Instructions to use kugu/AIAMD with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Keras
How to use kugu/AIAMD with Keras:
# !pip install -U keras tensorflow huggingface_hub # Keras needs TensorFlow installed to read "hf://" paths, so the tensorflow backend is selected here; # "jax" and "torch" also work for computation once TensorFlow is installed. import os os.environ["KERAS_BACKEND"] = "tensorflow" import keras model = keras.saving.load_model("hf://kugu/AIAMD") - Notebooks
- Google Colab
- Kaggle
Download training_summary.json from kugu/AIAMD: direct link, hf CLI and curl.
- Browser
- Download file 716 Bytes
-
https://huggingface.co/kugu/AIAMD/resolve/main/training_summary.json
- Command line
-
hf download hf://kugu/AIAMD/training_summary.json
-
curl -L -o training_summary.json https://huggingface.co/kugu/AIAMD/resolve/main/training_summary.json
716 Bytes
| { | |
| "created": "2026-11-16T09:43:43+00:00", | |
| "model_path": "models/amd_gru.keras", | |
| "monitor": "val_loss", | |
| "best_epoch": 4, | |
| "epochs_run": 14, | |
| "best_val": { | |
| "loss": 0.0763, | |
| "val_loss": 0.0777, | |
| "val_window_acc": 0.9694, | |
| "window_acc": 0.9609, | |
| "val_clip_balanced_acc": 0.9771, | |
| "val_clip_auc": 0.9964 | |
| }, | |
| "class_weights": { | |
| "0": 1.2205114570240743, | |
| "1": 0.846975745580194 | |
| }, | |
| "silence_dbfs": -50.0, | |
| "model": { | |
| "dense_units": 32, | |
| "gru_units": 48 | |
| }, | |
| "train": { | |
| "epochs": 50, | |
| "batch_size": 32, | |
| "learning_rate": 0.001, | |
| "model_path": "models/amd_gru.keras", | |
| "monitor": "val_loss", | |
| "patience": 10, | |
| "threshold": 0.5 | |
| }, | |
| "params": 44657 | |
| } |