#14 Live Coding - Tensorflow Image Classification with Transfer Learning - Refactoring my Notebook

#machinelearning #machinelearningproject #kaggle #tensorflow

In my last Livestream i have finally migrated my notebook from Kaggle to Google Colab and at the same time refactored my code to make it easier to run experiments. And in this way i was able to derive some important conclusions:

1) the dataset of images i have gathered from the internet are not helpful to the model for transfer learning. I need images from other security or wildlife cameras, not pictures of cute cats taken by human photographers.

2) i need to collect more images similar to the type of images i gathered from my raspberry pi camera.

For now i am going to proceed to the next phase of the project, that is, to deploy a first version of the tensorflow lite model to the raspberry pi and create a data pipeline to gather more data so we can improve the model. Mlops anyone?
This is going to be fun and i think this pet project is a great way to demonstrate the engineering that is required to deploy a machine learning model in the wild.

✅ Recommended Courses
(Includes Amazon Affiliate Links)
==================================

✅ Recommended Playlists
==================================

✅ My Favorite Tech
(Includes Amazon Affiliate Links)
==================================

✅ My RTX 3070 and Ryzen 5900 Machine Learning PC Build
(Includes Amazon Affiliate Links)
=======================================================

✅ MY EQUIPMENT FOR YOUTUBE
(Includes Amazon Affiliate Links)
==================================

As an Amazon Associate, I earn a small commission from qualifying purchases on the amazon links above.

✅ Source Code

✅ BUSINESS ENQUIRIES

✅ SUPPORT THE CHANNEL or get MENTORING

✅ FOLLOW ME

✅ Timestamps