Comments (6)
Hi @Lord-Psarris,
Any successful approach for segmenting different classes as you mentioned in the issue?
Please help, I have similar issue.
Thanks
from cloth-segmentation.
Hello @karndeepsingh,
I made a simple script to detect the colors in the image.
The segmented image mask have a max of 4 colors (black for background, and 3 others for full body, upper body and lower body), so it simply checks the pixels to see which of the colors are detected in the image.
You might want to optimize the image or reduce its resolution first if computing time and memory are an issue. Let me know if you'd like to see my implementation
from cloth-segmentation.
Hello @karndeepsingh, I made a simple script to detect the colors in the image.
The segmented image mask have a max of 4 colors (black for background, and 3 others for full body, upper body and lower body), so it simply checks the pixels to see which of the colors are detected in the image.
You might want to optimize the image or reduce its resolution first if computing time and memory are an issue. Let me know if you'd like to see my implementation
That’s great @Lord-Psarris
Can you share your work? I would like to understand it.
Thankyou so much
from cloth-segmentation.
@karndeepsingh @Lord-Psarris
I have similar issue, can you guys help with the script to retrive the original colors for the segmentation?
from cloth-segmentation.
@karndeepsingh , @kumar-hardik here is a google collab of my implementation.
Feel free to utilize it as you see fit
from cloth-segmentation.
@kumar-hardik , @karndeepsingh you can find my complete solution here:
https://github.com/Lord-Psarris/cloth-segmentation
from cloth-segmentation.
Related Issues (19)
- Model very slow on cpu HOT 2
- RuntimeError: CUDA out of memory. HOT 1
- Possible to adjust sensitivity threshold?
- [bug] labels should start from 1
- [question] Segmentation mask dimensions
- AttributeError: 'NoneType' object has no attribute 'to'; Issue with colab HOT 3
- Prorosal: Pack model for Huggingface inference HOT 2
- Is it possible to segregate the final output into each seperate label and have its original colour from the input image? HOT 2
- Inference error on trained checkpoints HOT 14
- final_label = first_channel + second_channel * 2 + third_channel * 3 conflict_mask = (final_label <= 3).astype("uint8") final_label = (conflict_mask) * final_label + (1 - conflict_mask) * 1 target_tensor = torch.as_tensor(final_label, dtype=torch.int64)
- 您好!如何将分割结果输出为RGB彩色图?
- Pretrained model file is not found using google drive link HOT 12
- Model isn't accurate HOT 1
- 多人图片的识别问题 HOT 15
- IsADirectoryError: [Errno 21] Is a directory: 'input_images/.ipynb_checkpoints' HOT 1
- TypeError: Caught TypeError in DataLoader worker process 0. and TypeError: 'float' object cannot be interpreted as an integer HOT 4
- How can upper body and Lower body segmentation can be separated out? HOT 1
- Can pretrain model to 11 class ?
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 cloth-segmentation.