Aller au contenu
ModelPrésentéExterne
Télécharger

SNAIC Week4 SmartCart

educational-use-only

Sourcehuggingface.co/Hongming111/SNAIC_Week4_SmartCart/tree/68df23dc37ab76df149dd34b5925a8e6e4efc41d
TypeOtherVersionDetector v0CClasse

Source du modèle

Type
Other
Taille du fichier
10,4 KB–22,7 MB
Version
vDetector v0
Mis à jour
22 oct. 2026
Source
Hugging Face

Description de la source

SmartCart SG — trained bundle (SNAIC Week 4 Capstone)

Trained artifacts for a self-checkout computer-vision pipeline (detect -> recognize -> price -> receipt) built on a home-grown Singapore grocery dataset. Source code and full writeup: hongming111/SNAIC_Week4_SmartCart.

Powers the companion Space: Hongming111/SNAIC_Week4_SmartCart.

Contents

FilePurpose
detector.pt, detector_v0.ptYOLO11 product detector (basket-hardened / earlier version)
FastSAM-s.ptFastSAM "segment everything" proposals for Basket mode
head.pt, head.onnx, head.int8.onnx25-way recognition head on frozen DINOv2 features (PyTorch / ONNX / quantized)
gallery_index.npy, gallery_meta.csvDINOv2 embedding gallery used for open-set gating
catalog_prices.csvReal median FairPrice SGD prices per class
confidence_threshold.jsonCalibrated serving threshold (0.6, held-out crop split)
labels.csv, manifest.json, crops/, crops_manifest.csv, crops_train.csvTraining/label provenance
decisive_lift_table.csv, lift_table.csv, lift_table_vs_real_photo.csv, per_class_metrics.csv, error_report.mdEvaluation and augmentation-lift measurements

Headline results

  • Detection: YOLO11n, mAP50-95 0.76; basket-hardened retrain: real 5-product basket 0 -> 7 boxes.
  • Recognition: 25-way linear head on frozen DINOv2, 94% validation (crop-aware).
  • Serving (head.onnx/head.int8.onnx): 76.5% on 17 held-out real photos, 96.2% on held-out detector crops; ONNX parity 1.4e-6; int8 = 10.6 KB.

License / usage restriction

Educational use only. Product studio images/prices originate from FairPrice/NTUC, collected under fair-dealing/educational use for coursework — do not use this repo or its contents commercially or redistribute the dataset. See the linked LICENSE for full terms.

Sources

1 source
Hugging FacePrincipalVersion 68df23dc37ab76df149dd34b5925a8e6e4efc41d
huggingface.co/Hongming111/SNAIC_Week4_SmartCart/tree/68df23dc37ab76df149dd34b5925a8e6e4efc41d

Vérifié 22 oct.

Artefacts du modèle

7 artefacts

detector_v0.pt

pt · 5,22 MB · SHA-256 78cb5e1cd241…25eb · Hugging Face

Télécharger

detector.pt

pt · 5,22 MB · SHA-256 90fa5bff4ff5…4115 · Hugging Face

Télécharger

FastSAM-s.pt

pt · 22,7 MB · SHA-256 c9f78716a81c…0844 · Hugging Face

Télécharger

head_v2.pt

pt · 39,0 KB · SHA-256 f16dc0a46546…9ed9 · Hugging Face

Télécharger

head.int8.onnx

onnx · 10,4 KB · SHA-256 6039c67ad68f…4fe6 · Hugging Face

Télécharger

head.onnx

onnx · 37,8 KB · SHA-256 72e5cb34a0fc…91be · Hugging Face

Télécharger

head.pt

pt · 39,0 KB · SHA-256 e618f0b9e59f…4cf3 · Hugging Face

Télécharger

Extraits de sources

2 extraits
Readme5 aoûthuggingface.co/Hongming111/SNAIC_Week4_SmartCart

--- license: other license_name: educational-use-only license_link: https://github.com/hongming111/SNAIC_Week4_SmartCart/blob/main/LICENSE tags: - computer-vision - object-detection - image-classification - gradio - yolo - dinov2 - onnx --- # SmartCart SG — trained bundle (SNAIC Week 4 Capstone) Trained artifacts for a self-checkout computer-vision pipeline (detect -> recognize -> price -> receipt) built on a home-grown Singapore grocery dataset. Source code and full writeup: [hongming111/SNAIC_Week4_SmartCart](https://github.com/hongming111/SNAIC_Week4_SmartCart). Powers the companion Space: [Hongming111/SNAIC_Week4_SmartCart](https://huggingface.co/spaces/Hongming111/SNAIC_Week4_SmartCart). ## Contents | File | Purpose | |---|---| | `detector.pt`, `detector_v0.pt` | YOLO11 product detector (basket-hardened / earlier version) | | `FastSAM-s.pt` | FastSAM "segment everything" proposals for Basket mode | | `head.pt`, `head.onnx`, `head.int8.onnx` | 25-way recognition head on frozen DINOv2 features (PyTorch / ONNX / quantized) | | `gallery_index.npy`, `gallery_meta.csv` | DINOv2 embedding gallery used for open-set gating | | `catalog_prices.csv` | Real median FairPrice SGD prices per class | | `confidence_threshold.json` | Calibrated serving threshold (0.6, held-out crop split) | | `labels.csv`, `manifest.json`, `crops/`, `crops_manifest.csv`, `crops_train.csv` | Training/label provenance | | `decisive_lift_table.csv`, `lift_table.csv`, `lift_table_vs_real_photo.csv`, `per_class_metrics.csv`, `error_report.md` | Evaluation and augmentation-lift measurements | ## Headline results - Detection: YOLO11n, mAP50-95 **0.76**; basket-hardened retrain: real 5-product basket 0 -> 7 boxes. - Recognition: 25-way linear head on frozen DINOv2, **94%** validation (crop-aware). - Serving (`head.onnx`/`head.int8.onnx`): **76.5%** on 17 held-out real photos, **96.2%** on held-out detector crops; ONNX parity 1.4e-6; int8 = 10.6 KB. ## License / usage restriction **Educational use only.** Product studio images/prices originate from FairPrice/NTUC, collected under fair-dealing/educational use for coursework — **do not use this repo or its contents commercially or redistribute the dataset.** See the linked LICENSE for full terms.

Note5 aoûthuggingface.co/Hongming111/SNAIC_Week4_SmartCart

Source context: 0 downloads · 0 likes · Pipeline image-classification · Repo Hongming111/SNAIC_Week4_SmartCart