Spaces:
Runtime error
Runtime error
File size: 6,529 Bytes
2d30bad | 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 | import os
import time
from pathlib import Path
import torch
import torch.nn as nn
from torch.utils.data import DataLoader, random_split
from torchvision import datasets, transforms, models
# ---------------------------------------------------------------------------
# Paths
# ---------------------------------------------------------------------------
BASE_DIR = Path(__file__).resolve().parents[1]
CROPS_DIR = BASE_DIR / "data" / "crops"
MODELS_DIR = BASE_DIR / "models"
MODELS_DIR.mkdir(exist_ok=True)
MODEL_PATH = MODELS_DIR / "slot_classifier.pth"
# ---------------------------------------------------------------------------
# Config
# ---------------------------------------------------------------------------
IMG_SIZE = 224
BATCH_SIZE = 32
EPOCHS = 10
LR = 1e-4
VAL_SPLIT = 0.2
DEVICE = torch.device("cuda" if torch.cuda.is_available() else "cpu")
# ---------------------------------------------------------------------------
# Transforms
# ---------------------------------------------------------------------------
train_transforms = transforms.Compose([
transforms.Resize((IMG_SIZE, IMG_SIZE)),
transforms.RandomHorizontalFlip(),
transforms.RandomVerticalFlip(),
transforms.ColorJitter(brightness=0.3, contrast=0.3, saturation=0.2),
transforms.ToTensor(),
transforms.Normalize([0.485, 0.456, 0.406],
[0.229, 0.224, 0.225]),
])
val_transforms = transforms.Compose([
transforms.Resize((IMG_SIZE, IMG_SIZE)),
transforms.ToTensor(),
transforms.Normalize([0.485, 0.456, 0.406],
[0.229, 0.224, 0.225]),
])
# ---------------------------------------------------------------------------
# Dataset
# ---------------------------------------------------------------------------
def build_loaders():
full_dataset = datasets.ImageFolder(CROPS_DIR)
print(f"Classes : {full_dataset.classes}")
print(f"Total : {len(full_dataset)} images")
val_size = int(len(full_dataset) * VAL_SPLIT)
train_size = len(full_dataset) - val_size
train_ds, val_ds = random_split(
full_dataset,
[train_size, val_size],
generator=torch.Generator().manual_seed(42),
)
# Apply correct transforms to each split
train_ds.dataset.transform = train_transforms
val_ds.dataset.transform = val_transforms
train_loader = DataLoader(train_ds, batch_size=BATCH_SIZE, shuffle=True, num_workers=0)
val_loader = DataLoader(val_ds, batch_size=BATCH_SIZE, shuffle=False, num_workers=0)
print(f"Train : {train_size} | Val : {val_size}")
return train_loader, val_loader, full_dataset.classes
# ---------------------------------------------------------------------------
# Model
# ---------------------------------------------------------------------------
def build_model(num_classes: int = 2) -> nn.Module:
model = models.mobilenet_v2(weights=models.MobileNet_V2_Weights.DEFAULT)
# Freeze all base layers
for param in model.parameters():
param.requires_grad = False
# Replace classifier head
in_features = model.classifier[1].in_features
model.classifier = nn.Sequential(
nn.Dropout(0.3),
nn.Linear(in_features, num_classes),
)
return model.to(DEVICE)
# ---------------------------------------------------------------------------
# Train / Eval loops
# ---------------------------------------------------------------------------
def train_one_epoch(model, loader, criterion, optimizer):
model.train()
total_loss = 0.0
correct = 0
total = 0
for images, labels in loader:
images, labels = images.to(DEVICE), labels.to(DEVICE)
optimizer.zero_grad()
outputs = model(images)
loss = criterion(outputs, labels)
loss.backward()
optimizer.step()
total_loss += loss.item() * images.size(0)
preds = outputs.argmax(dim=1)
correct += (preds == labels).sum().item()
total += labels.size(0)
return total_loss / total, correct / total
def evaluate(model, loader, criterion):
model.eval()
total_loss = 0.0
correct = 0
total = 0
with torch.no_grad():
for images, labels in loader:
images, labels = images.to(DEVICE), labels.to(DEVICE)
outputs = model(images)
loss = criterion(outputs, labels)
total_loss += loss.item() * images.size(0)
preds = outputs.argmax(dim=1)
correct += (preds == labels).sum().item()
total += labels.size(0)
return total_loss / total, correct / total
# ---------------------------------------------------------------------------
# Main
# ---------------------------------------------------------------------------
def main():
print(f"Device : {DEVICE}")
print(f"Epochs : {EPOCHS} | Batch : {BATCH_SIZE} | LR : {LR}\n")
train_loader, val_loader, classes = build_loaders()
model = build_model(num_classes=len(classes))
criterion = nn.CrossEntropyLoss()
optimizer = torch.optim.Adam(
filter(lambda p: p.requires_grad, model.parameters()),
lr=LR,
)
scheduler = torch.optim.lr_scheduler.StepLR(optimizer, step_size=4, gamma=0.5)
best_val_acc = 0.0
for epoch in range(1, EPOCHS + 1):
t0 = time.time()
train_loss, train_acc = train_one_epoch(model, train_loader, criterion, optimizer)
val_loss, val_acc = evaluate(model, val_loader, criterion)
scheduler.step()
elapsed = time.time() - t0
marker = " *" if val_acc > best_val_acc else ""
print(
f"Epoch {epoch:02d}/{EPOCHS} | "
f"Train loss {train_loss:.4f} acc {train_acc:.4f} | "
f"Val loss {val_loss:.4f} acc {val_acc:.4f} | "
f"{elapsed:.1f}s{marker}"
)
if val_acc > best_val_acc:
best_val_acc = val_acc
torch.save({
"epoch" : epoch,
"model_state": model.state_dict(),
"classes" : classes,
"val_acc" : val_acc,
}, MODEL_PATH)
print(f"\nBest val accuracy : {best_val_acc:.4f}")
print(f"Model saved to : {MODEL_PATH}")
if __name__ == "__main__":
main() |