模型 run.py
import torch
import spacy
from torchtext.legacy.data import Field, LabelField,TabularDataset, Iterator, BucketIterator
from torchtext.legacy.datasets import IMDB
import torch.nn as nn
import torch.nn.functional as F
import random
import numpy as np
SEED = 1234
random.seed(SEED)
torch.manual_seed(SEED)
torch.backends.cudnn.deterministic = True
TEXT = Field(tokenize='spacy', tokenizer_language='en_core_web_sm', batch_first=True)
LABEL = LabelField(dtype=torch.float)
train_data, test_data = IMDB.splits(TEXT, LABEL)
train_data, valid_data = train_data.split(random_state=random.seed(SEED))
MAX_VOCAB_SIZE = 25_000
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 = BucketIterator.splits(
(train_data, valid_data, test_data),
batch_size=BATCH_SIZE,
device=device
)
print(len(train_iterator))
class CNN1d(nn.Module):
def __init__(self, vocab_size, embedding_dim, n_filters, filter_sizes, output_dim,
dropout, pad_idx):
super().__init__()
self.embedding = nn.Embedding(vocab_size, embedding_dim, padding_idx=pad_idx)
self.convs = nn.ModuleList([
nn.Conv1d(in_channels=embedding_dim,
out_channels=n_filters,
kernel_size=fs)
for fs in filter_sizes
])
self.fc = nn.Linear(len(filter_sizes) * n_filters, output_dim)
self.dropout = nn.Dropout(dropout)
def forward(self, text):
embedded = self.embedding(text)
embedded = embedded.permute(0, 2, 1)
conved = [F.relu(conv(embedded)) for conv in self.convs]
pooled = [F.max_pool1d(conv, conv.shape[2]).squeeze(2) for conv in conved]
cat = self.dropout(torch.cat(pooled, dim=1))
return self.fc(cat)
INPUT_DIM = len(TEXT.vocab)
EMBEDDING_DIM = 100
N_FILTERS = 100
FILTER_SIZES = [3, 4, 5]
OUTPUT_DIM = 1
DROPOUT = 0.5
PAD_IDX = TEXT.vocab.stoi[TEXT.pad_token]
model = CNN1d(INPUT_DIM, EMBEDDING_DIM, N_FILTERS, FILTER_SIZES, OUTPUT_DIM, 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
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)
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
"""
# round predictions to the closest integer
rounded_preds = torch.round(torch.sigmoid(preds))
correct = (rounded_preds == y).float() # convert into float for division
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()
predictions = model(batch.text).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:
predictions = model(batch.text).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 = 5
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(), 'tut4-model.pt')
torch.save(model.state_dict(), 'save_path.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('save_path.pt'))
test_loss, test_acc = evaluate(model, test_iterator, criterion)
print(f'Test Loss: {test_loss:.3f} | Test Acc: {test_acc * 100:.2f}%')
预测部分:test.py
import torch
import spacy
from torchtext.legacy.data import Field, LabelField
from run import CNN1d
nlp = spacy.load('en_core_web_sm')
TEXT = Field(tokenize='spacy', tokenizer_language='en_core_web_sm', batch_first=True)
LABEL = LabelField(dtype=torch.float)
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
model = CNN1d()
model.load_state_dict(torch.load('save_path.pt'))
model.eval()
def predict_sentiment(model, sentence, min_len=5):
# model.eval()
tokenized = [tok.text for tok in nlp.tokenizer(sentence)]
if len(tokenized) < min_len:
tokenized += ['<pad>'] * (min_len - len(tokenized))
indexed = [TEXT.vocab.stoi[t] for t in tokenized]
tensor = torch.LongTensor(indexed).to(device)
tensor = tensor.unsqueeze(0)
prediction = torch.sigmoid(model(tensor))
return prediction.item()
res = predict_sentiment(model, "This film is terrible")
print(res)
res = predict_sentiment(model, "This film is great")
print(res)