[DL]基于Pytorch的N-gram Language Model

import torchimport torch.autograd as autogradimport torch.nn as nnimport torch.nn.functional as Fimport torch.optim as optimtorch.manual_seed(1)word2index={'a':0,'b':1}embeds=nn.Embedding(2,5)a_embed=embeds(autograd.Variable(torch.LongTensor([word2index['a']])))print(a_embed)CONTEXT_SIZE = 2EMBEDDING_DIM = 10# We will use Shakespeare Sonnet 2test_sentence = """When forty winters shall besiege thy brow,And dig deep trenches in thy beauty's field,Thy youth's proud livery so gazed on now,Will be a totter'd weed of small worth held:Then being asked, where all thy beauty lies,Where all the treasure of thy lusty days;To say, within thine own deep sunken eyes,Were an all-eating shame, and thriftless praise.How much more praise deserv'd thy beauty's use,If thou couldst answer 'This fair child of mineShall sum my count, and make my old excuse,'Proving his beauty by succession thine!This were to be new made when thou art old,And see thy blood warm when thou feel'st it cold.""".split()# we should tokenize the input, but we will ignore that for now# build a list of tuples.  Each tuple is ([ word_i-2, word_i-1 ], target word)trigrams = [([test_sentence[i], test_sentence[i + 1]], test_sentence[i + 2])            for i in range(len(test_sentence) - 2)]# print the first 3, just so you can see what they look likeprint(trigrams[:3])vocab = set(test_sentence)word_to_ix = {word: i for i, word in enumerate(vocab)}class NGramLanguageModeler(nn.Module):    def __init__(self, vocab_size, embedding_dim, context_size):        super(NGramLanguageModeler, self).__init__()        self.embeddings = nn.Embedding(vocab_size, embedding_dim)        self.linear1 = nn.Linear(context_size * embedding_dim, 128)        self.linear2 = nn.Linear(128, vocab_size)    def forward(self, inputs):        print('inputs:',inputs)        embeds = self.embeddings(inputs).view((1, -1))        out = F.relu(self.linear1(embeds))        out = self.linear2(out)        log_probs = F.log_softmax(out)        return log_probslosses = []loss_function = nn.NLLLoss()model = NGramLanguageModeler(len(vocab), EMBEDDING_DIM, CONTEXT_SIZE)optimizer = optim.SGD(model.parameters(), lr=0.001)for epoch in range(10):    total_loss = torch.Tensor([0])    for context, target in trigrams:        # Step 1. Prepare the inputs to be passed to the model (i.e, turn the words        # into integer indices and wrap them in variables)        context_idxs = [word_to_ix[w] for w in context]        context_var = autograd.Variable(torch.LongTensor(context_idxs))        # Step 2. Recall that torch *accumulates* gradients. Before passing in a        # new instance, you need to zero out the gradients from the old        # instance        model.zero_grad()        # Step 3. Run the forward pass, getting log probabilities over next        # words        log_probs = model(context_var)        # Step 4. Compute your loss function. (Again, Torch wants the target        # word wrapped in a variable)        loss = loss_function(log_probs, autograd.Variable(            torch.LongTensor([word_to_ix[target]])))        # Step 5. Do the backward pass and update the gradient        loss.backward()        optimizer.step()        total_loss += loss.data    losses.append(total_loss)print(losses)  # The loss decreased every iteration over the training data!tensor=torch.LongTensor(2)tensor[0]=1tensor[1]=2print(torch.max(model(torch.autograd.Variable(tensor)),1))