PyTorch 2.2 中文官方教程（七）（1）

!pip  install  -U  portalocker>=2.0.0` 

import torch
from torchtext.datasets import AG_NEWS
train_iter = iter(AG_NEWS(split="train")) 

next(train_iter)
>>>  (3,  "Fears for T N pension after talks Unions representing workers at Turner
Newall say they are 'disappointed' after talks with stricken parent firm Federal
Mogul.")
next(train_iter)
>>>  (4,  "The Race is On: Second Private Team Sets Launch Date for Human
Spaceflight (SPACE.com) SPACE.com - TORONTO, Canada -- A second\\team of
rocketeers competing for the  #36;10 million Ansari X Prize, a contest
for\\privately funded suborbital space flight, has officially announced
the first\\launch date for its manned rocket.")
next(train_iter)
>>>  (4,  'Ky. Company Wins Grant to Study Peptides (AP) AP - A company founded
by a chemistry researcher at the University of Louisville won a grant to develop
a method of producing better peptides, which are short chains of amino acids, the
building blocks of proteins.') 

from torchtext.data.utils import get_tokenizer
from torchtext.vocab import build_vocab_from_iterator
tokenizer = get_tokenizer("basic_english")
train_iter = AG_NEWS(split="train")
def yield_tokens(data_iter):
    for _, text in data_iter:
        yield tokenizer(text)
vocab = build_vocab_from_iterator(yield_tokens(train_iter), specials=["<unk>"])
vocab.set_default_index(vocab["<unk>"]) 

vocab(['here',  'is',  'an',  'example'])
>>>  [475,  21,  30,  5297] 

text_pipeline = lambda x: vocab(tokenizer(x))
label_pipeline = lambda x: int(x) - 1 

text_pipeline('here is the an example')
>>>  [475,  21,  2,  30,  5297]
label_pipeline('10')
>>>  9 

from torch.utils.data import DataLoader
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
def collate_batch(batch):
    label_list, text_list, offsets = [], [], [0]
    for _label, _text in batch:
        label_list.append(label_pipeline(_label))
        processed_text = torch.tensor(text_pipeline(_text), dtype=torch.int64)
        text_list.append(processed_text)
        offsets.append(processed_text.size(0))
    label_list = torch.tensor(label_list, dtype=torch.int64)
    offsets = torch.tensor(offsets[:-1]).cumsum(dim=0)
    text_list = torch.cat(text_list)
    return label_list.to(device), text_list.to(device), offsets.to(device)
train_iter = AG_NEWS(split="train")
dataloader = DataLoader(
    train_iter, batch_size=8, shuffle=False, collate_fn=collate_batch
) 

from torch import nn
class TextClassificationModel(nn.Module):
    def __init__(self, vocab_size, embed_dim, num_class):
        super(TextClassificationModel, self).__init__()
        self.embedding = nn.EmbeddingBag(vocab_size, embed_dim, sparse=False)
        self.fc = nn.Linear(embed_dim, num_class)
        self.init_weights()
    def init_weights(self):
        initrange = 0.5
        self.embedding.weight.data.uniform_(-initrange, initrange)
        self.fc.weight.data.uniform_(-initrange, initrange)
        self.fc.bias.data.zero_()
    def forward(self, text, offsets):
        embedded = self.embedding(text, offsets)
        return self.fc(embedded) 

1  :  World
2  :  Sports
3  :  Business
4  :  Sci/Tec 

train_iter = AG_NEWS(split="train")
num_class = len(set([label for (label, text) in train_iter]))
vocab_size = len(vocab)
emsize = 64
model = TextClassificationModel(vocab_size, emsize, num_class).to(device) 

import time
def train(dataloader):
    model.train()
    total_acc, total_count = 0, 0
    log_interval = 500
    start_time = time.time()
    for idx, (label, text, offsets) in enumerate(dataloader):
        optimizer.zero_grad()
        predicted_label = model(text, offsets)
        loss = criterion(predicted_label, label)
        loss.backward()
        torch.nn.utils.clip_grad_norm_(model.parameters(), 0.1)
        optimizer.step()
        total_acc += (predicted_label.argmax(1) == label).sum().item()
        total_count += label.size(0)
        if idx % log_interval == 0 and idx > 0:
            elapsed = time.time() - start_time
            print(
                "| epoch {:3d} | {:5d}/{:5d} batches "
                "| accuracy {:8.3f}".format(
                    epoch, idx, len(dataloader), total_acc / total_count
                )
            )
            total_acc, total_count = 0, 0
            start_time = time.time()
def evaluate(dataloader):
    model.eval()
    total_acc, total_count = 0, 0
    with torch.no_grad():
        for idx, (label, text, offsets) in enumerate(dataloader):
            predicted_label = model(text, offsets)
            loss = criterion(predicted_label, label)
            total_acc += (predicted_label.argmax(1) == label).sum().item()
            total_count += label.size(0)
    return total_acc / total_count 

