luojq_sysusdcs

a question about transformer

1

class MultiHeadAttention(nn.Module): def __init__(self): super(MultiHeadAttention, self).__init__() self.W_Q = nn.Linear(d_model, d_k * n_heads) self.W_K = nn.Linear(d_model, d_k * n_heads) self.W_V = nn.Linear(d_model, d_v * n_heads) def forward(self, Q, K, V, attn_mask):...

class Multi_Head_Attention(nn.Module): def __init__(self, dim_model, num_head, dropout=0.0): super(Multi_Head_Attention, self).__init__() self.num_head = num_head assert dim_model % num_head == 0 self.dim_head = dim_model // self.num_head self.fc_Q = nn.Linear(dim_model, num_head * self.dim_head) self.fc_K...