Designed and trained a CNN-based image segmentation model for pixel-level classification. Preprocessed image–mask datasets with Albumentations for augmentation, split into training/validation/test using class-aware distribution, and evaluated with Dice, IoU, loss curves, confusion matrix, plus visualized predicted vs. ground truth masks.
-
Notifications
You must be signed in to change notification settings - Fork 0
Designed and trained a CNN-based image segmentation model for pixel-level classification. Preprocessed image–mask datasets with Albumentations for augmentation, split into training/validation/test using class-aware distribution, and evaluated with Dice, IoU, loss curves, confusion matrix, plus visualized predicted vs. ground truth masks.
Amitosh07/Image-Segmentation-System-project
Folders and files
| Name | Name | Last commit message | Last commit date | |
|---|---|---|---|---|
Repository files navigation
About
Designed and trained a CNN-based image segmentation model for pixel-level classification. Preprocessed image–mask datasets with Albumentations for augmentation, split into training/validation/test using class-aware distribution, and evaluated with Dice, IoU, loss curves, confusion matrix, plus visualized predicted vs. ground truth masks.
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published