Comments (3)
Here's a MATLAB script I wrote to do the preprocessing. Since YorkUrban is such a small dataset, it might be worthwhile just to reupload it in the preprocessed format.
This is to be ran in the york_raw
directory with the YorkUrbanDB unzipped to that directory.
york_urban_db_path = 'YorkUrbanDB';
load(fullfile(york_urban_db_path, 'Manhattan_Image_DB_Names.mat'));
load(fullfile(york_urban_db_path,'ECCV_TrainingAndTestImageNumbers.mat'));
n_exemplars = length(Manhattan_Image_DB_Names);
for i = 1:n_exemplars
name = Manhattan_Image_DB_Names{i}(1:end-1);
fprintf('Processing %d/%d\r', i, n_exemplars);
%% Image Ontology Preprocess
input_im_path = fullfile(york_urban_db_path, name, [name, '.jpg']);
output_im_path = [name, '_rgb.png'];
im = imread(input_im_path);
imwrite(im, output_im_path);
%% Line Segment Ontology Preprocess
input_contents_path = fullfile(york_urban_db_path, name, [name, 'LinesAndVP.mat']);
output_contents_path = [name, '.mat'];
contents = load(input_contents_path);
line = contents.lines;
save(output_contents_path, 'line');
end
from afm_cvpr2019.
You need to use matlab to read the YorkUrban dataset and write the images and line segments into "filename_rgb.png" and "filename.mat". The line segments in the mat file should be saved with the variable 'line'. In our evaluation, we only use the test data (51 images). You can read the guideline of YorkUrban dataset for the format.
from afm_cvpr2019.
Thank u very much,I will try it again。
from afm_cvpr2019.
Related Issues (20)
- OSError: CUDA_HOME environment variable is not set. Please set it to your CUDA install root. HOT 2
- ValueError: num_samples should be a positive integer value, but got num_samples=0 HOT 10
- Results wrong when testing at different input resolutions HOT 2
- skipping 'squeeze.cpp' Cython extension (up-to-date)
- ImportError: No module named 'squeeze.squeeze' HOT 5
- Threshold of the aspect ratio. HOT 2
- How can I evaluate a photo not in the dataset HOT 3
- no module named squeeze HOT 11
- Atrous Residual VS Unet. HOT 1
- The dataset can not be downloaded,why is it? HOT 2
- ImportError: /home/afm_cvpr2019-master/lib/afm_op/CUDA.cpython-36m-x86_64-linux-gnu.so: undefined symbol: __cudaRegisterFatBinaryEnd HOT 5
- How to evaluate the pre-trained model on my own images? HOT 1
- what`s the mean? did it succeed?
- RuntimeError: cuDNN error: CUDNN_STATUS_EXECUTION_FAILED
- Open dataset? HOT 1
- error"conda develop ../lib"
- error"python preparation_york.py" KeyError:'line' HOT 6
- unrecognized error code HOT 1
- evaluate
- 怎么在自己图像上测试线段检测 HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from afm_cvpr2019.