metadata

language:
  - en
library_name: tf-keras
license: apache-2.0
metrics:
  - accuracy
pipeline_tag: image-classification

Digit-classifier

Model Overview

The digit-classifier model is used to recognize manuscript digits from 0 to 9.

Details

Size: 1,256,080 parameters
Model type: Convolutional neural network
Optimizer: tf.keras.optimizers.Adam(learning_rate=0.001)
Number of Epochs: 10
Batch size: 256
Hardware: Tesla V4
Emissions: Not measured
Total Energy Consumption: Not measured

How to Use

from huggingface_hub import from_pretrained_keras

model = from_pretrained_keras("AiresPucrs/digit-classifier")

classes = ['zero', 'one', 'two', 'three', 'four', 'five', 'six', 'seven', 'eight', 'nine']

Intended Use

This model was created for research purposes only. Specifically, it was designed to recognize manuscript digits from 0 to 9. We do not recommend any application of this model outside this scope.

Training Data

The model was trained with the MNIST digits classification dataset.

Cite as 🤗

@misc{teenytinycastle,
    doi = {10.5281/zenodo.7112065},
    url = {https://github.com/Nkluge-correa/teeny-tiny_castle},
    author = {Nicholas Kluge Corr{\^e}a},
    title = {Teeny-Tiny Castle},
    year = {2024},
    publisher = {GitHub},
    journal = {GitHub repository},
}

License

This model is licensed under the Apache License, Version 2.0.