search

yun-liu / RCF

Richer Convolutional Features for Edge Detection
Other
761 stars 259 forks source link

归一化问题 #120

Open bigAndSmall opened 4 years ago

bigAndSmall commented 4 years ago

在data_loader.py 中： def prepare_image_PIL(im): im = im[:,:,::-1] - np.zeros_like(im) # rgb to bgr im -= np.array((104.00698793,116.66876762,122.67891434)) im = np.transpose(im, (2, 0, 1)) # (H x W x C) to (C x H x W) return im 我想请问一下这里的104.00698793,116.66876762,122.67891434是什么，是怎么得出来的？如果换了数据集的话，要怎么去获得呢，谢谢！

yun-liu commented 4 years ago

ImageNet均值

bigAndSmall commented 4 years ago

好的，谢谢