dlib: Out of memory

Hi,

I have compiled dlib on a AWS GPU instance (4G). When running dnn_mmod_ex faces i get the following error:

num training images: 4
num testing images:  5
detection window width,height:      40,40
overlap NMS IOU thresh:             0.0781701
overlap NMS percent covered thresh: 0.257122
step#: 0     learning rate: 0.1   average loss: 0           steps without apparent progress: 0
Error while calling cudaMalloc(&data, new_size*sizeof(float)) in file /home/ubuntu/dlib/dlib/dnn/gpu_data.cpp:191. code: 2, reason: out of memory

Any idea what i’m doing wrong ?