Instructions to use sharktide/FireTrustNet with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Keras
How to use sharktide/FireTrustNet with Keras:
# Available backend options are: "jax", "torch", "tensorflow". import os os.environ["KERAS_BACKEND"] = "jax" import keras model = keras.saving.load_model("hf://sharktide/FireTrustNet") - Notebooks
- Google Colab
- Kaggle
metadata
language:
- en
metrics:
- mse
library_name: keras
This model requires the following custom objects:
import tensorflow as tf
from tensorflow.keras.saving import register_keras_serializable
from tensorflow.keras import layers, models, backend as K
import numpy as np
@register_keras_serializable()
def firetrust_activation(x):
return 0.5 + tf.sigmoid(x) # output in range [0.5, 1.5]