Inception 网络期望输入图像具有从 [-1, 1] 缩放的颜色通道.如此处所见.

The Inception networks expect the input image to have color channels scaled from [-1, 1]. As seen here.

您可以使用现有的预处理，或者在您的示例中自己缩放图像:im = 2*(im/255.0)-1.0，然后将它们提供给网络.

You could either use the existing preprocessing, or in your example just scale the images yourself: im = 2*(im/255.0)-1.0 before feeding them to the network.

在不缩放输入 [0-255] 的情况下，它比网络预期的要大得多，并且所有偏差都可以非常强烈地预测类别 918(漫画书).

Without scaling the input [0-255] is much larger than the network expects and the biases all work to very strongly predict category 918 (comic books).