carpedm20 / carpedm20/DCGAN-tensorflow
Generating Segmented Output using GAN
- Dominant language
- JavaScript
- Stars
- 7.2k
- Forks
- 2.6k
- PR merge metrics
- No merged PRs in 30d
Description
Hello,
I replace the dataset with medical CT-image (of Aorta). It can generate the CT image. I am wondering whether it could be possible to assign label/ground-truth along with input image so I can get the segmented output which will be guided by label/ground-truth image. Could you please give me any suggestion regarding this? I attached herein the Original Data, Label/Ground-truth/mask and Generated image by GAN. I want to generate the segmented image like label/ground-truth.
Any kind of suggestion will be highly appreciated.
Regards
Hosna
Contributor guide
No contributing guide indexed for this repository
Research direction
The issue does not name a file, test, or entry point; begin by locating the repository's TensorFlow data-loading and training paths and checking how paired CT images and masks would enter the GAN. Done would require an agreed approach for conditioning generation on ground-truth masks and a way to verify the segmented output.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- tensorflow
- Domain
- machine-learning
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 20/100