_convex_polygon_jit(points, polygon, clockwise=True):
    <source elided>
    # first convert polygon to directed lines
    num_points_of_polygon = polygon.shape[1]
    ^

  state.func_ir.loc))
/home/rajat/Desktop/Radspot/Lidar-object-detection/SA-SSD/mmdet/core/bbox3d/geometry.py:229: NumbaWarning: 
Compilation is falling back to object mode WITH looplifting enabled because Function "points_in_convex_polygon_jit" failed type inference due to: No implementation of function Function(<built-in function getitem>) found for signature:

 >>> getitem(array(float32, 3d, C), Tuple(slice<a:b>, list(int64)<iv=None>, slice<a:b>))

There are 22 candidate implementations:
   - Of which 20 did not match due to:
   Overload of function 'getitem': File: <numerous>: Line N/A.
     With argument(s): '(array(float32, 3d, C), Tuple(slice<a:b>, list(int64)<iv=None>, slice<a:b>))':
    No match.
   - Of which 2 did not match due to:
   Overload in function 'GetItemBuffer.generic': File: numba/core/typing/arraydecl.py: Line 162.
     With argument(s): '(array(float32, 3d, C), Tuple(slice<a:b>, list(int64)<iv=None>, slice<a:b>))':
    Rejected as the implementation raised a specific error:
      TypeError: unsupported array index type list(int64)<iv=None> in Tuple(slice<a:b>, list(int64)<iv=None>, slice<a:b>)
  raised from /home/rajat/Desktop/Radspot/Lidar-object-detection/SA-SSD/venv/lib/python3.6/site-packages/numba/core/typing/arraydecl.py:69

During: typing of intrinsic-call at /home/rajat/Desktop/Radspot/Lidar-object-detection/SA-SSD/mmdet/core/bbox3d/geometry.py (245)

File "mmdet/core/bbox3d/geometry.py", line 245:
def points_in_convex_polygon_jit(points, polygon, clockwise=True):
    <source elided>
        vec1 = polygon - polygon[:, [num_points_of_polygon - 1] +
                                    list(range(num_points_of_polygon - 1)), :]
                                    ^

  @numba.jit
2020-09-29 16:36:14,884 - INFO - finding looplift candidates
/home/rajat/Desktop/Radspot/Lidar-object-detection/SA-SSD/mmdet/core/bbox3d/geometry.py:229: NumbaWarning: 
Compilation is falling back to object mode WITHOUT looplifting enabled because Function "points_in_convex_polygon_jit" failed type inference due to: cannot determine Numba type of <class 'numba.core.dispatcher.LiftedLoop'>

File "mmdet/core/bbox3d/geometry.py", line 253:
def points_in_convex_polygon_jit(points, polygon, clockwise=True):
    <source elided>
    cross = 0.0
    for i in range(num_points):
    ^

  @numba.jit
/home/rajat/Desktop/Radspot/Lidar-object-detection/SA-SSD/venv/lib/python3.6/site-packages/numba/core/object_mode_passes.py:178: NumbaWarning: Function "points_in_convex_polygon_jit" was compiled in object mode without forceobj=True, but has lifted loops.

File "mmdet/core/bbox3d/geometry.py", line 240:
def points_in_convex_polygon_jit(points, polygon, clockwise=True):
    <source elided>
    # first convert polygon to directed lines
    num_points_of_polygon = polygon.shape[1]
    ^

  state.func_ir.loc))
/home/rajat/Desktop/Radspot/Lidar-object-detection/SA-SSD/venv/lib/python3.6/site-packages/numba/core/object_mode_passes.py:188: NumbaDeprecationWarning: 
Fall-back from the nopython compilation path to the object mode compilation path has been detected, this is deprecated behaviour.

For more information visit https://numba.pydata.org/numba-doc/latest/reference/deprecation.html#deprecation-of-object-mode-fall-back-behaviour-when-using-jit

File "mmdet/core/bbox3d/geometry.py", line 240:
def points_in_convex_polygon_jit(points, polygon, clockwise=True):
    <source elided>
    # first convert polygon to directed lines
    num_points_of_polygon = polygon.shape[1]
    ^

  state.func_ir.loc))
/home/rajat/Desktop/Radspot/Lidar-object-detection/SA-SSD/venv/lib/python3.6/site-packages/numba/core/object_mode_passes.py:178: NumbaWarning: Function "points_in_convex_polygon_jit" was compiled in object mode without forceobj=True, but has lifted loops.

