代码在下边已经附上,每句代码的具体意思,也写在上边,没有注释的可能是在task01里写过了,这里就不再重复赘述。因为我自己电脑配置的原因,我将原先的迭代次数5次,改为了1次,原先的hidden_dim=256改成了10,这样跑起来就快多了,如果要调试的话,你可以先试试能不能跑得通,再修改参数。这里我把最后一个predict_sentiment(model, “This film is terrible”)这句代码理解写出来,理解不到位的地方,还请指正。 我们传入IMDB数据集训练好的模型,和我们要预测情感极性的距离,首先程序会到def predict_sentiment(model, sentence):这里,这里就是将,句子里的每一各单词拿出来,对应建立好的字典中,返回的是这个单词对应字典里的下标索引,tensor.unsqueeze(1)这句话会添加一个batch维度,返回size(4,1)的tensor,然后将这个tensor和length_tensor传入我们模型里,模型就是先embedding,把4个次分别进行编码,一个词用100维的向量来表示。接着把编码后的向量输入到RNN里,因为我们只需要最后的向前和向后传播的hidden states,我们只要最后2个hidden layers就行,所以,我们拼接torch.cat((hidden[-2, :, :], hidden[-1, :, :]), dim=1)。最后传入线性层,加个softmax.
import torch
from torchtext.legacy import data
SEED = 1234
torch.manual_seed(SEED)
torch.backends.deterministic = True
TEXT = data.Field(tokenize = 'spacy',
tokenizer_language = 'en_core_web_sm',
include_lengths = True)
LABEL = data.LabelField(dtype = torch.float)
from torchtext.legacy import datasets
train_data, test_data = datasets.IMDB.splits(TEXT, LABEL)
import random
train_data, valid_data = train_data.split(random_state = random.seed(SEED))
MAX_VOCAB_SIZE = 25000
TEXT.build_vocab(train_data,
max_size = MAX_VOCAB_SIZE,
vectors = "glove.6B.100d",
unk_init = torch.Tensor.normal_)
LABEL.build_vocab(train_data)
BATCH_SIZE = 64
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
train_iterator, valid_iterator, test_iterator = data.BucketIterator.splits(
(train_data, valid_data, test_data),
batch_size = BATCH_SIZE,
sort_within_batch = True,
device = device)
import torch.nn as nn
class RNN(nn.Module):
def __init__(self, vocab_size, embedding_dim, hidden_dim, output_dim, n_layers,
bidirectional, dropout, pad_idx):
super().__init__()
self.embedding = nn.Embedding(vocab_size, embedding_dim, padding_idx=pad_idx)
self.rnn = nn.LSTM(embedding_dim,
hidden_dim,
num_layers=n_layers,
bidirectional=bidirectional,
dropout=dropout)
self.fc = nn.Linear(hidden_dim * 2, output_dim)
self.dropout = nn.Dropout(dropout)
def forward(self, text, text_lengths):
embedded = self.dropout(self.embedding(text))
packed_embedded = nn.utils.rnn.pack_padded_sequence(embedded, text_lengths.to('cpu'))
packed_output, (hidden, cell) = self.rnn(packed_embedded)
output, output_lengths = nn.utils.rnn.pad_packed_sequence(packed_output)
hidden = self.dropout(torch.cat((hidden[-2, :, :], hidden[-1, :, :]), dim=1))
return self.fc(hidden)
INPUT_DIM = len(TEXT.vocab)
EMBEDDING_DIM = 100
HIDDEN_DIM = 10
OUTPUT_DIM = 1
N_LAYERS = 2
BIDIRECTIONAL = True
DROPOUT = 0.5
PAD_IDX = TEXT.vocab.stoi[TEXT.pad_token]
model = RNN(INPUT_DIM,
EMBEDDING_DIM,
HIDDEN_DIM,
OUTPUT_DIM,
N_LAYERS,
BIDIRECTIONAL,
DROPOUT,
PAD_IDX)
def count_parameters(model):
return sum(p.numel() for p in model.parameters() if p.requires_grad)
print(f'The model has {count_parameters(model):,} trainable parameters')
pretrained_embeddings = TEXT.vocab.vectors
print(pretrained_embeddings.shape)
model.embedding.weight.data.copy_(pretrained_embeddings)
UNK_IDX = TEXT.vocab.stoi[TEXT.unk_token]
