Maskrcnn-benchmark: Issue with Demo

[bebenoz]

🐛 Bug

Hello,
After following the steps in installation Option 1 Step by step installation. Everything seems to be ok installation wise however when I try to run the demo code for webcam I get the following error.
python webcam.py --min-image-size 800
Traceback (most recent call last):
File "webcam.py", line 6, in
from predictor import COCODemo
File "/home/nova/mask-rcnn/maskrcnn-benchmark/demo/predictor.py", line 6, in
from maskrcnn_benchmark.modeling.detector import build_detection_model
File "/home/nova/mask-rcnn/maskrcnn-benchmark/maskrcnn_benchmark/modeling/detector/__init__.py", line 2, in
from .detectors import build_detection_model
File "/home/nova/mask-rcnn/maskrcnn-benchmark/maskrcnn_benchmark/modeling/detector/detectors.py", line 2, in
from .generalized_rcnn import GeneralizedRCNN
File "/home/nova/mask-rcnn/maskrcnn-benchmark/maskrcnn_benchmark/modeling/detector/generalized_rcnn.py", line 11, in
from ..backbone import build_backbone
File "/home/nova/mask-rcnn/maskrcnn-benchmark/maskrcnn_benchmark/modeling/backbone/__init__.py", line 2, in
from .backbone import build_backbone
File "/home/nova/mask-rcnn/maskrcnn-benchmark/maskrcnn_benchmark/modeling/backbone/backbone.py", line 7, in
from maskrcnn_benchmark.modeling.make_layers import conv_with_kaiming_uniform
File "/home/nova/mask-rcnn/maskrcnn-benchmark/maskrcnn_benchmark/modeling/make_layers.py", line 10, in
from maskrcnn_benchmark.layers import Conv2d
File "/home/nova/mask-rcnn/maskrcnn-benchmark/maskrcnn_benchmark/layers/__init__.py", line 9, in
from .nms import nms
File "/home/nova/mask-rcnn/maskrcnn-benchmark/maskrcnn_benchmark/layers/nms.py", line 3, in
from maskrcnn_benchmark import _C
ImportError: /home/nova/mask-rcnn/maskrcnn-benchmark/maskrcnn_benchmark/_C.cpython-37m-x86_64-linux-gnu.so: undefined symbol: __cudaRegisterFatBinaryEnd
My specs are as follows

Thanks

[chengyangfu]

Hi @bebenoz ,
This is caused when you use different PyTorch versions to compile and execute the code.
Make sure you use the same PyTorch version/library to compile and run the code. Then remove the build directory and recompile the maskrcnn-benchmark.

rm -rf build
python setup.py build develop

[Dorozhko-Anton]

Hi @bebenoz . were you able to solve the problem ?
If no, could you provide environment info using collect_env.py script ?

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