I have a 6 g graphics card memory, but prompt every time not enough use, the model run is yolo v3, and guide how



Error:
Traceback (the most recent call last) :
The File "D:/08 - YOLO/PyTorch - YOLOv3/train. Py", line 125, in & lt; module>
Optimizer. Step ()
The File "C: \ ProgramData \ Anaconda3 \ envs \ CSGPU \ lib \ site - packages, torch, optim, Adam. Py", line 101, in step
Denom=exp_avg_sq. SQRT (). Add_ (group [' eps'])
RuntimeError: CUDA out of memory. Tried to the allocate 18.00 MiB (GPU 0; 6.00 GiB total capacity; 870.30 the MiB already allocated; 8.60 the MiB free; 89.70 the MiB cached)