ValueError: not enough values to unpack (expected 2, got 1) when training my custom dataset with resnet50 with its layer 1 about relevance-cam HOT 1 CLOSED

I do thank you so much to get your paper with github code because it helps me a lot to my study. It is ok to train with my custom dataset with other layers (2, 3 and 4) but not its layer 1. Please help me how I should fix it.

you should add some code，example layer1， elif mode == 'layer1': R3 = self.layer4.relprop(R4, 1) R2 = self.layer3.relprop(R3, 1) R1 = self.layer2.relprop(R2, 1) r_weight1 = torch.mean(R1, dim=(2, 3), keepdim=True) r_cam1 = layer1 * r_weight1 r_cam1 = torch.sum(r_cam1, dim=(1), keepdim=True) return r_cam1,z

from relevance-cam.