File size: 6,388 Bytes
233caeb |
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 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 |
"""
Training script for CIFAR-10 CNN
"""
import os
import torch
import torch.nn as nn
import torch.optim as optim
from tqdm import tqdm
import matplotlib.pyplot as plt
import config
from model import get_model, count_parameters
from data_loader import get_data_loaders
from utils import save_checkpoint, load_checkpoint, plot_training_history
def train_epoch(model, train_loader, criterion, optimizer, device):
"""
Train the model for one epoch
Args:
model: PyTorch model
train_loader: Training data loader
criterion: Loss function
optimizer: Optimizer
device: Device to train on
Returns:
tuple: (average_loss, accuracy)
"""
model.train()
running_loss = 0.0
correct = 0
total = 0
pbar = tqdm(train_loader, desc='Training')
for inputs, labels in pbar:
inputs, labels = inputs.to(device), labels.to(device)
# Zero the parameter gradients
optimizer.zero_grad()
# Forward pass
outputs = model(inputs)
loss = criterion(outputs, labels)
# Backward pass and optimize
loss.backward()
optimizer.step()
# Statistics
running_loss += loss.item()
_, predicted = outputs.max(1)
total += labels.size(0)
correct += predicted.eq(labels).sum().item()
# Update progress bar
pbar.set_postfix({
'loss': f'{running_loss / (pbar.n + 1):.4f}',
'acc': f'{100. * correct / total:.2f}%'
})
epoch_loss = running_loss / len(train_loader)
epoch_acc = 100. * correct / total
return epoch_loss, epoch_acc
def validate(model, test_loader, criterion, device):
"""
Validate the model
Args:
model: PyTorch model
test_loader: Test data loader
criterion: Loss function
device: Device to validate on
Returns:
tuple: (average_loss, accuracy)
"""
model.eval()
running_loss = 0.0
correct = 0
total = 0
with torch.no_grad():
pbar = tqdm(test_loader, desc='Validation')
for inputs, labels in pbar:
inputs, labels = inputs.to(device), labels.to(device)
# Forward pass
outputs = model(inputs)
loss = criterion(outputs, labels)
# Statistics
running_loss += loss.item()
_, predicted = outputs.max(1)
total += labels.size(0)
correct += predicted.eq(labels).sum().item()
# Update progress bar
pbar.set_postfix({
'loss': f'{running_loss / (pbar.n + 1):.4f}',
'acc': f'{100. * correct / total:.2f}%'
})
epoch_loss = running_loss / len(test_loader)
epoch_acc = 100. * correct / total
return epoch_loss, epoch_acc
def train():
"""
Main training function
"""
# Create directories
os.makedirs(config.CHECKPOINT_DIR, exist_ok=True)
os.makedirs(config.PLOTS_DIR, exist_ok=True)
# Get data loaders
print("Loading CIFAR-10 dataset...")
train_loader, test_loader = get_data_loaders()
print(f"Training samples: {len(train_loader.dataset)}")
print(f"Test samples: {len(test_loader.dataset)}")
# Create model
print(f"\nCreating model on device: {config.DEVICE}")
model = get_model(num_classes=config.NUM_CLASSES, device=config.DEVICE)
print(f"Model parameters: {count_parameters(model):,}")
# Loss function and optimizer
criterion = nn.CrossEntropyLoss()
optimizer = optim.SGD(
model.parameters(),
lr=config.LEARNING_RATE,
momentum=config.MOMENTUM,
weight_decay=config.WEIGHT_DECAY
)
# Learning rate scheduler
scheduler = None
if config.USE_SCHEDULER:
scheduler = optim.lr_scheduler.StepLR(
optimizer,
step_size=config.SCHEDULER_STEP_SIZE,
gamma=config.SCHEDULER_GAMMA
)
# Training history
history = {
'train_loss': [],
'train_acc': [],
'val_loss': [],
'val_acc': []
}
best_acc = 0.0
start_epoch = 0
# Training loop
print(f"\nStarting training for {config.EPOCHS} epochs...")
for epoch in range(start_epoch, config.EPOCHS):
print(f"\nEpoch {epoch + 1}/{config.EPOCHS}")
print("-" * 50)
# Train
train_loss, train_acc = train_epoch(
model, train_loader, criterion, optimizer, config.DEVICE
)
# Validate
val_loss, val_acc = validate(
model, test_loader, criterion, config.DEVICE
)
# Update learning rate
if scheduler:
scheduler.step()
current_lr = scheduler.get_last_lr()[0]
print(f"Learning rate: {current_lr:.6f}")
# Save history
history['train_loss'].append(train_loss)
history['train_acc'].append(train_acc)
history['val_loss'].append(val_loss)
history['val_acc'].append(val_acc)
# Print epoch summary
print(f"\nEpoch {epoch + 1} Summary:")
print(f"Train Loss: {train_loss:.4f} | Train Acc: {train_acc:.2f}%")
print(f"Val Loss: {val_loss:.4f} | Val Acc: {val_acc:.2f}%")
# Save best model
if val_acc > best_acc:
best_acc = val_acc
save_checkpoint(
model, optimizer, epoch, val_acc,
config.BEST_MODEL_PATH
)
print(f"✓ Best model saved with accuracy: {best_acc:.2f}%")
# Save last model
save_checkpoint(
model, optimizer, epoch, val_acc,
config.LAST_MODEL_PATH
)
# Plot training history
plot_training_history(history, config.PLOTS_DIR)
print("\n" + "=" * 50)
print(f"Training completed!")
print(f"Best validation accuracy: {best_acc:.2f}%")
print("=" * 50)
if __name__ == '__main__':
train()
|