bad result of mnist training

[songsu1008]

hello,
I trained the mnist file by following your code(change nothing),
(type like this in terminal :
ython train.py --dataset mnist --isize 32 --nc 1 --niter 1 --abnormal_class 0 --model skipganomaly
)
but the result is not good like below figure.(pink dots are normal_labels, and skyblue dots are abnormal_labels.) how can I increase difference of the anomaly scores between normal and abnormal?

Figure_1