File "mmdet/core/bbox3d/geometry.py", line 240:
def points_in_convex_polygon_jit(points, polygon, clockwise=True):
    <source elided>
    # first convert polygon to directed lines
    num_points_of_polygon = polygon.shape[1]
    ^

  state.func_ir.loc))
/home/rajat/Desktop/Radspot/Lidar-object-detection/SA-SSD/venv/lib/python3.6/site-packages/numba/core/object_mode_passes.py:188: NumbaDeprecationWarning: 
Fall-back from the nopython compilation path to the object mode compilation path has been detected, this is deprecated behaviour.

For more information visit https://numba.pydata.org/numba-doc/latest/reference/deprecation.html#deprecation-of-object-mode-fall-back-behaviour-when-using-jit

File "mmdet/core/bbox3d/geometry.py", line 240:
def points_in_convex_polygon_jit(points, polygon, clockwise=True):
    <source elided>
    # first convert polygon to directed lines
    num_points_of_polygon = polygon.shape[1]
    ^

  state.func_ir.loc))
/home/rajat/Desktop/Radspot/Lidar-object-detection/SA-SSD/mmdet/core/bbox3d/geometry.py:229: NumbaWarning: 
Compilation is falling back to object mode WITH looplifting enabled because Function "points_in_convex_polygon_jit" failed type inference due to: No implementation of function Function(<built-in function getitem>) found for signature:

 >>> getitem(array(float32, 3d, C), Tuple(slice<a:b>, list(int64)<iv=None>, slice<a:b>))

There are 22 candidate implementations:
   - Of which 20 did not match due to:
   Overload of function 'getitem': File: <numerous>: Line N/A.
     With argument(s): '(array(float32, 3d, C), Tuple(slice<a:b>, list(int64)<iv=None>, slice<a:b>))':
    No match.
   - Of which 2 did not match due to:
   Overload in function 'GetItemBuffer.generic': File: numba/core/typing/arraydecl.py: Line 162.
     With argument(s): '(array(float32, 3d, C), Tuple(slice<a:b>, list(int64)<iv=None>, slice<a:b>))':
    Rejected as the implementation raised a specific error:
      TypeError: unsupported array index type list(int64)<iv=None> in Tuple(slice<a:b>, list(int64)<iv=None>, slice<a:b>)
  raised from /home/rajat/Desktop/Radspot/Lidar-object-detection/SA-SSD/venv/lib/python3.6/site-packages/numba/core/typing/arraydecl.py:69

During: typing of intrinsic-call at /home/rajat/Desktop/Radspot/Lidar-object-detection/SA-SSD/mmdet/core/bbox3d/geometry.py (245)

File "mmdet/core/bbox3d/geometry.py", line 245:
def points_in_convex_polygon_jit(points, polygon, clockwise=True):
    <source elided>
        vec1 = polygon - polygon[:, [num_points_of_polygon - 1] +
                                    list(range(num_points_of_polygon - 1)), :]
                                    ^

  @numba.jit
2020-09-29 16:36:16,606 - INFO - finding looplift candidates
/home/rajat/Desktop/Radspot/Lidar-object-detection/SA-SSD/mmdet/core/bbox3d/geometry.py:229: NumbaWarning: 
Compilation is falling back to object mode WITHOUT looplifting enabled because Function "points_in_convex_polygon_jit" failed type inference due to: cannot determine Numba type of <class 'numba.core.dispatcher.LiftedLoop'>

File "mmdet/core/bbox3d/geometry.py", line 253:
def points_in_convex_polygon_jit(points, polygon, clockwise=True):
    <source elided>
    cross = 0.0
    for i in range(num_points):
    ^

  @numba.jit
/home/rajat/Desktop/Radspot/Lidar-object-detection/SA-SSD/venv/lib/python3.6/site-packages/numba/core/object_mode_passes.py:178: NumbaWarning: Function "points_in_convex_polygon_jit" was compiled in object mode without forceobj=True, but has lifted loops.

File "mmdet/core/bbox3d/geometry.py", line 240:
def points_in_convex_polygon_jit(points, polygon, clockwise=True):
    <source elided>
    # first convert polygon to directed lines
    num_points_of_polygon = polygon.shape[1]
    ^

  state.func_ir.loc))
/home/rajat/Desktop/Radspot/Lidar-object-detection/SA-SSD/venv/lib/python3.6/site-packages/numba/core/object_mode_passes.py:188: NumbaDeprecationWarning: 
Fall-back from the nopython compilation path to the object mode compilation path has been detected, this is deprecated behaviour.

