You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
hallo,
when i use the command
`!python tools/test.py configs/pointpillars/hv_pointpillars_fpn_sbn-all_4x8_2x_nus-3d.py /content/mmdetection3d/checkpoints/hv_pointpillars_secfpn_sbn-all_4x8_2x_nus-3d_20210826_225857-f19d00a3.pth --show-dir /content/mmdetection3d/results```
theres an error:
/content/mmdetection3d/mmdet3d/models/backbones/mink_resnet.py:10: UserWarning: Please follow getting_started.md to install MinkowskiEngine.
'Please follow getting_started.md to install MinkowskiEngine.`')
/usr/local/lib/python3.7/site-packages/mmdet/utils/setup_env.py:39: UserWarning: Setting OMP_NUM_THREADS environment variable for each process to be 1 in default, to avoid your system being overloaded, please further tune the variable for optimal performance in your application as needed.
f'Setting OMP_NUM_THREADS environment variable for each process '
/usr/local/lib/python3.7/site-packages/mmdet/utils/setup_env.py:49: UserWarning: Setting MKL_NUM_THREADS environment variable for each process to be 1 in default, to avoid your system being overloaded, please further tune the variable for optimal performance in your application as needed.
f'Setting MKL_NUM_THREADS environment variable for each process '
/usr/local/lib/python3.7/site-packages/torch/utils/data/dataloader.py:560: UserWarning: This DataLoader will create 4 worker processes in total. Our suggested max number of worker in current system is 2, which is smaller than what this DataLoader is going to create. Please be aware that excessive worker creation might get DataLoader running slow or even freeze, lower the worker number to avoid potential slowness/freeze if necessary.
cpuset_checked))
/content/mmdetection3d/mmdet3d/models/dense_heads/anchor3d_head.py:85: UserWarning: dir_offset and dir_limit_offset will be depressed and be incorporated into box coder in the future
'dir_offset and dir_limit_offset will be depressed and be '
load checkpoint from local path: /content/mmdetection3d/checkpoints/hv_pointpillars_secfpn_sbn-all_4x8_2x_nus-3d_20210826_225857-f19d00a3.pth
The model and loaded state dict do not match exactly
size mismatch for pts_bbox_head.conv_cls.weight: copying a param with shape torch.Size([140, 384, 1, 1]) from checkpoint, the shape in current model is torch.Size([80, 256, 1, 1]).
size mismatch for pts_bbox_head.conv_cls.bias: copying a param with shape torch.Size([140]) from checkpoint, the shape in current model is torch.Size([80]).
size mismatch for pts_bbox_head.conv_reg.weight: copying a param with shape torch.Size([126, 384, 1, 1]) from checkpoint, the shape in current model is torch.Size([72, 256, 1, 1]).
size mismatch for pts_bbox_head.conv_reg.bias: copying a param with shape torch.Size([126]) from checkpoint, the shape in current model is torch.Size([72]).
size mismatch for pts_bbox_head.conv_dir_cls.weight: copying a param with shape torch.Size([28, 384, 1, 1]) from checkpoint, the shape in current model is torch.Size([16, 256, 1, 1]).
size mismatch for pts_bbox_head.conv_dir_cls.bias: copying a param with shape torch.Size([28]) from checkpoint, the shape in current model is torch.Size([16]).
unexpected key in source state_dict: pts_neck.deblocks.0.0.weight, pts_neck.deblocks.0.1.weight, pts_neck.deblocks.0.1.bias, pts_neck.deblocks.0.1.running_mean, pts_neck.deblocks.0.1.running_var, pts_neck.deblocks.0.1.num_batches_tracked, pts_neck.deblocks.1.0.weight, pts_neck.deblocks.1.1.weight, pts_neck.deblocks.1.1.bias, pts_neck.deblocks.1.1.running_mean, pts_neck.deblocks.1.1.running_var, pts_neck.deblocks.1.1.num_batches_tracked, pts_neck.deblocks.2.0.weight, pts_neck.deblocks.2.1.weight, pts_neck.deblocks.2.1.bias, pts_neck.deblocks.2.1.running_mean, pts_neck.deblocks.2.1.running_var, pts_neck.deblocks.2.1.num_batches_tracked
[ ] 0/81, elapsed: 0s, ETA:/usr/local/lib/python3.7/site-packages/torch/functional.py:478: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at /opt/conda/conda-bld/pytorch_1656352464346/work/aten/src/ATen/native/TensorShape.cpp:2894.)
