Breaking News: Grepper is joining You.com. Read the official announcement!

How to train your model with PyTorch

Stan Mtete answered on June 19, 2023 Popularity 8/10 Helpfulness 3/10

answer How to train your model with PyTorch

How to train your model with PyTorch

Comment

import torch
import torch.nn as nn
import torch.optim as optim
from torchtext.data import Field, TabularDataset, BucketIterator

# Step 1: Prepare the data
text_field = Field(tokenize='spacy', lower=True)
label_field = Field(sequential=False, use_vocab=False)

train_data, test_data = TabularDataset.splits(
    path='path_to_dataset_folder',
    train='train.csv',
    test='test.csv',
    format='csv',
    fields=[('text', text_field), ('label', label_field)]
)

text_field.build_vocab(train_data)

# Step 2: Define the model
class TextClassifier(nn.Module):
    def __init__(self, vocab_size, embedding_dim, hidden_dim, output_dim):
        super(TextClassifier, self).__init__()
        self.embedding = nn.Embedding(vocab_size, embedding_dim)
        self.fc = nn.Linear(embedding_dim, hidden_dim)
        self.output = nn.Linear(hidden_dim, output_dim)

    def forward(self, x):
        embedded = self.embedding(x)
        hidden = torch.mean(embedded, dim=1)
        out = torch.relu(self.fc(hidden))
        return self.output(out)

vocab_size = len(text_field.vocab)
embedding_dim = 100
hidden_dim = 256
output_dim = 2

model = TextClassifier(vocab_size, embedding_dim, hidden_dim, output_dim)

# Step 3: Define loss function and optimizer
criterion = nn.CrossEntropyLoss()
optimizer = optim.Adam(model.parameters())

# Step 4: Train the model
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
model.to(device)
train_iterator, test_iterator = BucketIterator.splits(
    (train_data, test_data),
    batch_size=32,
    device=device
)

num_epochs = 10
for epoch in range(num_epochs):
    model.train()
    for batch in train_iterator:
        optimizer.zero_grad()
        text = batch.text
        labels = batch.label
        predictions = model(text).squeeze(1)
        loss = criterion(predictions, labels)
        loss.backward()
        optimizer.step()

# Step 5: Evaluate the model
model.eval()
correct = 0
total = 0
with torch.no_grad():
    for batch in test_iterator:
        text = batch.text
        labels = batch.label
        predictions = model(text).squeeze(1)
        predicted_labels = torch.argmax(predictions, dim=1)
        correct += (predicted_labels == labels).sum().item()
        total += labels.size(0)

accuracy = correct / total
print(f"Accuracy: {accuracy * 100}%")

Popularity 8/10 Helpfulness 3/10 Language python

Source: chat.openai.com

Tags: model python pytorch

Link to this answer
Share Copy Link

Contributed on Jun 19 2023

Stan Mtete

0 Answers Avg Quality 2/10

How to train your model with PyTorch

Contents

More Related Answers

How to train your model with PyTorch

Grepper

Documentation

Social

Legal

Contact

Oops, You will need to install Grepper and log-in to perform this action.