You can deploy this model and start earning money today!

GustavoGomes7/
VisionNet-CIFAR10

Name: VisionNet-CIFAR10
Availability: InStock

keras

apache-2.0

Views

No views yet

VisionNet-CIFAR10 - Pretrained CNN Model for Image Classification

This repository contains a pretrained Convolutional Neural Network (CNN) for image classification on the CIFAR-10 dataset.

Download & Load the Model

To use the pretrained model, run the following code:

python

from huggingface_hub import hf_hub_download
from tensorflow.keras.models import load_model

# Download model
model_path = hf_hub_download(repo_id="GustavoGomes7/VisionNet-CIFAR10", filename="best_model.keras")

# Load model
model = load_model(model_path)

print("Model downloaded and loaded successfully!")

Model Performance

Metric	Value
Dataset	CIFAR-10 (10 classes, 60,000 images)
Test Accuracy	89.90%
Test Loss	0.5551
Best-performing classes	Automobile (F1-score 0.95), Ship (F1-score 0.94), Truck(F1-score 0.94)
Most challenging class	Cat (F1-score 0.80)

More Information

For the full project, check out the GitHub repository: GitHub - CNN CIFAR-10 Classifier