from torch.utils.data.dataset import random_split
from torchtext.data.functional import to_map_style_dataset
# Hyperparameters
EPOCHS = 10  # epoch
LR = 5  # learning rate
BATCH_SIZE = 64  # batch size for training
criterion = torch.nn.CrossEntropyLoss()
optimizer = torch.optim.SGD(model.parameters(), lr=LR)
scheduler = torch.optim.lr_scheduler.StepLR(optimizer, 1.0, gamma=0.1)
total_accu = None
train_iter, test_iter = AG_NEWS()
train_dataset = to_map_style_dataset(train_iter)
test_dataset = to_map_style_dataset(test_iter)
num_train = int(len(train_dataset) * 0.95)
split_train_, split_valid_ = random_split(
    train_dataset, [num_train, len(train_dataset) - num_train]
)
train_dataloader = DataLoader(
    split_train_, batch_size=BATCH_SIZE, shuffle=True, collate_fn=collate_batch
)
valid_dataloader = DataLoader(
    split_valid_, batch_size=BATCH_SIZE, shuffle=True, collate_fn=collate_batch
)
test_dataloader = DataLoader(
    test_dataset, batch_size=BATCH_SIZE, shuffle=True, collate_fn=collate_batch
)
for epoch in range(1, EPOCHS + 1):
    epoch_start_time = time.time()
    train(train_dataloader)
    accu_val = evaluate(valid_dataloader)
    if total_accu is not None and total_accu > accu_val:
        scheduler.step()
    else:
        total_accu = accu_val
    print("-" * 59)
    print(
        "| end of epoch {:3d} | time: {:5.2f}s | "
        "valid accuracy {:8.3f} ".format(
            epoch, time.time() - epoch_start_time, accu_val
        )
    )
    print("-" * 59) 

| epoch   1 |   500/ 1782 batches | accuracy    0.694
| epoch   1 |  1000/ 1782 batches | accuracy    0.856
| epoch   1 |  1500/ 1782 batches | accuracy    0.877
-----------------------------------------------------------
| end of epoch   1 | time: 11.29s | valid accuracy    0.886
-----------------------------------------------------------
| epoch   2 |   500/ 1782 batches | accuracy    0.898
| epoch   2 |  1000/ 1782 batches | accuracy    0.899
| epoch   2 |  1500/ 1782 batches | accuracy    0.906
-----------------------------------------------------------
| end of epoch   2 | time: 10.99s | valid accuracy    0.895
-----------------------------------------------------------
| epoch   3 |   500/ 1782 batches | accuracy    0.916
| epoch   3 |  1000/ 1782 batches | accuracy    0.913
| epoch   3 |  1500/ 1782 batches | accuracy    0.915
-----------------------------------------------------------
| end of epoch   3 | time: 10.97s | valid accuracy    0.894
-----------------------------------------------------------
| epoch   4 |   500/ 1782 batches | accuracy    0.930
| epoch   4 |  1000/ 1782 batches | accuracy    0.932
| epoch   4 |  1500/ 1782 batches | accuracy    0.929
-----------------------------------------------------------
| end of epoch   4 | time: 10.97s | valid accuracy    0.902
-----------------------------------------------------------
| epoch   5 |   500/ 1782 batches | accuracy    0.932
| epoch   5 |  1000/ 1782 batches | accuracy    0.933
| epoch   5 |  1500/ 1782 batches | accuracy    0.931
-----------------------------------------------------------
| end of epoch   5 | time: 10.92s | valid accuracy    0.902
-----------------------------------------------------------
| epoch   6 |   500/ 1782 batches | accuracy    0.933
| epoch   6 |  1000/ 1782 batches | accuracy    0.932
| epoch   6 |  1500/ 1782 batches | accuracy    0.935
-----------------------------------------------------------
| end of epoch   6 | time: 10.91s | valid accuracy    0.903
-----------------------------------------------------------
| epoch   7 |   500/ 1782 batches | accuracy    0.934
| epoch   7 |  1000/ 1782 batches | accuracy    0.933
| epoch   7 |  1500/ 1782 batches | accuracy    0.935
-----------------------------------------------------------
| end of epoch   7 | time: 10.90s | valid accuracy    0.903
-----------------------------------------------------------
| epoch   8 |   500/ 1782 batches | accuracy    0.935
| epoch   8 |  1000/ 1782 batches | accuracy    0.933
| epoch   8 |  1500/ 1782 batches | accuracy    0.935
-----------------------------------------------------------
| end of epoch   8 | time: 10.91s | valid accuracy    0.904
-----------------------------------------------------------
| epoch   9 |   500/ 1782 batches | accuracy    0.934
| epoch   9 |  1000/ 1782 batches | accuracy    0.934
| epoch   9 |  1500/ 1782 batches | accuracy    0.934
-----------------------------------------------------------
| end of epoch   9 | time: 10.90s | valid accuracy    0.904
-----------------------------------------------------------
| epoch  10 |   500/ 1782 batches | accuracy    0.934
| epoch  10 |  1000/ 1782 batches | accuracy    0.936
| epoch  10 |  1500/ 1782 batches | accuracy    0.933
-----------------------------------------------------------
| end of epoch  10 | time: 10.91s | valid accuracy    0.905
----------------------------------------------------------- 

print("Checking the results of test dataset.")
accu_test = evaluate(test_dataloader)
print("test accuracy {:8.3f}".format(accu_test)) 

Checking the results of test dataset.
test accuracy    0.907 

ag_news_label = {1: "World", 2: "Sports", 3: "Business", 4: "Sci/Tec"}
def predict(text, text_pipeline):
    with torch.no_grad():
        text = torch.tensor(text_pipeline(text))
        output = model(text, torch.tensor([0]))
        return output.argmax(1).item() + 1
ex_text_str = "MEMPHIS, Tenn. – Four days ago, Jon Rahm was \
 enduring the season’s worst weather conditions on Sunday at The \
 Open on his way to a closing 75 at Royal Portrush, which \
 considering the wind and the rain was a respectable showing. \
 Thursday’s first round at the WGC-FedEx St. Jude Invitational \
 was another story. With temperatures in the mid-80s and hardly any \
 wind, the Spaniard was 13 strokes better in a flawless round. \
 Thanks to his best putting performance on the PGA Tour, Rahm \
 finished with an 8-under 62 for a three-stroke lead, which \
 was even more impressive considering he’d never played the \
 front nine at TPC Southwind."
model = model.to("cpu")
print("This is a %s news" % ag_news_label[predict(ex_text_str, text_pipeline)]) 

This is a Sports news