Live 86: Decision Forests, TensorFlow with Docker in Apple Silicon M1/M2 & TFLite Signatures
In Live 86, we continued training a decision forest algorithm to classify penguins by species with the tensorflow_decision_forests Python framework on the Palmer Penguins dataset, we saw how to run TensorFlow inside of Docker and a few tricks to create containers and manage them, and briefly looked at TensorFlow signatures, which are supported by TensorFlow Lite since version 2.7.0 and let us export different named operations in a single model that can be executed in C++, Java, and Python.
Here are links to most of the things we covered.
- TensorFlow Decision Forests library
- Colab notebook for Decision Forests Palmer Penguin classification1dpQY87nAFyjgKt3-IZO0uBbiGpJYZsKU?usp=sharing
- palmerpenguins dataset
- Hands-on Machine Learning with Scikit-Learn, Keras, and TensorFlow
- Colab notebook for Keras Preprocessing Modelusp=sharing
- Run TensorFlow on a Docker container
- Signatures in TensorFlow Lite
You can spread the word by liking and sharing this tweet.
If this is something that interests you, please let me know on Twitter or, even better, on the Discord community.
Thanks for watching.
See you next week!
Chapters
- 02:26 Introduction
- 04:46 Today
- 05:04 Decision Forests — Overview
- 10:02 Decision Forests — Recap of Live 85
- 14:42 Decision Forests — Notebook
- 40:06 Decision Forests — Understanding Keras Preprocessors
- 01:05:36 Keras Preprocessing Models
- 01:30:08 Break
- 01:33:24 Interlude
- 01:39:30 Preparation — TensorFlow in Docker
- 01:44:18 Demo — TensorFlow in Docker
- 01:56:28 TensorFlow in Docker — Tutorial
- 02:02:34 Demo — TensorFlow in Docker
- 02:04:58 Interlude
- 02:05:40 TensorFlow Signatures
- 02:16:50 Interlude
- 02:17:38 Docker Tricks
- 02:20:06 Getting Simple Announcements & Sneak Peek
- 02:25:11 Outro