Instructions to use johko/wideresnet28-2-mnist with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Keras
How to use johko/wideresnet28-2-mnist with Keras:
# Available backend options are: "jax", "torch", "tensorflow". import os os.environ["KERAS_BACKEND"] = "jax" import keras model = keras.saving.load_model("hf://johko/wideresnet28-2-mnist") - Notebooks
- Google Colab
- Kaggle
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:
| name | learning_rate | decay | beta_1 | beta_2 | epsilon | amsgrad | training_precision |
|---|---|---|---|---|---|---|---|
| Adam | {'class_name': 'CosineDecay', 'config': {'initial_learning_rate': 0.03, 'decay_steps': 9370, 'alpha': 0.25, 'name': None}} | 0.0 | 0.8999999761581421 | 0.9990000128746033 | 1e-07 | False | float32 |
Model Plot
- Downloads last month
- -