return _VF.meshgrid(tensors, **kwargs) # type: ignore[attr-defined]
[>>] 81/81, 1.3 task/s, elapsed: 62s, ETA: 0s`
And theres nothing in my results folder
Environment
sys.platform: linux
Python: 3.7.10 (default, Jun 4 2021, 14:48:32) [GCC 7.5.0]
CUDA available: True
GPU 0: Tesla P100-PCIE-16GB
CUDA_HOME: /usr/local/cuda
NVCC: Cuda compilation tools, release 11.1, V11.1.105
GCC: gcc (Ubuntu 7.5.0-3ubuntu1~18.04) 7.5.0
PyTorch: 1.12.0
PyTorch compiling details: PyTorch built with:
GCC 9.3
C++ Version: 201402
Intel(R) oneAPI Math Kernel Library Version 2021.4-Product Build 20210904 for Intel(R) 64 architecture applications
hallo,
when i use the command
`!python tools/test.py configs/pointpillars/hv_pointpillars_fpn_sbn-all_4x8_2x_nus-3d.py /content/mmdetection3d/checkpoints/hv_pointpillars_secfpn_sbn-all_4x8_2x_nus-3d_20210826_225857-f19d00a3.pth --show-dir /content/mmdetection3d/results```
theres an error:
/content/mmdetection3d/mmdet3d/models/backbones/mink_resnet.py:10: UserWarning: Please follow
getting_started.md
to install MinkowskiEngine.'Please follow getting_started.md to install MinkowskiEngine.`')
/usr/local/lib/python3.7/site-packages/mmdet/utils/setup_env.py:39: UserWarning: Setting OMP_NUM_THREADS environment variable for each process to be 1 in default, to avoid your system being overloaded, please further tune the variable for optimal performance in your application as needed.
f'Setting OMP_NUM_THREADS environment variable for each process '
/usr/local/lib/python3.7/site-packages/mmdet/utils/setup_env.py:49: UserWarning: Setting MKL_NUM_THREADS environment variable for each process to be 1 in default, to avoid your system being overloaded, please further tune the variable for optimal performance in your application as needed.
f'Setting MKL_NUM_THREADS environment variable for each process '
/usr/local/lib/python3.7/site-packages/torch/utils/data/dataloader.py:560: UserWarning: This DataLoader will create 4 worker processes in total. Our suggested max number of worker in current system is 2, which is smaller than what this DataLoader is going to create. Please be aware that excessive worker creation might get DataLoader running slow or even freeze, lower the worker number to avoid potential slowness/freeze if necessary.
cpuset_checked))
/content/mmdetection3d/mmdet3d/models/dense_heads/anchor3d_head.py:85: UserWarning: dir_offset and dir_limit_offset will be depressed and be incorporated into box coder in the future
'dir_offset and dir_limit_offset will be depressed and be '
load checkpoint from local path: /content/mmdetection3d/checkpoints/hv_pointpillars_secfpn_sbn-all_4x8_2x_nus-3d_20210826_225857-f19d00a3.pth
The model and loaded state dict do not match exactly
size mismatch for pts_bbox_head.conv_cls.weight: copying a param with shape torch.Size([140, 384, 1, 1]) from checkpoint, the shape in current model is torch.Size([80, 256, 1, 1]).
size mismatch for pts_bbox_head.conv_cls.bias: copying a param with shape torch.Size([140]) from checkpoint, the shape in current model is torch.Size([80]).
size mismatch for pts_bbox_head.conv_reg.weight: copying a param with shape torch.Size([126, 384, 1, 1]) from checkpoint, the shape in current model is torch.Size([72, 256, 1, 1]).
size mismatch for pts_bbox_head.conv_reg.bias: copying a param with shape torch.Size([126]) from checkpoint, the shape in current model is torch.Size([72]).
size mismatch for pts_bbox_head.conv_dir_cls.weight: copying a param with shape torch.Size([28, 384, 1, 1]) from checkpoint, the shape in current model is torch.Size([16, 256, 1, 1]).
