Downloads · 30 days
0
computer-vision-cifar-10
mestrevh/computer-vision-cifar-10
computer-vision-cifar-10 is a image classification model from mestrevh. Use it when you need a label for an image. The card lists the license as apache-2.0.
This model is a Vision Transformer (ViT) fine-tuned on the CIFAR-10 dataset for image classification.
Access
Public
Updated Mar 9, 2025
Repo size
—
Likes
0
Public
Repo makeup
Click a slice to open those files.
Other1.5 KB · 65%
At a glance
- Task
- Image Classification
- License
- apache-2.0
- Access
- Public
- Created
- Mar 9, 2025
- Updated
- Mar 9, 2025
- SHA
- f83dd959
Model card
From the Hugging Face model README
Vision Transformer Fine-tuned on CIFAR-10
This model is a Vision Transformer (ViT) fine-tuned on the CIFAR-10 dataset for image classification.
Model Description
The model was trained on the CIFAR-10 dataset, which consists of 60,000 32x32 color images in 10 classes, with 6,000 images per class. The fine-tuning was performed on the pretrained ViT base model.
Intended Use
This model is intended for image classification tasks.
How to Use
from transformers import pipeline
classifier = pipeline('image-classification', model='your-username/your-model-name')
results = classifier('path/to/your/image.jpg')
print(results)
- Task
- Image Classification
- License
- apache-2.0
- Created
- Mar 9, 2025
- Updated
- Mar 9, 2025