I tried running Deep Floor Plan with Python 3.6.10.

Introduction

I rewrote "Deep Floor Plan Recognition Using a Multi-Task Network with Room-Boundary-Guided Attention" (hereinafter referred to as "Deep Floor Plan") announced at ICCV2019 to the python3 version and tried it. [paper, github python3 version)](https://github.com/c-makitahiroki/DeepFloorplan)]

I was worried that the task might have specific business needs. In this article, I will briefly introduce DeepFloorPlan and then write the result of running the demo program. The results of running the learning program will be added in the future.

What is DeepFloorPlan?

In a nutshell, it's a DNN that "** recognizes the room layout **". deepfloorplan.png It is characteristic that the decoder is separated for each room boundary prediction task and room type prediction task. In addition, room boundary information is used as an attention for room type prediction.

The network itself is relatively simple, but better performance than PSPNet and DeepLab V3 + Is out. deepfloorplan_eval.png

Execution environment

OS: windows10 64bit GPU: GeForce GTX1060 6GB

Demo program execution result

I tried running the demo program using the trained model. Here, I would like to give an example where reasoning is relatively good and an example where it is not.

An example that can be estimated

うまくいっている例.png Some of the halls are recognized as closets and toilets, but the background and room types, as well as the doors and windows, are relatively correctly recognized.

Examples that cannot be estimated

うまくいっていない例.png The boundary between the balcony and the dining room is not recognized correctly. It seems that the door type is a little special. Also, this data does not recognize some of the background and room boundaries correctly. It seems that the cause is that the annotation of the drawing is included in the background part of the input image.

Consideration

I looked at some other data, but the following points seem to be difficult.

I would like to make improvements to deal with this area in the future.

Learning program execution result

I would like to improve it and add the results later. If you have any suggestions for improving accuracy, please comment!

Recommended Posts

I tried running Deep Floor Plan with Python 3.6.10.
I tried running prolog with python 3.8.2.
I tried fp-growth with python
I tried gRPC with Python
I tried scraping with python
I tried web scraping with python.
I tried Grumpy (Go running Python).
I tried SMTP communication with Python
I tried running Movidius NCS with python of Raspberry Pi3
I tried scraping Yahoo News with Python
I tried sending an email with python.
I tried non-photorealistic rendering with Python + opencv
I tried a functional language with Python
I tried recursion with Python ② (Fibonacci sequence)
#I tried something like Vlookup with Python # 2
I tried "smoothing" the image with Python + OpenCV
I tried hundreds of millions of SQLite with python
I tried running pymc
I tried "differentiating" the image with Python + OpenCV
I tried Python> autopep8
I tried Jacobian and partial differential with python
I tried to get CloudWatch data with Python
I tried using mecab with python2.7, ruby2.3, php7
I tried function synthesis and curry with python
I tried to output LLVM IR with Python
I tried deep learning
I tried "binarizing" the image with Python + OpenCV
I tried to automate sushi making with python
I tried playing mahjong with Python (single mahjong edition)
I tried running python -m summpy.server -h 127.0.0.1 -p 8080
I tried running alembic, a Python migration tool
I tried sending an email with SendGrid + Python
I tried Python> decorator
I tried running TensorFlow
I tried running BERT with Sakura VPS (without GPU)
I tried to get started with blender python script_Part 01
I tried to touch the CSV file with Python
I tried to draw a route map with Python
[OpenCV / Python] I tried image analysis of cells with OpenCV
I tried running python etc. from a bat file
I tried to get started with blender python script_Part 02
I tried to implement an artificial perceptron with python
I tried to automatically generate a password with Python3
Mayungo's Python Learning Episode 1: I tried printing with print
[Python] I tried running a local server using flask
I tried to solve the problem with Python Vol.1
I tried "morphology conversion" of images with Python + OpenCV
I tried hitting the API with echonest's python client
I tried to solve AOJ's number theory with Python
I tried Learning-to-Rank with Elasticsearch!
I made blackjack with python!
I tried clustering with PyCaret
I tried Python C extension
Try running Python with Try Jupyter
[Python] I tried using OpenPose
I made blackjack with Python.
I made wordcloud with Python.
I tried deploying Kubernetes Pods / Helm Chart with Pulumi (Python)
I tried to find the entropy of the image with python
I tried "gamma correction" of the image with Python + OpenCV
I tried to simulate how the infection spreads with Python