Rathnavelu/indian-currency-cnn-yolo

Camera Frame → [YOLOv8-nano] → Detect & Localize Currency → [MobileNetV3-Small] → Classify Denomination

import torch
from torchvision import models, transforms
from PIL import Image

# Load model
model = models.mobilenet_v3_small()
model.classifier = torch.nn.Sequential(
    torch.nn.Linear(576, 256),
    torch.nn.Hardswish(),
    torch.nn.Dropout(0.3),
    torch.nn.Linear(256, 7)
)
checkpoint = torch.load("mobilenetv3_currency.pth", map_location="cpu")
model.load_state_dict(checkpoint['model_state_dict'])
model.eval()

# Preprocess
transform = transforms.Compose([
    transforms.Resize(256),
    transforms.CenterCrop(224),
    transforms.ToTensor(),
    transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225]),
])

# Predict
img = Image.open("your_currency_photo.jpg").convert("RGB")
input_tensor = transform(img).unsqueeze(0)
with torch.no_grad():
    output = model(input_tensor)
    class_names = ["₹10", "₹100", "₹20", "₹200", "₹2000", "₹50", "₹500"]
    prediction = class_names[output.argmax(1).item()]
    confidence = torch.softmax(output, 1).max().item()
    print(f"Detected: {prediction} ({confidence:.1%})")

from ultralytics import YOLO

model = YOLO("yolov8n_currency_best.pt")
results = model("currency_photo.jpg")
results[0].show()

import onnxruntime as ort
import numpy as np
from PIL import Image

# CNN Classifier
session = ort.InferenceSession("mobilenetv3_currency.onnx")
img = Image.open("currency.jpg").resize((224, 224))
img_array = np.array(img).astype(np.float32) / 255.0
img_array = (img_array - [0.485, 0.456, 0.406]) / [0.229, 0.224, 0.225]
input_data = img_array.transpose(2, 0, 1)[np.newaxis, ...]
outputs = session.run(None, {"input": input_data})
class_names = ["₹10", "₹100", "₹20", "₹200", "₹2000", "₹50", "₹500"]
print(f"Predicted: {class_names[np.argmax(outputs[0])]}")