CODEWITHSUNDEEP
datasetartificial-intelligencetensorflow-datasetsimage-recognitionpre-trained-model
mmz
mmz

Reputation: 1151

Pre-trained model to recognize residential floor plans?

Is there a model that, given an image, recognizes whether the image is a floor plan of a residential property? Or a pre-trained, general-purpose model where I could apply transfer learning?

Here's a sample image. Should be quick to train one, but wanted to check whether there's a generally accepted model out there.

Upvotes: 0

Views: 575

Answers (1)

Frank Bryce
Frank Bryce

Reputation: 8446

fastai has pre-trained models for imagenet that you can re-use & transfer learn against. You can probably use a pre-trained resnet network, then retrain it on a dataset you come up with.

Here's one example from the net, but you can search "fastai transfer learning" for more examples: https://towardsdatascience.com/transfer-learning-using-the-fastai-library-d686b238213e

The hardest part will be you getting a dataset. Here is an example, but I'd honestly recommend working through lesson 1 and 2 of the free fastai course. It'll give you a better overview.

TL;DR - if you can search google for "residential floor plan" or something, you can create a dataset. The hard part will be choosing what non-floor plans to include in your data set. Probably you'll need a lot of random things, but also many things that look close to a residential floor plan, but aren't, so it can get good at distinguishing between a floor plan and a maze, and a pinball layout, and a spreadsheet, etc.

Upvotes: 1

Related Questions