advanced_source/ddp_pipeline.py [87:120]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    sys.exit(0)

class Encoder(nn.Module):
    def __init__(self, ntoken, ninp, dropout=0.5):
        super(Encoder, self).__init__()
        self.pos_encoder = PositionalEncoding(ninp, dropout)
        self.encoder = nn.Embedding(ntoken, ninp)
        self.ninp = ninp
        self.init_weights()

    def init_weights(self):
        initrange = 0.1
        self.encoder.weight.data.uniform_(-initrange, initrange)

    def forward(self, src):
        # Need (S, N) format for encoder.
        src = src.t()
        src = self.encoder(src) * math.sqrt(self.ninp)
        return self.pos_encoder(src)

class Decoder(nn.Module):
    def __init__(self, ntoken, ninp):
        super(Decoder, self).__init__()
        self.decoder = nn.Linear(ninp, ntoken)
        self.init_weights()

    def init_weights(self):
        initrange = 0.1
        self.decoder.bias.data.zero_()
        self.decoder.weight.data.uniform_(-initrange, initrange)

    def forward(self, inp):
        # Need batch dimension first for output of pipeline.
        return self.decoder(inp).permute(1, 0, 2)
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



intermediate_source/pipeline_tutorial.py [54:87]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    sys.exit(0)

class Encoder(nn.Module):
    def __init__(self, ntoken, ninp, dropout=0.5):
        super(Encoder, self).__init__()
        self.pos_encoder = PositionalEncoding(ninp, dropout)
        self.encoder = nn.Embedding(ntoken, ninp)
        self.ninp = ninp
        self.init_weights()

    def init_weights(self):
        initrange = 0.1
        self.encoder.weight.data.uniform_(-initrange, initrange)

    def forward(self, src):
        # Need (S, N) format for encoder.
        src = src.t()
        src = self.encoder(src) * math.sqrt(self.ninp)
        return self.pos_encoder(src)

class Decoder(nn.Module):
    def __init__(self, ntoken, ninp):
        super(Decoder, self).__init__()
        self.decoder = nn.Linear(ninp, ntoken)
        self.init_weights()

    def init_weights(self):
        initrange = 0.1
        self.decoder.bias.data.zero_()
        self.decoder.weight.data.uniform_(-initrange, initrange)

    def forward(self, inp):
        # Need batch dimension first for output of pipeline.
        return self.decoder(inp).permute(1, 0, 2)
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -