Downloads · 30 days
0
0% of all-time downloads
deeplab-v3
keja/deeplab-v3
deeplab-v3 is a image segmentation model from keja. Use it for the image segmentation task on the model card, and read the license before you ship it in a product. It is set up for keras.
All-time downloads
57
Public
Repo size
53.5 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.data-00000-of-0000147.6 MB · 89%
At a glance
- Task
- Image Segmentation
- Library
- keras
- Access
- Public
- Created
- May 30, 2022
- Updated
- May 30, 2022
- SHA
- edddc47c
Model card
From the Hugging Face model README
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- optimizer: {'name': 'Adam', 'learning_rate': 0.001, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
- training_precision: float32
Training Metrics
| Epochs | Train Loss | Train Accuracy | Validation Loss | Validation Accuracy |
|---|---|---|---|---|
| 1 | 1.189 | 0.639 | 2.374 | 0.596 |
| 2 | 0.954 | 0.697 | 1.89 | 0.59 |
| 3 | 0.84 | 0.732 | 1.3 | 0.651 |
| 4 | 0.77 | 0.753 | 1.014 | 0.677 |
| 5 | 0.704 | 0.773 | 1.053 | 0.668 |
Model Plot
<details> <summary>View Model Plot</summary>
- Task
- Image Segmentation
- Library
- keras
- Created
- May 30, 2022
- Updated
- May 30, 2022