hezar.models.backbone.vit.vit module

class hezar.models.backbone.vit.vit.ViT(config: ViTConfig, **kwargs)

Bases: Model

forward(pixel_values=None, bool_masked_pos=None, head_mask=None, output_attentions=None, output_hidden_states=None, interpolate_pos_encoding=None)

Forward inputs through the model and return logits, etc.

Parameters:

model_inputs – The required inputs for the model forward

Returns:

A dict of outputs like logits, loss, etc.

image_processor = 'image_processor'

loss_func_name: str | LossType = 'cross_entropy'

post_process(model_outputs: Dict[str, Tensor])

Process model outputs and return human-readable results. Called in self.predict()

Parameters:

• model_outputs – model outputs to process

• **kwargs – extra arguments specific to the derived class

Returns:

Processed model output values and converted to human-readable results

preprocess(inputs: List[str] | List[np.ndarray] | List['Image'] | List[torch.Tensor], **kwargs)

Given raw inputs, preprocess the inputs and prepare them for model’s forward().

Parameters:

• raw_inputs – Raw model inputs

• **kwargs – Extra kwargs specific to the model. See the model’s specific class for more info

Returns:

A dict of inputs for model forward

required_backends: List[Backends | str] = [Backends.TRANSFORMERS, Backends.TOKENIZERS, Backends.PILLOW]