# CIFAR10-Prediction-In-Keras

**Repository Path**: jack1314/CIFAR10-Prediction-In-Keras

## Basic Information

- **Project Name**: CIFAR10-Prediction-In-Keras
- **Description**: This software visualizes CIFAR-10 image files label prediction results by a ResNet model or a CNN model.
- **Primary Language**: Unknown
- **License**: MIT
- **Default Branch**: master
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 0
- **Forks**: 0
- **Created**: 2020-07-10
- **Last Updated**: 2021-11-03

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

# CIFAR-10 Prediction In Keras

[![https://gyazo.com/308fbe9513a88fc7e943b50f8ecf0598](https://i.gyazo.com/308fbe9513a88fc7e943b50f8ecf0598.gif)](https://gyazo.com/308fbe9513a88fc7e943b50f8ecf0598)

'keras_cifar10_prediction.ipynb' predict a webcam photo by a neaural network that is trained by CIFAR-10 datas.  

[![https://gyazo.com/b209037ac23ee815069ca28214db0669](https://i.gyazo.com/b209037ac23ee815069ca28214db0669.png)](https://gyazo.com/b209037ac23ee815069ca28214db0669)

'keras_cifar10_prediction.ipynb' visualizes CIFAR-10 image files label prediction results by a ResNet model or a CNN model. 
A fail prediction is displayed red text. left side text is a fail prediction, right side is a correct label.

## How to use

1. clone this repository using `git`:

```sh
git clone https://github.com/uchidama/CIFAR10-Prediction-In-Keras.git
```

2. `cd` to the folder and run jupyter notebook:
```sh
cd CIFAR10-Prediction-In-Keras
jupyter notebook
```

3. click 'keras_cifar10_prediction.ipynb' and run.

## Installation

This software using Keras.
- [Keras installation instructions](https://github.com/keras-team/keras#installation).

If you want to run without to think keras and backend deeplearning frameworks, enter this command.   
```sh
pip install tensorflow==1.4.1
pip install keras==2.1.2
```

Then, enter this command to install other using python packages.
```sh
pip install -r requirements.txt
```

## Model Files

- cifar10_ResNet20v1_model.092.h5 is generated by [cifar10_resnet.py in keras examples](https://github.com/keras-team/keras/blob/master/examples/cifar10_resnet.py).  
- keras_cifar10_trained_model.h5 is generated by [cifar10_cnn.py in keras examples](https://github.com/keras-team/keras/blob/master/examples/cifar10_cnn.py).  

## License

[MIT](LICENSE.md)