For more information visit https://numba.pydata.org/numba-doc/latest/reference/deprecation.html#deprecation-of-object-mode-fall-back-behaviour-when-using-jit

File "mmdet/core/bbox3d/geometry.py", line 240:
def points_in_convex_polygon_jit(points, polygon, clockwise=True):
    <source elided>
    # first convert polygon to directed lines
    num_points_of_polygon = polygon.shape[1]
    ^

  state.func_ir.loc))
Traceback (most recent call last):
  File "train.py", line 127, in <module>
    main()
  File "train.py", line 117, in main
    log_interval = cfg.log_config.interval
  File "/home/rajat/Desktop/Radspot/Lidar-object-detection/SA-SSD/tools/train_utils/__init__.py", line 99, in train_model
    log_interval = log_interval
  File "/home/rajat/Desktop/Radspot/Lidar-object-detection/SA-SSD/tools/train_utils/__init__.py", line 57, in train_one_epoch
    outputs = batch_processor(model, data_batch)
  File "/home/rajat/Desktop/Radspot/Lidar-object-detection/SA-SSD/tools/train_utils/__init__.py", line 29, in batch_processor
    losses = model(**data)
  File "/home/rajat/Desktop/Radspot/Lidar-object-detection/SA-SSD/venv/lib/python3.6/site-packages/torch/nn/modules/module.py", line 532, in __call__
    result = self.forward(*input, **kwargs)
  File "/home/rajat/Desktop/Radspot/Lidar-object-detection/SA-SSD/venv/lib/python3.6/site-packages/mmcv/parallel/data_parallel.py", line 42, in forward
    return super().forward(*inputs, **kwargs)
  File "/home/rajat/Desktop/Radspot/Lidar-object-detection/SA-SSD/venv/lib/python3.6/site-packages/torch/nn/parallel/data_parallel.py", line 150, in forward
    return self.module(*inputs[0], **kwargs[0])
  File "/home/rajat/Desktop/Radspot/Lidar-object-detection/SA-SSD/venv/lib/python3.6/site-packages/torch/nn/modules/module.py", line 532, in __call__
    result = self.forward(*input, **kwargs)
  File "/home/rajat/Desktop/Radspot/Lidar-object-detection/SA-SSD/mmdet/models/detectors/base.py", line 79, in forward
    return self.forward_train(img, img_meta, **kwargs)
  File "/home/rajat/Desktop/Radspot/Lidar-object-detection/SA-SSD/mmdet/models/detectors/single_stage.py", line 97, in forward_train
    ret['anchors_mask'], ret['gt_bboxes'], ret['gt_labels'], thr=self.train_cfg.rpn.anchor_thr)
  File "/home/rajat/Desktop/Radspot/Lidar-object-detection/SA-SSD/mmdet/models/single_stage_heads/ssd_rotate_head.py", line 367, in get_guided_anchors
    top_labels = torch.cat([gt_lbls, top_labels],0)
RuntimeError: Expected object of backend CUDA but got backend CPU for sequence element 1 in sequence argument at position #1 'tensors'

Any idea why am I getting this error and how to solve it ?

Also, I am getting a lot of warnings related to numba, how to resolve them?

Thanks in advance

Rajat-Mehta commented 4 years ago

The error is in this line, File "/SA-SSD/mmdet/models/single_stage_heads/ssd_rotate_head.py", line 367, in get_guided_anchors:

top_labels = torch.cat([gt_lbls, top_labels],0)

For now I have fixed this issue by adding this line:

top_labels=top_labels.to(gt_lbls.device) // i.e. gpu
top_labels = torch.cat([gt_lbls, top_labels],0)

is there a better solution for this ?

wennieWN commented 4 years ago

The error is in this line, File "/SA-SSD/mmdet/models/single_stage_heads/ssd_rotate_head.py", line 367, in get_guided_anchors:

top_labels = torch.cat([gt_lbls, top_labels],0)

For now I have fixed this issue by adding this line:

top_labels=top_labels.to(gt_lbls.device) // i.e. gpu
top_labels = torch.cat([gt_lbls, top_labels],0)

is there a better solution for this ?

THX! I have met the same problem, and have been solved by your solution!