https://github.com/aidinhamedi/ai-mnist-advanced-model
This project uses an AI model trained on the MNIST dataset to predict handwritten numbers with img noise.
https://github.com/aidinhamedi/ai-mnist-advanced-model
ai cnn-classification cnn-keras convolutional-neural-networks deep-learning keras machine-learning mnist model neural-network tensorflow training
Last synced: 2 months ago
JSON representation
This project uses an AI model trained on the MNIST dataset to predict handwritten numbers with img noise.
- Host: GitHub
- URL: https://github.com/aidinhamedi/ai-mnist-advanced-model
- Owner: AidinHamedi
- License: mit
- Created: 2023-08-08T14:47:21.000Z (almost 2 years ago)
- Default Branch: main
- Last Pushed: 2023-11-02T18:39:38.000Z (over 1 year ago)
- Last Synced: 2024-11-26T15:50:20.366Z (7 months ago)
- Topics: ai, cnn-classification, cnn-keras, convolutional-neural-networks, deep-learning, keras, machine-learning, mnist, model, neural-network, tensorflow, training
- Language: Jupyter Notebook
- Homepage:
- Size: 202 MB
- Stars: 2
- Watchers: 2
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
- Code of conduct: CODE_OF_CONDUCT.md
Awesome Lists containing this project
README
# Ai-MNIST-Advanced-model
### This project uses an AI model trained on the MNIST dataset to predict handwritten numbers with noise(real world data).
> **Warning**\
> Please note that this model is optimized for predicting very noisy images. As a result, it may not perform with very high accuracy on the standard MNIST validation data. Keep this in mind when evaluating the model’s
> performance.
## Release
> ### Newest release 📃
> #### [Go to newest release](https://github.com/Aydinhamedi/Ai-MNIST-Advanced-model/releases/tag/V0.3.6)
> ### Examples 📚
> #### [Go to example](https://github.com/Aydinhamedi/Ai-MNIST-Advanced-model/blob/main/TR.md)
## Data Processing
The data processing pipeline is optimized to handle noisy images. It includes the following steps:
1. Random zooming: The images are randomly zoomed in or out to create variations in the training.
2. Random cropping: The images are randomly cropped to create variations in the training data.
3. Adding noise: Random noise is added to the images to simulate real-world conditions.
4. generating data with random fonts.
5. Increasing the number of training records: The data augmentation techniques increase the number of training records from the original 60,000 to around 760,000.
## Model
The AI model is a convolutional neural network (CNN) that is trained on the MNIST dataset. The model architecture and hyperparameters are chosen to achieve high accuracy on noisy images(real world data).
## Usage
To use the model, follow these steps:
1. Install the required dependencies by running `pip install -r requirements.txt`.
2. You can use the pre trained model `...\pre-trained model\MNIST_model.h5`
3. download the data set with `download dataset.py`