Downloads · 30 days
9
13% of all-time downloads
dementia
dhineshkmar/dementia
dementia is a image classification model from dhineshkmar. Use it when you need a label for an image. The card lists the license as mit.
This model detects dementia from brain MRI scans.
All-time downloads
68
Public
Repo size
39.7 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.h539.7 MB · 100%
At a glance
- Task
- Image Classification
- License
- mit
- Model type
- efficientnet
- Access
- Public
- Created
- Nov 24, 2025
- Updated
- Nov 24, 2025
- SHA
- c152e9c0
Model card
From the Hugging Face model README
Dementia Detection Model
This model detects dementia from brain MRI scans.
Model Details
- Architecture: EFFICIENTNET
- Task: Image Classification
- Classes: 4
- Input Size: 128x128
Labels
- 0: Non-Demented
- 1: Very-Mild-Demented
- 2: Mild-Demented
- 3: Moderate-Demented
Usage
from transformers import AutoFeatureExtractor, AutoModelForImageClassification
from PIL import Image
model_name = "dhineshkmar/dementia"
feature_extractor = AutoFeatureExtractor.from_pretrained(model_name)
model = AutoModelForImageClassification.from_pretrained(model_name)
image = Image.open("brain_scan.jpg")
inputs = feature_extractor(images=image, return_tensors="pt")
outputs = model(**inputs)
predicted_class = outputs.logits.argmax(-1).item()
Training
Trained on brain MRI scan dataset for dementia detection.
- Task
- Image Classification
- Type
- efficientnet
- License
- mit
- Created
- Nov 24, 2025
- Updated
- Nov 24, 2025