Training Yolov1 error with "invalid device symbol"

[mingmmq]

I am using the GTX1080 trying to train the yolov1 following: ./darknet yolo train cfg/yolov1/yolo.train.cfg extraction.conv.weights but encounter the "invalid device symbol" problem.

Erro Info:

Loading weights from extraction.conv.weights...Done!
Loaded: 1.221084 seconds
[train_yolo: before train_network]
Detection Avg IOU: 0.000000, Pos Cat: 0.000000, All Cat: 0.000000, Pos Obj: 0.000000, Any Obj: 0.000000, count: 41
CUDA Error: invalid device symbol
darknet: ./src/cuda.c:38: check_error: Assertion '0' failed.
Aborted (core dumped)

What the makefile now looks:

GPU=1
CUDNN=0
OPENCV=0
OPENMP=0
DEBUG=0

#ARCH= -gencode arch=compute_30,code=sm_30 \
      #-gencode arch=compute_35,code=sm_35 \
      #-gencode arch=compute_50,code=[sm_50,compute_50] \
      #-gencode arch=compute_52,code=[sm_52,compute_52] \
      #-gencode arch=compute_61,code=[sm_61,compute_61] \
      #-gencode arch=compute_62,code=[sm_62,compute_62]
      #-gencode arch=compute_20,code=[sm_20,sm_21] 
ARCH= --gpu-architecture=compute_52 --gpu-code=compute_52

Any clue of how to sovle this?

[barresoft]

do you solve it?