BLIP2Seq2SeqLM model

[source]

BLIP2Seq2SeqLM class

keras_hub.models.BLIP2Seq2SeqLM(backbone, preprocessor=None, **kwargs)

An end-to-end multimodal BLIP-2 model for seq2seq language modeling.

This is the encoder-decoder (Flan-T5) BLIP-2 task. A seq2seq language model is conditioned on an input "context" — here the encoder text prompt plus a Q-Former visual soft-prompt distilled from the image — and the decoder autoregressively predicts the output text (e.g. a caption or VQA answer).

The forward pass runs the frozen vision encoder and the Q-Former once to obtain visual query features, projects and prepends them to the T5 encoder sequence, and decodes the answer. Because the underlying T5 stack does not support a key/value cache, generation recomputes the decoder at each step; the vision encoder and Q-Former are only run once per generate() call.

This model has a generate() method, which generates text based on the image and an optional encoder/decoder prompt. The generation strategy used is controlled by an additional sampler argument on compile(). By default, "greedy" sampling will be used.

This model can optionally be configured with a preprocessor layer, in which case it will automatically apply preprocessing to raw inputs during fit(), predict(), evaluate() and generate(). This is done by default when creating the model with from_preset().

Arguments

• backbone: A keras_hub.models.BLIP2Backbone instance whose language_model is a keras_hub.models.BLIP2FlanT5.
• preprocessor: A keras_hub.models.BLIP2Seq2SeqLMPreprocessor or None. If None, this model will not apply preprocessing, and inputs should be preprocessed before calling the model. Defaults to None.

[source]

from_preset method

BLIP2Seq2SeqLM.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,
)

[source]

generate method

BLIP2Seq2SeqLM.generate(
    inputs, max_length=None, stop_token_ids="auto", strip_prompt=False
)

Generate text given prompt inputs.

This method generates text based on given inputs. The sampling method used for generation can be set via the compile() method.

If inputs are a tf.data.Dataset, outputs will be generated "batch-by-batch" and concatenated. Otherwise, all inputs will be handled as a single batch.

If a preprocessor is attached to the model, inputs will be preprocessed inside the generate() function and should match the structure expected by the preprocessor layer (usually raw strings). If a preprocessor is not attached, inputs should match the structure expected by the backbone. See the example usage above for a demonstration of each.

Arguments

• inputs: python data, tensor data, or a tf.data.Dataset. If a preprocessor is attached to the model, inputs should match the structure expected by the preprocessor layer. If a preprocessor is not attached, inputs should match the structure expected the backbone model.
• max_length: Optional. int. The max length of the generated sequence. Will default to the max configured sequence_length of the preprocessor. If preprocessor is None, inputs should be should be padded to the desired maximum length and this argument will be ignored.
• stop_token_ids: Optional. None, "auto", or tuple of token ids. Defaults to "auto" which uses the preprocessor.tokenizer.end_token_id. Not specifying a processor will produce an error. None stops generation after generating max_length tokens. You may also specify a list of token id's the model should stop on. Note that sequences of tokens will each be interpreted as a stop token, multi-token stop sequences are not supported.
• strip_prompt: Optional. By default, generate() returns the full prompt followed by its completion generated by the model. If this option is set to True, only the newly generated text is returned.

backbone property

keras_hub.models.BLIP2Seq2SeqLM.backbone

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

preprocessor property

keras_hub.models.BLIP2Seq2SeqLM.preprocessor

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