about fssd_lite_mobilenetv1

[WesterL]

(1). My pytorch version is 1.4.0, and my data class is 1, when I train this model ,I encountered this problem:
RuntimeError: Error(s) in loading state_dict for FSSDLite:
size mismatch for conf.0.weight: copying a param with shape torch.Size([126, 512, 3, 3]) from checkpoint, the shape in current model is torch.Size([12, 512, 3, 3]).
......
size mismatch for conf.5.bias: copying a param with shape torch.Size([84]) from checkpoint, the shape in current model is torch.Size([8]).
I have change the num_classes to 2. Is it just because my pytoch version or other problems? Thank you for any reply！

(2) In FSSD-MobileNet, I want to change the number of fused feature maps, such as make four feature maps to fuse together, which part should I change?