Downloads · 30 days
4
9% of all-time downloads
cervical-cancer-vit
bineesh627/cervical-cancer-vit
cervical-cancer-vit is a machine learning model from bineesh627. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
This model is a Vision Transformer (ViT-B/16) trained to classify cervical cytology images into five categories representing different cell types.
All-time downloads
45
Public
Repo size
343 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pth343 MB · 100%
At a glance
- Model type
- vision-transformer
- Access
- Public
- Created
- Jan 5, 2026
- Updated
- Jan 5, 2026
- SHA
- b47fc644
Model card
From the Hugging Face model README
Cervical Cancer Image Classification (ViT)
Overview
This model is a Vision Transformer (ViT-B/16) trained to classify cervical cytology images into five categories representing different cell types.
Model Details
- Architecture: Vision Transformer (ViT-B/16)
- Input size: 224 × 224 RGB
- Framework: PyTorch
- Task: Multi-class image classification
Training Summary
- Transfer learning with frozen backbone
- Optimizer: AdamW
- Loss function: CrossEntropyLoss
- Epochs trained: 34
- Best validation accuracy: 93.09%
- Best checkpoint selected based on validation accuracy
Classes
- Dyskeratotic
- Koilocytotic
- Metaplastic
- Parabasal
- Superficial-Intermediate
Dataset
This model was trained using a cervical cancer image dataset hosted on Hugging Face:
https://huggingface.co/datasets/bineesh627/cervical-cancer-multimodal
Usage
from inference import predict
result = predict("sample.jpg")
print(result)
- Type
- vision-transformer
- Created
- Jan 5, 2026
- Updated
- Jan 5, 2026