GithubHelp home page GithubHelp logo

Comments (12)

tkwoo avatar tkwoo commented on September 15, 2024

Label image is represented to gray scale, not 3ch rgb color.
Label : 24(pedestrian), 25(cyclist)
I changed label into a sparse matrix for making ground truth. so 24, 25 -> 255

if gt[idx]==24 or gt[idx]==25:
 human[idx] = 255
else:
 human[idx] = 0

from visualization-segmentation-process.

Zumbalamambo avatar Zumbalamambo commented on September 15, 2024

20170905094129778

This is how the groundtruth image will be incase if I photoshop it.
However the groundtruth image that you've provided looks bit different... May I know how do did you generate them?

from visualization-segmentation-process.

Zumbalamambo avatar Zumbalamambo commented on September 15, 2024

I have got one more doubt...

How do we get the label as 24,25? is it hardcoded value based on cityscape dataset?

from visualization-segmentation-process.

tkwoo avatar tkwoo commented on September 15, 2024

@Zumbalamambo cityscape provide with 2 types groundtruth, one is color type, another is grayscale.
Check original GT parser
https://github.molgen.mpg.de/mohomran/cityscapes/blob/682adf38b69bdf858bed556796638a5a78f1c762/scripts/helpers/labels.py#L56

Label(  'person'               , 24 ,       11 , 'human'           , 6       , True         , False        , (220, 20, 60) ),
Label(  'rider'                , 25 ,       12 , 'human'           , 6       , True         , False        , (255,  0,  0) ),

from visualization-segmentation-process.

Zumbalamambo avatar Zumbalamambo commented on September 15, 2024

@tkwoo Thank you. If i have to train on my own dataset, how the make_regressor_label should be? I used the grayscale and the accuracy is bit low. Will it improve if I use rgb?

from visualization-segmentation-process.

tkwoo avatar tkwoo commented on September 15, 2024

@Zumbalamambo How many do you prepare the training images? In this project, I used 3750 rgb images and Unet, valdiation quality was quite reasonable.(I checked qualitatively)

from visualization-segmentation-process.

Zumbalamambo avatar Zumbalamambo commented on September 15, 2024

i have used 1000 images....I will increase the dataset. Can you please tell me how i need to change the make_regressor_label label function if I have to train more than three class ?

from visualization-segmentation-process.

enomto avatar enomto commented on September 15, 2024

Could you tell me the attributes of the 3750 images? Also, I'm worried about how to design labels etc. Although I am rewriting, there may be something that goes wrong occasionally, so I may understand something.

from visualization-segmentation-process.

tkwoo avatar tkwoo commented on September 15, 2024

@enomto
I rescaled cityscape image into 1/4 size for fast training. (1024, 2048, 3) --> (256, 512, 3)
Feel free to modify input size.

from visualization-segmentation-process.

Zumbalamambo avatar Zumbalamambo commented on September 15, 2024

@tkwoo Thank you. I will try with the new code and will update ...

from visualization-segmentation-process.

Zumbalamambo avatar Zumbalamambo commented on September 15, 2024

I have set the width to 1920 and height to 1080. But Im getting the following error,

ValueError: A Concatenate layer requires inputs with matching shapes except for the concat axis. Got inputs shapes: [(None, 134, 240, 256), (None, 135, 240, 256)]

How do I sort it out?

from visualization-segmentation-process.

Zumbalamambo avatar Zumbalamambo commented on September 15, 2024

@tkwoo how do I choose the input shape?

from visualization-segmentation-process.

Related Issues (3)

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo 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.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.