size mismatch for pts_bbox_head.conv_dir_cls.bias: copying a param with shape torch.Size([28]) from checkpoint, the shape in current model is torch.Size([16]).
unexpected key in source state_dict: pts_neck.deblocks.0.0.weight, pts_neck.deblocks.0.1.weight, pts_neck.deblocks.0.1.bias, pts_neck.deblocks.0.1.running_mean, pts_neck.deblocks.0.1.running_var, pts_neck.deblocks.0.1.num_batches_tracked, pts_neck.deblocks.1.0.weight, pts_neck.deblocks.1.1.weight, pts_neck.deblocks.1.1.bias, pts_neck.deblocks.1.1.running_mean, pts_neck.deblocks.1.1.running_var, pts_neck.deblocks.1.1.num_batches_tracked, pts_neck.deblocks.2.0.weight, pts_neck.deblocks.2.1.weight, pts_neck.deblocks.2.1.bias, pts_neck.deblocks.2.1.running_mean, pts_neck.deblocks.2.1.running_var, pts_neck.deblocks.2.1.num_batches_tracked
missing keys in source state_dict: pts_neck.lateral_convs.0.conv.weight, pts_neck.lateral_convs.0.bn.weight, pts_neck.lateral_convs.0.bn.bias, pts_neck.lateral_convs.0.bn.running_mean, pts_neck.lateral_convs.0.bn.running_var, pts_neck.lateral_convs.1.conv.weight, pts_neck.lateral_convs.1.bn.weight, pts_neck.lateral_convs.1.bn.bias, pts_neck.lateral_convs.1.bn.running_mean, pts_neck.lateral_convs.1.bn.running_var, pts_neck.lateral_convs.2.conv.weight, pts_neck.lateral_convs.2.bn.weight, pts_neck.lateral_convs.2.bn.bias, pts_neck.lateral_convs.2.bn.running_mean, pts_neck.lateral_convs.2.bn.running_var, pts_neck.fpn_convs.0.conv.weight, pts_neck.fpn_convs.0.bn.weight, pts_neck.fpn_convs.0.bn.bias, pts_neck.fpn_convs.0.bn.running_mean, pts_neck.fpn_convs.0.bn.running_var, pts_neck.fpn_convs.1.conv.weight, pts_neck.fpn_convs.1.bn.weight, pts_neck.fpn_convs.1.bn.bias, pts_neck.fpn_convs.1.bn.running_mean, pts_neck.fpn_convs.1.bn.running_var, pts_neck.fpn_convs.2.conv.weight, pts_neck.fpn_convs.2.bn.weight, pts_neck.fpn_convs.2.bn.bias, pts_neck.fpn_convs.2.bn.running_mean, pts_neck.fpn_convs.2.bn.running_var
[ ] 0/81, elapsed: 0s, ETA:/usr/local/lib/python3.7/site-packages/torch/functional.py:478: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at /opt/conda/conda-bld/pytorch_1656352464346/work/aten/src/ATen/native/TensorShape.cpp:2894.)
return _VF.meshgrid(tensors, **kwargs) # type: ignore[attr-defined]
[>>] 81/81, 1.3 task/s, elapsed: 62s, ETA: 0s`
And theres nothing in my results folder
Environment
sys.platform: linux
Python: 3.7.10 (default, Jun 4 2021, 14:48:32) [GCC 7.5.0]
CUDA available: True
GPU 0: Tesla P100-PCIE-16GB
CUDA_HOME: /usr/local/cuda
NVCC: Cuda compilation tools, release 11.1, V11.1.105
GCC: gcc (Ubuntu 7.5.0-3ubuntu1~18.04) 7.5.0
PyTorch: 1.12.0
PyTorch compiling details: PyTorch built with:
TorchVision: 0.13.0
OpenCV: 4.6.0
MMCV: 1.6.0
MMCV Compiler: GCC 9.3
MMCV CUDA Compiler: 11.3
MMDetection: 2.25.0
MMSegmentation: 0.26.0
MMDetection3D: 1.0.0rc3+eb5a5a2
spconv2.0: False
another question
how can i install the old version of mmdet3d
thanks
The text was updated successfully, but these errors were encountered: