Downloads · 30 days
9
4% of all-time downloads
deeplab-v3
lmazzon70/deeplab-v3
deeplab-v3 is a image segmentation model from lmazzon70. 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 tf-keras.
All-time downloads
227
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
- tf-keras
- Access
- Public
- Created
- Jun 1, 2022
- Updated
- Nov 14, 2024
- SHA
- 53f0c3de
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 | 1.231 | 0.635 | 1.913 | 0.596 |
| 2 | 0.947 | 0.699 | 2.633 | 0.599 |
| 3 | 0.841 | 0.731 | 1.06 | 0.68 |
| 4 | 0.772 | 0.752 | 1.035 | 0.685 |
| 5 | 0.701 | 0.774 | 1.03 | 0.697 |
Model Plot
<details> <summary>View Model Plot</summary>
- Task
- Image Segmentation
- Library
- tf-keras
- Created
- Jun 1, 2022
- Updated
- Nov 14, 2024