Closed Xavier-Zeng closed 5 years ago
Hi,
It's difficult to say what the problem is without further information.
Can you please copy and paste the output from the environment collection script from PyTorch (or fill out the checklist below manually).
You can get the script and run it with:
wget https://raw.githubusercontent.com/pytorch/pytorch/master/torch/utils/collect_env.py
# For security purposes, please check the contents of collect_env.py before running it.
python collect_env.py
conda
, pip
, source):Thanks for you patient reply!
conda install pytorch torchvision -c pytorch
When I run webcam.py, Another errors happened as follows:
Traceback (most recent call last):
File "webcam.py", line 6, in <module>
from predictor import COCODemo
File "/media/xavier/SSD256/caffe2_notebooks/maskrcnn-benchmark/demo/predictor.py", line 6, in <module>
from maskrcnn_benchmark.modeling.detector import build_detection_model
File "/media/xavier/SSD256/caffe2_notebooks/maskrcnn-benchmark/maskrcnn_benchmark/modeling/detector/__init__.py", line 2, in <module>
from .detectors import build_detection_model
File "/media/xavier/SSD256/caffe2_notebooks/maskrcnn-benchmark/maskrcnn_benchmark/modeling/detector/detectors.py", line 2, in <module>
from .generalized_rcnn import GeneralizedRCNN
File "/media/xavier/SSD256/caffe2_notebooks/maskrcnn-benchmark/maskrcnn_benchmark/modeling/detector/generalized_rcnn.py", line 11, in <module>
from ..backbone import build_backbone
File "/media/xavier/SSD256/caffe2_notebooks/maskrcnn-benchmark/maskrcnn_benchmark/modeling/backbone/__init__.py", line 2, in <module>
from .backbone import build_backbone
File "/media/xavier/SSD256/caffe2_notebooks/maskrcnn-benchmark/maskrcnn_benchmark/modeling/backbone/backbone.py", line 7, in <module>
from . import resnet
File "/media/xavier/SSD256/caffe2_notebooks/maskrcnn-benchmark/maskrcnn_benchmark/modeling/backbone/resnet.py", line 19, in <module>
from maskrcnn_benchmark.layers import FrozenBatchNorm2d
File "/media/xavier/SSD256/caffe2_notebooks/maskrcnn-benchmark/maskrcnn_benchmark/layers/__init__.py", line 8, in <module>
from .nms import nms
File "/media/xavier/SSD256/caffe2_notebooks/maskrcnn-benchmark/maskrcnn_benchmark/layers/nms.py", line 3, in <module>
from maskrcnn_benchmark import _C
ImportError: /media/xavier/SSD256/caffe2_notebooks/maskrcnn-benchmark/maskrcnn_benchmark/_C.cpython-36m-x86_64-linux-gnu.so: undefined symbol: _ZN2at5ErrorC1ENS_14SourceLocationERKNSt7__cxx1112basic_stringIcSt11char_traitsIcESaIcEEE
And Now, I can't even run Mask_R-CNN_demo.ipynb!
Hi,
Please follow the installation instructions from https://github.com/facebookresearch/maskrcnn-benchmark/blob/master/INSTALL.md. You need to install PyTorch nightly, and you probably have conflicting libraries in your system.
I'd suggest creating a new conda environment.
Also, this library runs on PyTorch, and not the caffe2 backend. There might be conflicts if you try to install and old version of caffe2 in the same environment as PyTorch.
I'm closing this issue as it seems like following the installation instructions from INSTALL.md should solve your issue, but let me know if that's not the case.
Excuse me, are you solving this problem now?I have same problem as you.
Traceback (most recent call last):
File "C:/Users/rrrr/Desktop/maskrcnn-benchmark-master/demo/predictor.py", line 6, in
❓ Questions and Help
Thanks for your great contributions! When I run the demo as follows,
an error happened as this:
Is there anything I've made wrong? How could I solve this problem? Thanks for your help!