HGNetV2ImageClassifier model

[source]

HGNetV2ImageClassifier class

keras_hub.models.HGNetV2ImageClassifier(
    backbone,
    preprocessor,
    num_classes,
    head_filters=None,
    pooling="avg",
    activation=None,
    dropout=0.0,
    head_dtype=None,
    **kwargs
)

HGNetV2 image classification model.

HGNetV2ImageClassifier wraps a HGNetV2Backbone and a HGNetV2ImageClassifierPreprocessor to create a model that can be used for image classification tasks. This model implements the HGNetV2 architecture with an additional classification head including a 1x1 convolution layer, global pooling, and a dense output layer.

The model takes an additional num_classes argument, controlling the number of predicted output classes, and optionally, a head_filters argument to specify the number of filters in the classification head's convolution layer. To fine-tune with fit(), pass a dataset containing tuples of (x, y) labels where x is an image tensor and y is an integer from [0, num_classes).

Arguments

• backbone: A HGNetV2Backbone instance.
• preprocessor: A HGNetV2ImageClassifierPreprocessor instance, a keras.Layer instance, or a callable. If None no preprocessing will be applied to the inputs.
• num_classes: int. The number of classes to predict.
• head_filters: int, optional. The number of filters in the classification head's 1x1 convolution layer. If None, it defaults to the last value of hidden_sizes from the backbone.
• pooling: "avg" or "max". The type of global pooling to apply after the head convolution. Defaults to "avg".
• activation: None, str, or callable. The activation function to use on the final Dense layer. Set activation=None to return the output logits. Defaults to None.
• dropout: float. Dropout rate applied before the final dense layer. Defaults to 0.0.
• head_dtype: None, str, or keras.mixed_precision.DTypePolicy. The dtype to use for the classification head's computations and weights.

Examples

Call predict() to run inference.

# Load preset and predict.
images = np.random.randint(0, 256, size=(2, 224, 224, 3))
classifier = keras_hub.models.HGNetV2ImageClassifier.from_preset(
    "hgnetv2_b5_ssld_stage2_ft_in1k"
)
classifier.predict(images)

Call fit() on a single batch.

# Load preset and train.
images = np.random.randint(0, 256, size=(2, 224, 224, 3))
labels = [0, 3]
classifier = keras_hub.models.HGNetV2ImageClassifier.from_preset(
    "hgnetv2_b5_ssld_stage2_ft_in1k"
)
classifier.fit(x=images, y=labels, batch_size=2)

Call fit() with custom loss, optimizer and frozen backbone.

classifier = keras_hub.models.HGNetV2ImageClassifier.from_preset(
    "hgnetv2_b5_ssld_stage2_ft_in1k"
)
classifier.compile(
    loss=keras.losses.SparseCategoricalCrossentropy(from_logits=True),
    optimizer=keras.optimizers.Adam(5e-5),
)
classifier.backbone.trainable = False
classifier.fit(x=images, y=labels, batch_size=2)

Create a custom HGNetV2 classifier with specific head configuration.

backbone = keras_hub.models.HGNetV2Backbone.from_preset(
    "hgnetv2_b5_ssld_stage2_ft_in1k"
)
preproc = keras_hub.models.HGNetV2ImageClassifierPreprocessor.from_preset(
    "hgnetv2_b5_ssld_stage2_ft_in1k"
)
classifier = keras_hub.models.HGNetV2ImageClassifier(
    backbone=backbone,
    preprocessor=preproc,
    num_classes=10,
    pooling="avg",
    dropout=0.2,
)

[source]

from_preset method

HGNetV2ImageClassifier.from_preset(preset, load_weights=True, **kwargs)

Instantiate a keras_hub.models.Task from a model preset.

A preset is a directory of configs, weights and other file assets used to save and load a pre-trained model. The preset can be passed as one of:

1. a built-in preset identifier like 'bert_base_en'
2. a Kaggle Models handle like 'kaggle://user/bert/keras/bert_base_en'
3. a Hugging Face handle like 'hf://user/bert_base_en'
4. a path to a local preset directory like './bert_base_en'

For any Task subclass, you can run cls.presets.keys() to list all built-in presets available on the class.

This constructor can be called in one of two ways. Either from a task specific base class like keras_hub.models.CausalLM.from_preset(), or from a model class like keras_hub.models.BertTextClassifier.from_preset(). If calling from the a base class, the subclass of the returning object will be inferred from the config in the preset directory.

Arguments

• preset: string. A built-in preset identifier, a Kaggle Models handle, a Hugging Face handle, or a path to a local directory.
• load_weights: bool. If True, saved weights will be loaded into the model architecture. If False, all weights will be randomly initialized.

Examples

# Load a Gemma generative task.
causal_lm = keras_hub.models.CausalLM.from_preset(
    "gemma_2b_en",
)

# Load a Bert classification task.
model = keras_hub.models.TextClassifier.from_preset(
    "bert_base_en",
    num_classes=2,
)

backbone property

keras_hub.models.HGNetV2ImageClassifier.backbone

A keras_hub.models.Backbone model with the core architecture.

preprocessor property

keras_hub.models.HGNetV2ImageClassifier.preprocessor

A keras_hub.models.Preprocessor layer used to preprocess input.