In torch, we can share parameters between two nets like this, local r1 = nn.Recurrent( opt.embeddingSize, cnn, h2h, nn.Identity(), opt.sampleSeqLength) local r2 = nn.Recurrent( opt.embeddingSize, cnn:clone('weight','bias','gradWeight','gradBia…

I think you can refer to this topic: [image] How to create model with sharing weight? EDIT: we do support sharing Parameters between modules, but it’s recommended to decompose your model into many pieces that don’t share parameters if possible. We don’t support using the…

you can simply use the same nets on different outputs. In Torch, each net is tied to a particular output, in PyTorch it is not.

Hi, can you explain it ? Thanks

we can implement weight sharing among the innermost layers by simply reusing the same Module multiple times when defining the forward pass. please see https://pytorch.org/tutorials/beginner/examples_nn/dynamic_net.html#pytorch-control-flow-weight-sharing

Yes, you’re right,this is how pytorch creates model with sharing weight.

Do you use torch instead of pytorch?

No, I use pytorch instead of torch.

How to share weights between two nets?

shufanwu (Wushufan) June 27, 2017, 2:13am 2

I think you can refer to this topic: