无论我训练多长时间，准确性仍然很低，并且损失没有减少。
input_dim = len（vocab）
embedding_dim：我尝试了100〜500，没有太大改善
hidden_dim = 512
output_dim = 6
forward（）的每个“输入”都类似于下面的张量，每个元素都是词汇中单词的索引。
tensor([[11831, 11831, 11831, 11831, 11831, 11831, 11831, 11831, 11831, 11831,
11831, 11831, 11831, 11831, 11831, 11831, 11831, 11831, 11831, 11831,
11831, 11831, 11831, 11831, 11831, 11831, 11831, 11831, 11831, 11831,
11831, 11831, 11831, 11831, 11831, 11831, 11831, 11831, 11831, 11831,
11831, 11831, 11831, 11831, 11831, 11831, 11831, 11831, 11831, 11831,
11831, 11831, 11831, 11831, 11831, 11831, 11831, 11831, 11831, 11831,
11831, 11831, 11831, 11831, 11831, 11831, 5010, 3771, 7949, 2125,
8461, 1170, 5010, 3771, 7949, 2125, 0, 4937, 4939, 4281]],
device='cuda:0')
模型有什么问题吗？
class RNN(nn.Module):
def __init__(self, input_dim, embedding_dim, hidden_dim, output_dim):
super(RNN, self).__init__()
self.hidden_dim = hidden_dim
self.embedding = nn.Embedding(input_dim, embedding_dim)
self.rnn = nn.RNN(embedding_dim, hidden_dim, batch_first=True)
self.W = nn.Linear(hidden_dim, output_dim)
self.softmax = nn.LogSoftmax(dim=1)
self.loss = nn.NLLLoss()
def compute_Loss(self, predicted_vector, gold_label):
return self.loss(predicted_vector, gold_label)
def hidden0(self, inputs):
batch_dim = inputs.size(0)
h0 = torch.zeros(1, batch_dim, self.hidden_dim)
return h0
def forward(self, inputs):
hidden = self.hidden0(inputs).to(get_device())
inputs = inputs.reshape(-1)
#print(inputs)
embed = self.embedding(inputs).unsqueeze(0)
out, hn = self.rnn(embed, hidden)
output = out.view(-1, self.hidden_dim)
z = self.W(output)
predicted_vector = self.softmax(z)
predicted_vector = predicted_vector[-1].view(1,6)
return predicted_vector