model.embedding.weight.data[UNK_IDX] = torch.zeros(EMBEDDING_DIM)
model.embedding.weight.data[PAD_IDX] = torch.zeros(EMBEDDING_DIM)
print(model.embedding.weight.data)
import torch.optim as optim
optimizer = optim.Adam(model.parameters())
criterion = nn.BCEWithLogitsLoss()
model = model.to(device)
criterion = criterion.to(device)
def binary_accuracy(preds, y):
"""
Returns accuracy per batch, i.e. if you get 8/10 right, this returns 0.8, NOT 8
"""
rounded_preds = torch.round(torch.sigmoid(preds))
correct = (rounded_preds == y).float()
acc = correct.sum() / len(correct)
return acc
def train(model, iterator, optimizer, criterion):
epoch_loss = 0
epoch_acc = 0
model.train()
for batch in iterator:
optimizer.zero_grad()
text, text_lengths = batch.text
predictions = model(text, text_lengths).squeeze(1)
loss = criterion(predictions, batch.label)
acc = binary_accuracy(predictions, batch.label)
loss.backward()
optimizer.step()
epoch_loss += loss.item()
epoch_acc += acc.item()
return epoch_loss / len(iterator), epoch_acc / len(iterator)
def evaluate(model, iterator, criterion):
epoch_loss = 0
epoch_acc = 0
model.eval()
with torch.no_grad():
for batch in iterator:
text, text_lengths = batch.text
predictions = model(text, text_lengths).squeeze(1)
loss = criterion(predictions, batch.label)
acc = binary_accuracy(predictions, batch.label)
epoch_loss += loss.item()
epoch_acc += acc.item()
return epoch_loss / len(iterator), epoch_acc / len(iterator)
import time
def epoch_time(start_time, end_time):
elapsed_time = end_time - start_time
elapsed_mins = int(elapsed_time / 60)
elapsed_secs = int(elapsed_time - (elapsed_mins * 60))
return elapsed_mins, elapsed_secs
N_EPOCHS = 1
best_valid_loss = float('inf')
for epoch in range(N_EPOCHS):
start_time = time.time()
train_loss, train_acc = train(model, train_iterator, optimizer, criterion)
valid_loss, valid_acc = evaluate(model, valid_iterator, criterion)
end_time = time.time()
epoch_mins, epoch_secs = epoch_time(start_time, end_time)
if valid_loss < best_valid_loss:
best_valid_loss = valid_loss
torch.save(model.state_dict(), 'tut2-model.pt')
print(f'Epoch: {epoch + 1:02} | Epoch Time: {epoch_mins}m {epoch_secs}s')
print(f'\tTrain Loss: {train_loss:.3f} | Train Acc: {train_acc * 100:.2f}%')
print(f'\t Val. Loss: {valid_loss:.3f} | Val. Acc: {valid_acc * 100:.2f}%')
model.load_state_dict(torch.load('tut2-model.pt'))
test_loss, test_acc = evaluate(model, test_iterator, criterion)
print(f'Test Loss: {test_loss:.3f} | Test Acc: {test_acc*100:.2f}%')
import spacy
nlp = spacy.load('en_core_web_sm')
def predict_sentiment(model, sentence):
model.eval()
tokenized = [tok.text for tok in nlp.tokenizer(sentence)]
indexed = [TEXT.vocab.stoi[t] for t in tokenized]
length = [len(indexed)]
tensor = torch.LongTensor(indexed).to(device)
tensor = tensor.unsqueeze(1)
length_tensor = torch.LongTensor(length)
prediction = torch.sigmoid(model(tensor, length_tensor))
return prediction.item()
predict_sentiment(model, "This film is terrible")
|