U-Net: Convolutional Networks for Biomedical Image Segmentation
Paper • 1505.04597 • Published • 18
Model description
This model uses the u-net architecture to train boundary detection on patches from sketched boundaries collected during the SmartLandMaps project.
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
| Hyperparameters | Value |
|---|---|
| name | RMSprop |
| weight_decay | None |
| clipnorm | None |
| global_clipnorm | None |
| clipvalue | None |
| use_ema | False |
| ema_momentum | 0.99 |
| ema_overwrite_frequency | 100 |
| jit_compile | True |
| is_legacy_optimizer | False |
| learning_rate | 9.999999747378752e-05 |
| rho | 0.9 |
| momentum | 0.0 |
| epsilon | 1e-07 |
| centered | False |
| training_precision | float32 |
Model Plot
View Model Plot
- Downloads last month
- 23
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support