Nepali Banknote Models
A collection of models for the bankNotes-OCR pipeline — a hierarchical 2-stage banknote retrieval system for Nepalese banknotes.
Pipeline Overview
Query Image
├── Stage 0: ConvNeXt Binary Classifier (banknote vs. random)
├── Stage 1a: YOLO Denomination Detector (11 denominations)
├── Stage 1b: RFDETR + Swin Signature Classifier (20 governors)
└── Stage 2: DinoV2-Base patch embeddings + Qdrant vector search
Model 1: ConvNeXt Tiny — Binary Classifier (best_model.pth)
Stage 0: Determines if an image is a banknote or a random image.
| Architecture | convnext_tiny (torchvision) |
| Classes | 2: random (0), banknote (1) |
| Input size | 224x224 RGB |
| Normalization | ImageNet mean=[0.485,0.456,0.406], std=[0.229,0.224,0.225] |
| Weight size | ~319 MB |
from huggingface_hub import hf_hub_download
import torch
from src.models.resnet import get_model
model_path = hf_hub_download("MANTRAIDEAS1/nepali-banknote-models", "best_model.pth")
model = get_model(model_name="convnext_tiny", num_classes=2, pretrained=False)
checkpoint = torch.load(model_path, map_location="cpu", weights_only=False)
model.load_state_dict(checkpoint["model_state_dict"])
model.eval()
Model 2: YOLO — Denomination Detector (best.pt)
Stage 1a: Detects and classifies the denomination of a banknote.
| Architecture | YOLO (Ultralytics) |
| Classes (11) | 1, 2, 5, 10, 20, 25, 50, 100, 250, 500, 1000 |
| Input size | 640x640 RGB |
| Weight size | ~113 MB |
from ultralytics import YOLO
from huggingface_hub import hf_hub_download
model_path = hf_hub_download("MANTRAIDEAS1/nepali-banknote-models", "best.pt")
model = YOLO(str(model_path))
results = model("image.jpg", conf=0.5, device="cpu")
Model 3: RFDETR-Large — Signature Detector (detector.pth)
Stage 1b: Detects the governor signature region on a banknote.
| Architecture | RFDETRLarge (rfdetr library) |
| Detection threshold | 0.3 |
| Weight size | ~128 MB |
from rfdetr import RFDETRLarge
from huggingface_hub import hf_hub_download
model_path = hf_hub_download("MANTRAIDEAS1/nepali-banknote-models", "detector.pth")
detector = RFDETRLarge.from_checkpoint(model_path, device="cpu")
Model 4: Swin-Base — Signature Classifier (classifier.pth)
Stage 1b: Classifies a cropped signature region into one of 20 Nepali governors.
| Architecture | swin_base_patch4_window7_224 (timm) |
| Classes | 20 Nepali governors |
| Input size | 224x224 RGB |
| Normalization | ImageNet mean=[0.485,0.456,0.406], std=[0.229,0.224,0.225] |
| Weight size | ~331 MB |
Governor Classes
Bharat_Raj_Pandey, Bhekh_Bahadur_Thapa, Bijaynath_Bhattarai,
Chiranjibi_Nepal, Dipendra_Purush_Dhakal, Ganesh_Bahadur_Thapa,
Hari_Shankar_Tripathi, Himalaya_SJB_Rana, Janak_Raj_Pandey,
Kalyan_Bikram_Adhikari, Krishna_Bahadur_Manandhar, Kul_Sekhar_Sharma,
Laxmi_Nath_Gautam, Maha_Prasad_Adhikari, Narendra_Raj_Pandey,
Pradhumna_Lal_Rajbhandari, Satyendra_Pyara_Shrestha,
Tilak_Bahadur_Rawal, Yadav_Prasad_Pant, Yubaraj_Khatiwada
import timm
import torch
from huggingface_hub import hf_hub_download
model_path = hf_hub_download("MANTRAIDEAS1/nepali-banknote-models", "classifier.pth")
model = timm.create_model("swin_base_patch4_window7_224", pretrained=False, num_classes=20)
model.load_state_dict(torch.load(model_path, map_location="cpu"))
model.eval()
Additional Model (not in this repo)
| Model | Source | Purpose |
|---|---|---|
| DinoV2-Base | facebook/dinov2-base | Stage 2 — patch-level embeddings for visual similarity search |
License
MIT