File size: 2,880 Bytes
5787f5d a8449c1 5787f5d a8449c1 5787f5d a8449c1 5787f5d a8449c1 5787f5d a8449c1 5787f5d a8449c1 5787f5d a8449c1 5787f5d a8449c1 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 |
import torch
import torch.nn as nn
from torchvision import models, datasets, transforms
from torch.utils.data import DataLoader
from transformers import ViTForImageClassification, ViTFeatureExtractor
class ToxicImageClassifier(nn.Module):
def __init__(self, num_classes=2):
super(ToxicImageClassifier, self).__init__()
# ResNet50
self.resnet = models.resnet50(pretrained=True)
num_features = self.resnet.fc.in_features
self.resnet.fc = nn.Linear(num_features, num_classes)
# Vision Transformer
self.vit = ViTForImageClassification.from_pretrained(
'google/vit-base-patch16-224',
num_labels=num_classes,
ignore_mismatched_sizes=True
)
self.feature_extractor = ViTFeatureExtractor.from_pretrained(
'google/vit-base-patch16-224'
)
def forward(self, x, model_type='resnet'):
if model_type == 'resnet':
return self.resnet(x)
else: # vit
return self.vit(x).logits
def train_model(model, train_loader, criterion, optimizer, device):
model.train()
running_loss = 0.0
correct = 0
total = 0
for inputs, labels in train_loader:
inputs, labels = inputs.to(device), labels.to(device)
optimizer.zero_grad()
outputs = model(inputs)
loss = criterion(outputs, labels)
loss.backward()
optimizer.step()
running_loss += loss.item()
_, predicted = torch.max(outputs.data, 1)
total += labels.size(0)
correct += (predicted == labels).sum().item()
epoch_loss = running_loss / len(train_loader)
epoch_acc = 100 * correct / total
return epoch_loss, epoch_acc
def get_data_loaders(batch_size=32):
transform = transforms.Compose([
transforms.Resize((224, 224)),
transforms.ToTensor(),
transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])
])
train_dataset = datasets.ImageFolder('data/train', transform=transform)
test_dataset = datasets.ImageFolder('data/test', transform=transform)
train_loader = DataLoader(train_dataset, batch_size=batch_size, shuffle=True)
test_loader = DataLoader(test_dataset, batch_size=batch_size)
return train_loader, test_loader
# Example training script (run separately or comment out)
"""
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
model = ToxicImageClassifier().to(device)
criterion = nn.CrossEntropyLoss()
optimizer = torch.optim.Adam(model.parameters(), lr=0.001)
train_loader, test_loader = get_data_loaders()
for epoch in range(10): # Adjust epochs as needed
loss, acc = train_model(model, train_loader, criterion, optimizer, device)
print(f"Epoch {epoch+1}: Loss = {loss:.4f}, Accuracy = {acc:.2f}%")
torch.save(model.state_dict(), "toxic_classifier.pth")
""" |