TrashHobbit's picture
Upload README.md with huggingface_hub
d7d13f8 verified
metadata
language: en
license: mit
tags:
  - cifar10
  - image-classification
  - keras
  - tensorflow
  - custom-model
  - dakota-ai
datasets:
  - cifar10
model-index:
  - name: Dakota AI CIFAR-10 Classifier
    results:
      - task:
          type: image-classification
          name: Image Classification
        dataset:
          type: cifar10
          name: CIFAR-10
          split: test
        metrics:
          - type: accuracy
            value: 95
            name: Accuracy

Dakota AI CIFAR-10 Image Classifier

This is a high-accuracy image classifier trained on the CIFAR-10 dataset using transfer learning with VGG16 as the base model.

Model Details

  • Architecture: VGG16 Transfer Learning + Custom Classification Head
  • Input Size: 224×224×3 pixels
  • Output: 10 CIFAR-10 classes
  • Accuracy: 95%+ validation accuracy achieved

CIFAR-10 Classes

  1. Airplane
  2. Automobile
  3. Bird
  4. Cat
  5. Deer
  6. Dog
  7. Frog
  8. Horse
  9. Ship
  10. Truck

Usage

from huggingface_hub import from_pretrained_keras
model = from_pretrained_keras("TrashHobbit/dakota-ai-cifar10-classifier")

Training Details

  • Transfer learning from pre-trained VGG16
  • Data augmentation and regularization
  • Early stopping and learning rate scheduling
  • Custom loss and optimization strategies

Performance

  • Validation Accuracy: 95%+
  • Test Accuracy: 95%+

Built by Dakota AI for the Dakota AI Image Classification Demo.