Image-to-Image
Keras
cuneiform
image-generation
pix2pix
normal-maps
digital-humanities
cultural-heritage
Instructions to use GhentCDH/Cuneinormals_P2P with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Keras
How to use GhentCDH/Cuneinormals_P2P with Keras:
# Available backend options are: "jax", "torch", "tensorflow". import os os.environ["KERAS_BACKEND"] = "jax" import keras model = keras.saving.load_model("hf://GhentCDH/Cuneinormals_P2P") - Notebooks
- Google Colab
- Kaggle
| { | |
| "training_date": "2025/09/02", | |
| "color_images": 61711, | |
| "normal_images": 7716, | |
| "augments": true, | |
| "split_ratio": 0.9, | |
| "image_resolution": 1024, | |
| "pad_stride": 0.9, | |
| "dataset_mode": "grid", | |
| "image_shape": [ | |
| 1024, | |
| 1024, | |
| 3 | |
| ], | |
| "lambda_l1": 20.0, | |
| "loss_function": "binary_crossentropy", | |
| "epochs": 20, | |
| "dataset_subdivisions": 30, | |
| "batch_size": 6, | |
| "learning_rate": 0.0012000000000000001, | |
| "G_learning_rate": 1.0, | |
| "D_learning_rate": 1.0, | |
| "architecture": "pix2pix", | |
| "last_epoch": 14, | |
| "last_subdivision": 21 | |
| } |