SegFormer Segmentation

[source]

SegFormer class

keras_cv.models.SegFormer(backbone, num_classes, projection_filters=256, **kwargs)

A Keras model implementing the SegFormer architecture for semantic segmentation.

References

• SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers # noqa: E501 - Based on the TensorFlow implementation from DeepVision # noqa: E501

Arguments

• backbone: keras.Model. The backbone network for the model that is used as a feature extractor for the SegFormer encoder. It is intended to be used only with the MiT backbone model which was created specifically for SegFormers. It should either be a keras_cv.models.backbones.backbone.Backbone or a tf.keras.Model that implements the pyramid_level_inputs property with keys "P2", "P3", "P4", and "P5" and layer names as values.
• num_classes: int, the number of classes for the detection model, including the background class.
• projection_filters: int, number of filters in the convolution layer projecting the concatenated features into a segmentation map. Defaults to 256`.

Examples

Using the class with a backbone:

import tensorflow as tf
import keras_cv

images = np.ones(shape=(1, 96, 96, 3))
labels = np.zeros(shape=(1, 96, 96, 1))
backbone = keras_cv.models.MiTBackbone.from_preset("mit_b0_imagenet")
model = keras_cv.models.segmentation.SegFormer(
    num_classes=1, backbone=backbone,
)

# Evaluate model
model(images)

# Train model
model.compile(
    optimizer="adam",
    loss=keras.losses.BinaryCrossentropy(from_logits=False),
    metrics=["accuracy"],
)
model.fit(images, labels, epochs=3)

[source]

from_preset method

SegFormer.from_preset(
    preset, num_classes, load_weights=None, input_shape=None, **kwargs
)

Instantiate SegFormer model from preset config and weights.

Arguments

• preset: string. Must be one of "mit_b0", "mit_b1", "mit_b2", "mit_b3", "mit_b4", "mit_b5", "mit_b0_imagenet", "segformer_b0", "segformer_b1", "segformer_b2", "segformer_b3", "segformer_b4", "segformer_b5", "segformer_b0_imagenet". If looking for a preset with pretrained weights, choose one of "segformer_b0_imagenet".
• load_weights: Whether to load pre-trained weights into model. Defaults to None, which follows whether the preset has pretrained weights available.
• input_shape : input shape that will be passed to backbone initialization, Defaults to None.If None, the preset value will be used.

Examples

# Load architecture and weights from preset
model = keras_cv.models.SegFormer.from_preset(
    "segformer_b0_imagenet",
)

# Load randomly initialized model from preset architecture with weights
model = keras_cv.models.SegFormer.from_preset(
    "segformer_b0_imagenet",
    load_weights=False,