in model.py line 76: context = attn_weights.bmm(encoder_outputs.transpose(0, 1)) # (B,1,N)

[Huijun-Cui]

Is this correct? I look up the explanation about bmm in official document,it syas that
batch1 and batch2 must be 3-D tensors each containing the same number of matrices.
but as you defined before, the attn_weights is a 2-D shape ,I think here may be some mistakes

[Hahallo]

return F.softmax(attn_energies, dim=1).unsqueeze(1)
This line of code makes attn_weights 3-D shape