bhimrazy / bhimrazy/sem-segmentation

Mismatch in Mask Dimensions for Multi-Class Segmentation (3 Classes)

Open
#2 1 comment 0 reactions 0 assignees View on GitHub
question
Dominant language
Python
Stars
8
Forks
1
PR merge metrics
No merged PRs in 30d

Description

The default class_nums = 1, but if i want to change it to 3, and the mask I provided have 3 classes, the data preprocessing for the mask(y_pred) only have 1 dim not 3 dims, but the model 's output(y) has 3 dims, so an error occured ! Please tell me how to solve this problem. Thanks!

Contributor guide

No contributing guide indexed for this repository

Research direction

Start by locating the class_nums configuration and tracing the mask preprocessing alongside the model output for a three-class example. Reproduce the reported dimension mismatch with the provided three-class mask. Done means preprocessing produces dimensions compatible with the model output and the error no longer occurs.

Written by the indexing model from the issue text.

Assessment

Tech stack
machine-learning, python
Domain
computer-vision
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.