Fix code example in RetinaNet class docstring

[DiegoMont]

Fix code example in RetinaNet class docstring

When running the code as it is currently written in the example (the imports are not in the example), an error is thrown:

images = np.ones((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 without box decoding and NMS
model(images)

# Prediction with box decoding and NMS
model.predict(images)

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

ValueError: Failed to find data adapter that can handle input: <class 'numpy.ndarray'>, (<class 'dict'> containing {"<class 'str'>"} keys and {'(<class \'list\'> containing values of types {\'(<class \\\'list\\\'> containing values of types {"<class \\\'int\\\'>"})\'})', '(<class \'list\'> containing values of types {\'(<class \\\'list\\\'> containing values of types {\\\'(<class \\\\\\\'list\\\\\\\'> containing values of types {"<class \\\\\\\'int\\\\\\\'>"})\\\'})\'})'} values)

This pull request adds a correction to the labels dictionary that fixes the error. I took how the dictionary is created from the definition of the unpackage_raw_tfds_inputs function in the Object Detection with KerasCV guide from keras.io

labels = {
    "boxes": tf.cast([
        [
            [0, 0, 100, 100],
            [100, 100, 200, 200],
            [300, 300, 100, 100],
        ]
    ], dtype=tf.float32),
    "classes": tf.cast([[1, 1, 1]], dtype=tf.float32),
}

Before submitting

• This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case).

Who can review?

Anyone in the community is free to review the PR once the tests have passed. Feel free to tag
members/contributors who may be interested in your PR.

[google-cla]

Thanks for your pull request! It looks like this may be your first contribution to a Google open source project. Before we can look at your pull request, you'll need to sign a Contributor License Agreement (CLA).

View this failed invocation of the CLA check for more information.

For the most up to date status, view the checks section at the bottom of the pull request.

[DiegoMont]

This pull request adds a correction to the labels dictionary that fixes the error. I took how the dictionary is created from the definition of the unpackage_raw_tfds_inputs function in the Object Detection with KerasCV guide from keras.io
@ianstenbit @jbischof

[ianstenbit]

Great, thank you for the fix!

[jbischof]

@ianstenbit do we want to reintroduce TF code?

[ianstenbit]

@ianstenbit do we want to reintroduce TF code?

I figure for the purpose of a code example this is fine. I thought about using ops instead but to new users that might be a bit confusing