Mastering Image Classification: A Journey with Cakes
What happens when your AI fails so badly it decides 'the cake is a lie'? Discover the practical path to mastering image classification.
#1about 4 minutes
The origin of the "Is it Cake?" machine learning project
Inspired by the TV show "Is it Cake?", a personal project was started to build an image classifier using TensorFlow.js.
#2about 3 minutes
Sourcing and preparing the cake and not-cake image data
Data was collected by scraping bakers' websites with Playwright and using the Unsplash API, but this introduced data quality issues like logos and ambiguous images.
#3about 3 minutes
Evaluating the pre-trained MobileNet image classification model
The pre-trained MobileNet model in TensorFlow.js was tested but performed poorly, often misclassifying cakes as candles or bakeries.
#4about 2 minutes
Using the Coco-SSD model for object detection
The Coco-SSD object detection model performed better than MobileNet but still made significant errors, like identifying a cake as a person.
#5about 6 minutes
Building a custom convolutional neural network from scratch
An attempt to build a custom Convolutional Neural Network (CNN) using TensorFlow.js sequential models resulted in failure, with the model classifying every image as "not cake".
#6about 2 minutes
Improving model accuracy with transfer learning
Transfer learning was used by taking the feature extraction layers of MobileNet and adding a custom classification head, which significantly improved the model's performance.
#7about 4 minutes
Playing the "Is it Cake?" game and comparing results
The audience participates in an interactive game to classify images, outperforming the custom models and demonstrating the difficulty of the task.
Related jobs
Jobs that call for the skills explored in this talk.
Matching moments
03:27 MIN
Using JavaScript and ML to solve a baking show challenge
Is it (F)ake?! Image Classification with TensorFlow.js
04:41 MIN
Building an image classification game inspired by "Is It Cake?"
Mastering Image Classification: A Journey with Cakes
02:40 MIN
Building a machine learning game with JavaScript
Building Your Own Classification Model with JavaScript - Coffee with Developers - Carly Richmond
02:14 MIN
Collecting and balancing the cake vs not-cake dataset
Is it (F)ake?! Image Classification with TensorFlow.js
01:47 MIN
Sourcing cake and not-cake images for training data
Mastering Image Classification: A Journey with Cakes
02:40 MIN
Improving accuracy with transfer classification and MobileNet
Building Your Own Classification Model with JavaScript - Coffee with Developers - Carly Richmond
03:16 MIN
First attempt using the MobileNet classification model
Mastering Image Classification: A Journey with Cakes
01:07 MIN
Diagnosing why the custom classification model failed
Building Your Own Classification Model with JavaScript - Coffee with Developers - Carly Richmond
Dev Digest 112 - The True Crime of AI DevelopmentIn last Friday's Dev Digest, we had some great AI news, some worrying security threats and a swipe-aware game in CSS with explanations! News and ArticlesLet's kick off with some AI news. Netflix caused a stir with AI-generated images in a true crime ...
Daniel Cranney
Coffee with Developers is Now Available as an Audio PodcastFor the past few years, we’ve had the privilege of meeting fascinating developers and tech professionals from around the world through our Coffee with Developers episodes. While all of the episodes are available in their original video format on our ...
Chris Heilmann
All the videos of Halfstack London 2024!Last month was Halfstack London, a conference about the web, JavaScript and half a dozen other things. We were there to deliver a talk, but also to record all the sessions and we're happy to share them with you. It took a bit as we had to wait for th...
From learning to earning
Jobs that call for the skills explored in this talk.
25:19
25:43
36:29
49:45
38:24
57:46
27:23
39:58
