https://github.com/g-eoj/kaggle-mnist
MNIST classification with a low parameter convolutional neural network based on inception modules.
https://github.com/g-eoj/kaggle-mnist
cnn deep-learning inception keras mnist
Last synced: about 2 months ago
JSON representation
MNIST classification with a low parameter convolutional neural network based on inception modules.
- Host: GitHub
- URL: https://github.com/g-eoj/kaggle-mnist
- Owner: g-eoj
- Created: 2018-09-06T03:45:53.000Z (over 7 years ago)
- Default Branch: master
- Last Pushed: 2018-12-16T20:52:08.000Z (over 7 years ago)
- Last Synced: 2026-01-03T10:29:49.682Z (5 months ago)
- Topics: cnn, deep-learning, inception, keras, mnist
- Language: Jupyter Notebook
- Homepage:
- Size: 1.39 MB
- Stars: 0
- Watchers: 0
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Kaggle Digit Recognizer
MNIST classification with a low parameter convolutional neural network based on [inception modules](https://arxiv.org/abs/1602.07261).
### Kernels
The 'kernels' folder contains [Kernels](https://www.kaggle.com/docs/kernels) for Kaggle.
- [MNIST Data Augmentation with Elastic Distortion](https://www.kaggle.com/babbler/mnist-data-augmentation-with-elastic-distortion): Overview/visualization of elastic distortion and select Keras data augmentation methods on MNIST.
- `mnist-inception-9970-test-acc-kernel.ipynb`: Method for training a 76,264 parameter inception model that scored 99.7% test accuracy in the [Kaggle Digit Recognizer competition](https://www.kaggle.com/c/digit-recognizer).
### Exploratory Notebooks
- `mnist-inception.ipynb`: Used to explore methods and generate results, which can be appended to a csv file.
- `mnist-inception-results.ipynb`: Used to explore results (which are loaded in from the csv file) and other related ideas.