search

ssecv / LeNo

The official implementation of AAAI 2023 "LeNo: Adversarial Robust Salient Object Detection Networks with Learnable Noise"
16 stars 3 forks source link

train error #3

Open zgp123-wq opened 1 year ago

zgp123-wq commented 1 year ago

stack expects each tensor to be equal size, but got [3, 1632, 1224] at entry 0 and [3, 1296, 968] at entry 1

cdfcyt commented 1 year ago

How to generate adversarial samples for RGBD datasets？

chciw commented 1 year ago

Before inputting to the network, the images should be pre-processed to a uniform size.

kexi0714 commented 1 week ago

在输入网络之前，应该将图像预处理为统一的大小。

For LeNo, I deployed it on my SOD network and it didn't show any defensive effect. Can you give me some help? I will be very grateful