Spend too much time on running detectron2.engine.DefaultPredictor(cfg)

[ralph0813]

If you do not know the root cause of the problem / bug, and wish someone to help you, please
include:

When I try to run the demo :

from detectron2.engine import DefaultPredictor
from detectron2.config import get_cfg
cfg = get_cfg()
cfg.merge_from_file("./detectron2_repo/configs/COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_3x.yaml")
cfg.MODEL.ROI_HEADS.SCORE_THRESH_TEST = 0.5  # set threshold for this model
cfg.MODEL.WEIGHTS = "detectron2://COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_3x/137849600/model_final_f10217.pkl"
predictor = DefaultPredictor(cfg)
outputs = predictor(im)

It took 390 seconds to run predictor = DefaultPredictor(cfg)

when I debug the code, it seemed to be
pixel_mean = torch.Tensor(cfg.MODEL.PIXEL_MEAN).to(self.device).view(num_channels, 1, 1)
in the rcnn.py which took a long time.
But it works fine on colab.
How can i fix it or what's wrong with my environment?

Environment

---

Python 3.7.4 (default, Aug 13 2019, 20:35:49) [GCC 7.3.0]
Detectron2 Compiler GCC 7.4
DETECTRON2_ENV_MODULE
PyTorch 1.3.0
PyTorch Debug Build False
CUDA available True
GPU 0 GeForce RTX 2080
Pillow 6.1.0
cv2 4.1.0

---

PyTorch built with:

• GCC 7.3
• Intel(R) Math Kernel Library Version 2019.0.4 Product Build 20190411 for Intel(R) 64 architecture applications
• Intel(R) MKL-DNN v0.20.5 (Git Hash 0125f28c61c1f822fd48570b4c1066f96fcb9b2e)
• OpenMP 201511 (a.k.a. OpenMP 4.5)
• NNPACK is enabled
• CUDA Runtime 10.1
• NVCC architecture flags: -gencode;arch=compute_35,code=sm_35;-gencode;arch=compute_50,code=sm_50;-gencode;arch=compute_50,code=compute_50
• CuDNN 7.6.3
• Magma 2.5.1
• Build settings: BLAS=MKL, BUILD_NAMEDTENSOR=OFF, BUILD_TYPE=Release, CXX_FLAGS= -Wno-deprecated -fvisibility-inlines-hidden -fopenmp -DUSE_FBGEMM -DUSE_QNNPACK -DUSE_PYTORCH_QNNPACK -O2 -fPIC -Wno-narrowing -Wall -Wextra -Wno-missing-field-initializers -Wno-type-limits -Wno-array-bounds -Wno-unknown-pragmas -Wno-sign-compare -Wno-unused-parameter -Wno-unused-variable -Wno-unused-function -Wno-unused-result -Wno-strict-overflow -Wno-strict-aliasing -Wno-error=deprecated-declarations -Wno-stringop-overflow -Wno-error=pedantic -Wno-error=redundant-decls -Wno-error=old-style-cast -fdiagnostics-color=always -faligned-new -Wno-unused-but-set-variable -Wno-maybe-uninitialized -fno-math-errno -fno-trapping-math -Wno-stringop-overflow, DISABLE_NUMA=1, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, PERF_WITH_AVX512=1, USE_CUDA=True, USE_EXCEPTION_PTR=1, USE_GFLAGS=OFF, USE_GLOG=OFF, USE_MKL=ON, USE_MKLDNN=ON, USE_MPI=OFF, USE_NCCL=ON, USE_NNPACK=ON, USE_OPENMP=ON, USE_STATIC_DISPATCH=OFF,

[ppwwyyxx]

Duplicate of #27 and #7 . This is a pytorch installation issue. Please check the existing issues for details.