---
license: mit
library_name: pytorch
tags:
- computer-vision
- image-classification
- efficientnet
- surgical-tools
- surgical-instruments
- binary-classification
datasets:
- joonhaim/hinged-state-classifier-crops
---

# hinged-state-classifier-efficientnet-b0

EfficientNet-B0 image classification model for surgical instrument state recognition.

## Task
Binary classification of hinged surgical instrument state:
- closed
- open

## Model details
- Architecture: EfficientNet-B0
- Framework: PyTorch
- Checkpoint: `best.pt`
- Input image size: 224 × 224

## Dataset
Trained on:
- `joonhaim/hinged-state-classifier-crops`

## Class mapping
- 0: closed
- 1: open

## Notes
This is a custom PyTorch checkpoint for classifying the state of hinged surgical instruments from cropped images.

The class order must match the order used during training.