我正在尝试运行Facebook研究的maskrcnn代码,主要是按照this自述文件进行安装。我刚刚将pytorch-nightly替换为pytorch 1.0,并已为cuda 10安装了它。总之,在install.md中运行命令后,我又运行了一个conda install pytorch=1.0 torchvision cudatoolkit=10.0 -c pytorch
命令
当我尝试运行maskrcnn代码时,出现此错误。
Traceback (most recent call last):
File "maskrcnn-benchmark/tools/train_net.py", line 16, in <module>
from maskrcnn_benchmark.data import make_data_loader
File "/mnt/nfshome1/FRACTAL/mridul.sharma/maskrcnn-benchmark/maskrcnn_benchmark/data/__init__.py", line 2, in <module>
from .build import make_data_loader
File "/mnt/nfshome1/FRACTAL/mridul.sharma/maskrcnn-benchmark/maskrcnn_benchmark/data/build.py", line 11, in <module>
from . import datasets as D
File "/mnt/nfshome1/FRACTAL/mridul.sharma/maskrcnn-benchmark/maskrcnn_benchmark/data/datasets/__init__.py", line 2, in <module>
from .coco import COCODataset
File "/mnt/nfshome1/FRACTAL/mridul.sharma/maskrcnn-benchmark/maskrcnn_benchmark/data/datasets/coco.py", line 6, in <module>
from maskrcnn_benchmark.structures.segmentation_mask import SegmentationMask
File "/mnt/nfshome1/FRACTAL/mridul.sharma/maskrcnn-benchmark/maskrcnn_benchmark/structures/segmentation_mask.py", line 5, in <module>
from maskrcnn_benchmark.layers.misc import interpolate
File "/mnt/nfshome1/FRACTAL/mridul.sharma/maskrcnn-benchmark/maskrcnn_benchmark/layers/__init__.py", line 10, in <module>
from .nms import nms
File "/mnt/nfshome1/FRACTAL/mridul.sharma/maskrcnn-benchmark/maskrcnn_benchmark/layers/nms.py", line 3, in <module>
from maskrcnn_benchmark import _C
ImportError: libcudart.so.9.0: cannot open shared object file: No such file or directory
我使用此命令来运行代码
python maskrcnn-benchmark/tools/train_net.py --config-file "maskrcnn-benchmark/configs/e2e_mask_rcnn_R_50_FPN_1x.yaml" SOLVER.IMS_PER_BATCH 2