metadata

library_name: keras
tags:
  - Image Classification
language:
  - en
metrics:
  - accuracy

cats-vs-dogs

Model Overview

The cats-vs-dogs model is a convolutional neural network (CNN) trained on the Cats vs Dogs dataset, a large set of images of cats and dogs.

Details

Size: 3,453,121 parameters
Model type: CNN
Optimizer: RMSprop
Number of Epochs:
Hardware: Tesla V4
Emissions: Not measured
Total Energy Consumption: Not measured

How to Use

!pip install huggingface_hub["tensorflow"] -q

# We are loading our Keras model from the Hub via the `huggingface_hub.from_pretrained_keras`
from huggingface_hub import from_pretrained_keras
import tensorflow as tf

model = from_pretrained_keras("AiresPucrs/cats-vs-dogs")
model.trainable = False
model.summary()

Intended Use

This model was created for research purposes only. We do not recommend any application of this model outside this scope.

Performance Metrics

Accuracy

Training Data

cats_vs_dogs dataset.

The dataset consists of a set of images of cats and dogs.

Details:

Homepage
Version: 1.0
Date Published: 5/9/2022
File Size:786.7 MB

Training hyperparameters

The following hyperparameters were used during training:

Hyperparameters	Value
name	RMSprop
learning_rate	9.999999747378752e-05
decay	0.0
rho	0.8999999761581421
momentum	0.0
epsilon	1e-07
centered	False
training_precision	float32

Limitations

We do not recommend using this model in real-world applications. It was solely developed for academic and educational purposes.

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

The cats-vs-dogs pre-trained model is under the Apache 2.0 License. The cats_vs_dogs Dataset is licensed under the Creative Commons(CC) License CC BY-NC-SA 4.0.

Model Plot

View Model Plot