The RetinaNet model

[source]

RetinaNet class

keras_cv.models.RetinaNet(
    backbone,
    num_classes,
    bounding_box_format,
    anchor_generator=None,
    label_encoder=None,
    prediction_decoder=None,
    classification_head=None,
    box_head=None,
    **kwargs
)

A Keras model implementing the RetinaNet meta-architecture.

Implements the RetinaNet architecture for object detection. The constructor requires num_classes, bounding_box_format, and a backbone. Optionally, a custom label encoder, and prediction decoder may be provided.

Examples

images = tf.ones(shape=(1, 512, 512, 3))
labels = {
    "boxes": [
        [
            [0, 0, 100, 100],
            [100, 100, 200, 200],
            [300, 300, 100, 100],
        ]
    ],
    "classes": [[1, 1, 1]],
}
model = keras_cv.models.RetinaNet(
    num_classes=20,
    bounding_box_format="xywh",
    backbone=keras_cv.models.ResNet50Backbone.from_preset(
        "resnet50_imagenet"
    )
)

# Evaluate model
model(images)

# Train model
model.compile(
    classification_loss='focal',
    box_loss='smoothl1',
    optimizer=tf.optimizers.SGD(global_clipnorm=10.0),
    jit_compile=False,
)
model.fit(images, labels)

Arguments

• num_classes: the number of classes in your dataset excluding the background class. Classes should be represented by integers in the range [0, num_classes).
• bounding_box_format: The format of bounding boxes of input dataset. Refer to the keras.io docs for more details on supported bounding box formats.
• backbone: keras.Model. Must implement the pyramid_level_inputs property with keys 3, 4, and 5 and layer names as values. A somewhat sensible backbone to use in many cases is the: keras_cv.models.ResNetBackbone.from_preset("resnet50_imagenet")
• anchor_generator: (Optional) a keras_cv.layers.AnchorGenerator. If provided, the anchor generator will be passed to both the label_encoder and the prediction_decoder. Only to be used when both label_encoder and prediction_decoder are both None. Defaults to an anchor generator with the parameterization: strides=[2**i for i in range(3, 8)], scales=[2**x for x in [0, 1 / 3, 2 / 3]], sizes=[32.0, 64.0, 128.0, 256.0, 512.0], and aspect_ratios=[0.5, 1.0, 2.0].
• label_encoder: (Optional) a keras.Layer that accepts an image Tensor, a bounding box Tensor and a bounding box class Tensor to its call() method, and returns RetinaNet training targets. By default, a KerasCV standard RetinaNetLabelEncoder is created and used. Results of this object's call() method are passed to the loss object for box_loss and classification_loss the y_true argument.
• prediction_decoder: (Optional) A keras.layers.Layer that is responsible for transforming RetinaNet predictions into usable bounding box Tensors. If not provided, a default is provided. The default prediction_decoder layer is a keras_cv.layers.MultiClassNonMaxSuppression layer, which uses a Non-Max Suppression for box pruning.
• classification_head: (Optional) A keras.Layer that performs classification of the bounding boxes. If not provided, a simple ConvNet with 3 layers will be used.
• box_head: (Optional) A keras.Layer that performs regression of the bounding boxes. If not provided, a simple ConvNet with 3 layers will be used.

[source]

from_preset method

RetinaNet.from_preset()

Instantiate RetinaNet model from preset architecture and weights.

Arguments

• preset: string. Must be one of "resnet18", "resnet34", "resnet50", "resnet101", "resnet152", "resnet18_v2", "resnet34_v2", "resnet50_v2", "resnet101_v2", "resnet152_v2", "mobilenet_v3_small", "mobilenet_v3_large", "csp_darknet_tiny", "csp_darknet_s", "csp_darknet_m", "csp_darknet_l", "csp_darknet_xl", "efficientnetv2_s", "efficientnetv2_m", "efficientnetv2_l", "efficientnetv2_b0", "efficientnetv2_b1", "efficientnetv2_b2", "efficientnetv2_b3", "resnet50_imagenet", "resnet50_v2_imagenet", "mobilenet_v3_large_imagenet", "csp_darknet_tiny_imagenet", "csp_darknet_l_imagenet", "efficientnetv2_s_imagenet", "efficientnetv2_b0_imagenet", "efficientnetv2_b1_imagenet", "efficientnetv2_b2_imagenet", "retinanet_resnet50_pascalvoc". If looking for a preset with pretrained weights, choose one of "resnet50_imagenet", "resnet50_v2_imagenet", "mobilenet_v3_large_imagenet", "csp_darknet_tiny_imagenet", "csp_darknet_l_imagenet", "efficientnetv2_s_imagenet", "efficientnetv2_b0_imagenet", "efficientnetv2_b1_imagenet", "efficientnetv2_b2_imagenet", "retinanet_resnet50_pascalvoc".
• load_weights: Whether to load pre-trained weights into model. Defaults to None, which follows whether the preset has pretrained weights available.

Examples

# Load architecture and weights from preset
model = keras_cv.models.RetinaNet.from_preset(
    "resnet50_imagenet",
)

# Load randomly initialized model from preset architecture with weights
model = keras_cv.models.RetinaNet.from_preset(
    "resnet50_imagenet",
    load_weights=False,