Image for post
Image for post
Photo by Manuel Cosentino on Unsplash

I created a simple translation app using streamlit to highlight the simplicity of using the platform to quickly create apps. The app takes English input from a user which is then translated to Japanese.

Using deep learning to Classify Handwritten Digits from Kaggle MNIST data with fastai and Google Colab

Image for post
Image for post
Photo by Christopher Burns on Unsplash

After starting fastai’s practical deep learning for coders, I’ve built a simple model in Google Colab with fastai to identify handwritten numbers from the Kaggle MNIST dataset.

The code downloads the MNIST data from Kaggle, creates jpg images and stores it in your google drive. It then trains and tests the model to submit to Kaggle. The final results from this model achieved a public score of 0.97396.

A lot of the motivation for this work was to prepare myself to compete in future Kaggle competitions and to apply the knowledge I’ve learnt so far through fastai’s MOOC. …

Jiro Ishida

Budding Data Scientist by day, mediocre Olympic Weightlifter/Hip-hop Producer by night.

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store