got 'AssertionError: Torch not compiled with CUDA enabled'

[myounus96]

I installed pytorch with cpuonly,but still got the above error,even I didn't have gpu.

Also tried
cfg.MODEL.DEVICE = "cpu" from https://github.com/facebookresearch/detectron2/issues/300#issuecomment-552465720

output of python -m detectron2.utils.collect_env
log.txt

---

sys.platform win32
Python 3.7.6 (default, Jan 8 2020, 20:23:39) [MSC v.1916 64 bit (AMD64)]
Numpy 1.17.4
Detectron2 Compiler MSVC 192328106
Detectron2 CUDA Compiler not available
DETECTRON2_ENV_MODULE
PyTorch 1.3.1
PyTorch Debug Build False
torchvision unknown
CUDA available False
Pillow 6.2.2
cv2 4.1.2

---

PyTorch built with:

• MSVC 191125547
• Intel(R) Math Kernel Library Version 2019.0.4 Product Build 20190411 for Intel(R) 64 architecture applications
• OpenMP 200203
• Build settings: BLAS=MKL, BUILD_NAMEDTENSOR=OFF, BUILD_TYPE=Release, CXX_FLAGS=/DWIN32 /D_WINDOWS /GR /w /EHa /MP /bigobj -openmp, DISABLE_NUMA=1, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, USE_CUDA=False, USE_EXCEPTION_PTR=1, USE_GFLAGS=OFF, USE_GLOG=OFF, USE_MKL=ON, USE_MKLDNN=OFF, USE_MPI=OFF, USE_NCCL=OFF, USE_NNPACK=OFF, USE_OPENMP=ON, USE_STATIC_DISPATCH=OFF,