Comments (3)
Yes, because that yaml file contains path to image and init_contour
file for that image. You can use it like that too:
import argparse
parser = argparse.ArgumentParser()
parser.add_argument("-i", "--input", help="yaml file with GameTheoreticFramework object", required=True)
parser.add_argument("-in", "--image_name", help="name of the ph2 image (eg. IMD002)",
required=True)
parser.add_argument("-pb", "--path_beginning", help="beginning of the image path, added to each path",
required=True)
args = parser.parse_args()
with open(args.input) as file:
gt_segmentation = yaml.load(file, Loader=yaml.Loader)
img_n = args.image_name
path_beg = args.path_beginning
gt_segmentation.image_path = path_beg + r'/%s/%s_Dermoscopic_Image/%s.bmp' % (img_n, img_n, img_n)
gt_segmentation.init_contours = path_beg + r'/init_lesion/%s_lesion.png' % (img_n)
In above example you can use single yaml file for multiple images. You pass an command line argument with some image name, that is used to construct paths to the image itself and to file file with init_contours
, then whatever paths were saved in the yaml file get overwritten with this new paths.
This is how an file with init_contours
can look like:
It works with any extension supported by openCV function imread
(https://docs.opencv.org/3.4/d4/da8/group__imgcodecs.html#ga288b8b3da0892bd651fce07b3bbd3a56).
from gt_im_s.
- I made some changes in the
game_theoretic_framework
class so it works as a library and added an script with example of such usage.
If you want an image to be stored as a numpy array then setfull_init
toTrue
when creating the yaml file. I don't recommend it though, because storing images in a yaml file is inefficient.
Colour images need to be converted to grayscale (it's done automatically when usingload_image
), because with that kind of images in mind whole algorithm was developed.
Yaml file used to acquire that output mask:
!!python/object:game_theoretic_framework.GameTheoreticFramework
b_cost_interlaced: null
clique_size: 4
contours: null
differential_evolution_bounds_width: 0.55
expected_val_in: 1
expected_val_out: 0
image: null
image_gradient: null
image_path: .\obrazki_do_testow\IMD004\IMD004_Dermoscopic_Image\IMD004.bmp
img_gradient_ksize: 27
init_b_cost_interlaced: null
init_contours: .\obrazki_do_testow\IMD004\IMD004_lesion\IMD004_lesion.bmp
init_fourier_coeffs_first_part: null
init_fourier_coeffs_second_part: null
init_img_seg: null
init_tr: null
iter_num: 0
max_iterations: 3
object_brighter_than_background: false
order_of_fourier_coeffs: 14
p2c_acc: 2000
prior_b_cost: 0
region_segmentation: null
scaling_const_alpha: 0.1
scaling_const_beta: 0.1
sm_const: 14
- In
utils
there is functionhair_removal
that removes hair from given image.
from gt_im_s.
Ok, so for multiple images I need to create a yaml file similar to this one and an init_contours
image for each one of them? How such an image should look like, @jaroslaw243 ?
Does it work for other extensions than *.bmp
?
from gt_im_s.
Related Issues (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 gt_im_s.