divamgupta/image-segmentation-keras

Gray images to input for unet

Open

#102 opened on Sep 1, 2019

View on GitHub
 (3 comments) (0 reactions) (0 assignees)Python (1,151 forks)github user discovery
help wanted

Repository metrics

Stars
 (3,004 stars)
PR merge metrics
 (No merged PRs in 30d)

Description

Hello. I wanted to train vanilla unet model with gray images. But model require 3 dimentional images. Can I solve this problem?

Contributor guide

Research direction
Modify the input shape of the UNet model to accept (height, width, 1) instead of (height, width, 3). Convert grayscale images to 3 channels by repeating the single channel three times (np.repeat) or adjust the model's first layer.
Tech stack
python
Domain
machine learningai
Issue type
Research
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
2
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
Under 1 hour
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
Active
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
Clear
Prerequisites
PythonKeras
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
75