---
library_name: keras-hub
license: apache-2.0
language:
- en
tags:
- text-classification
- keras
pipeline_tag: text-classification
---
## Model Overview
FNet is a set of language models published by Google as part of the paper [FNet: Mixing Tokens with Fourier Transforms](https://arxiv.org/abs/2105.03824). FNet replaces the self-attention of BERT with an unparameterized fourier transform, dramatically lowering the number of trainable parameters in the model. FNet achieves training at 92-97% accuracy of BERT counterparts on GLUE benchmark, with faster training and much smaller saved checkpoints.

Weights and Keras model code are released under the [Apache 2 License](https://github.com/keras-team/keras-hub/blob/master/LICENSE).

## Links

* [FNet Quickstart Notebook](https://www.kaggle.com/code/matthewdwatson/fnet-quickstart/)
* [FNet API Documentation](https://keras.io/api/keras_hub/models/f_net/)
* [FNet Model Card](https://github.com/google-research/google-research/blob/master/f_net/README.md)
* [KerasHub Beginner Guide](https://keras.io/guides/keras_hub/getting_started/)
* [KerasHub Model Publishing Guide](https://keras.io/guides/keras_hub/upload/)

## Installation

Keras and KerasHub can be installed with:

```
pip install -U -q keras-hub
pip install -U -q keras>=3
```

Jax, TensorFlow, and Torch come preinstalled in Kaggle Notebooks. For instruction on installing them in another environment see the [Keras Getting Started](https://keras.io/getting_started/) page.

## Presets

The following model checkpoints are provided by the Keras team. Full code examples for each are available below.

| Preset name    | Parameters | Description                                   |
|----------------|------------|-----------------------------------------------|
| `f_net_base_en`  | 82.86M     | 12-layer FNet model where case is maintained. |
| `f_net_large_en` | 236.95M    | 24-layer FNet model where case is maintained. |

## Example Usage
```python
import keras
import keras_hub
import numpy as np
```

Raw string data.
```python
features = ["The quick brown fox jumped.", "I forgot my homework."]
labels = [0, 3]

# Pretrained classifier.
classifier = keras_hub.models.FNetClassifier.from_preset(
    "f_net_base_en",
    num_classes=4,
)
classifier.fit(x=features, y=labels, batch_size=2)
classifier.predict(x=features, batch_size=2)

# Re-compile (e.g., with a new learning rate).
classifier.compile(
    loss=keras.losses.SparseCategoricalCrossentropy(from_logits=True),
    optimizer=keras.optimizers.Adam(5e-5),
    jit_compile=True,
)
# Access backbone programmatically (e.g., to change `trainable`).
classifier.backbone.trainable = False
# Fit again.
classifier.fit(x=features, y=labels, batch_size=2)
```

Preprocessed integer data.
```python
features = {
    "token_ids": np.ones(shape=(2, 12), dtype="int32"),
    "segment_ids": np.array([[0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 0, 0]] * 2),
}
labels = [0, 3]

# Pretrained classifier without preprocessing.
classifier = keras_hub.models.FNetClassifier.from_preset(
    "f_net_base_en",
    num_classes=4,
    preprocessor=None,
)
classifier.fit(x=features, y=labels, batch_size=2)
```

## Example Usage with Hugging Face URI

```python
import keras
import keras_hub
import numpy as np
```

Raw string data.
```python
features = ["The quick brown fox jumped.", "I forgot my homework."]
labels = [0, 3]

# Pretrained classifier.
classifier = keras_hub.models.FNetClassifier.from_preset(
    "f_net_base_en",
    num_classes=4,
)
classifier.fit(x=features, y=labels, batch_size=2)
classifier.predict(x=features, batch_size=2)

# Re-compile (e.g., with a new learning rate).
classifier.compile(
    loss=keras.losses.SparseCategoricalCrossentropy(from_logits=True),
    optimizer=keras.optimizers.Adam(5e-5),
    jit_compile=True,
)
# Access backbone programmatically (e.g., to change `trainable`).
classifier.backbone.trainable = False
# Fit again.
classifier.fit(x=features, y=labels, batch_size=2)
```

Preprocessed integer data.
```python
features = {
    "token_ids": np.ones(shape=(2, 12), dtype="int32"),
    "segment_ids": np.array([[0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 0, 0]] * 2),
}
labels = [0, 3]

# Pretrained classifier without preprocessing.
classifier = keras_hub.models.FNetClassifier.from_preset(
    "f_net_base_en",
    num_classes=4,
    preprocessor=None,
)
classifier.fit(x=features, y=labels, batch_size=2)
```