源纹理从CG纹理库中获取,并进行下采样使得像素总数等于256的平方(下采样是为了匹配网络训练中图像的尺寸,并降低计算成本)。在K40 GPU上运行一个纹理需要10分钟,纹理是通过匹配Simonyan and Zisserman等人的工作中提到的19层VGG网络的归一化版本的“pool4”、“pool3”、“pool2”、“pool1”、“conv_1”各层feature map之间的相关性生成的。
The weights in the normalised network are scaled such that the mean activation of each filter over images and positions is equal to one. Such re-scaling can always be done without changing the output of a neural network as long as the non-linearities in the network is are rectifying linear.