Skip to content

DPT

The DPT (Dense Prediction Transformer) is a vision model for dense prediction tasks like depth estimation. It combines Vision Transformer (ViT) features with a specialized decoder for accurate pixel-level predictions. RBLN NPUs can accelerate DPT model inference using Optimum RBLN.

Key Classes

API Reference

Classes

RBLNDPTForDepthEstimation

Bases: RBLNModelForDepthEstimation

DPT (Dense Prediction Transformer) model optimized for depth estimation on RBLN NPUs.

Functions

from_pretrained(model_id, export=False, rbln_config=None, **kwargs) classmethod

The from_pretrained() function is utilized in its standard form as in the HuggingFace transformers library. User can use this function to load a pre-trained model from the HuggingFace library and convert it to a RBLN model to be run on RBLN NPUs.

Parameters:

Name Type Description Default
model_id Union[str, Path]

The model id of the pre-trained model to be loaded. It can be downloaded from the HuggingFace model hub or a local path, or a model id of a compiled model using the RBLN Compiler.

required
export bool

A boolean flag to indicate whether the model should be compiled.

False
rbln_config Optional[Union[Dict, RBLNModelConfig]]

Configuration for RBLN model compilation and runtime. This can be provided as a dictionary or an instance of the model's configuration class (e.g., RBLNLlamaForCausalLMConfig for Llama models). For detailed configuration options, see the specific model's configuration class documentation.

None
kwargs Dict[str, Any]

Additional keyword arguments. Arguments with the prefix 'rbln_' are passed to rbln_config, while the remaining arguments are passed to the HuggingFace library.

{}

Returns:

Type Description
Self

A RBLN model instance ready for inference on RBLN NPU devices.

from_model(model, *, rbln_config=None, **kwargs) classmethod

Converts and compiles a pre-trained HuggingFace library model into a RBLN model. This method performs the actual model conversion and compilation process.

Parameters:

Name Type Description Default
model PreTrainedModel

The PyTorch model to be compiled. The object must be an instance of the HuggingFace transformers PreTrainedModel class.

required
rbln_config Optional[Union[Dict, RBLNModelConfig]]

Configuration for RBLN model compilation and runtime. This can be provided as a dictionary or an instance of the model's configuration class (e.g., RBLNLlamaForCausalLMConfig for Llama models). For detailed configuration options, see the specific model's configuration class documentation.

None
kwargs Dict[str, Any]

Additional keyword arguments. Arguments with the prefix 'rbln_' are passed to rbln_config, while the remaining arguments are passed to the HuggingFace library.

{}

The method performs the following steps:

  1. Compiles the PyTorch model into an optimized RBLN graph
  2. Configures the model for the specified NPU device
  3. Creates the necessary runtime objects if requested
  4. Saves the compiled model and configurations

Returns:

Type Description
Self

A RBLN model instance ready for inference on RBLN NPU devices.

save_pretrained(save_directory)

Saves a model and its configuration file to a directory, so that it can be re-loaded using the [from_pretrained] class method.

Parameters:

Name Type Description Default
save_directory Union[str, PathLike]

The directory to save the model and its configuration files. Will be created if it doesn't exist.

required

Classes

RBLNDPTForDepthEstimationConfig

Bases: RBLNModelForDepthEstimationConfig

Configuration class for RBLNDPTForDepthEstimation models.

This class an alias of RBLNModelForDepthEstimationConfig.

Functions

__init__(image_size=None, batch_size=None, **kwargs)

Base configuration class for image models running on RBLN NPUs.

This class extends the RBLNModelConfig to include parameters specific to image models, such as image dimensions and batch sizes for inference.

Parameters:

Name Type Description Default
image_size Optional[Union[int, Tuple[int, int]]]

The size of input images. Can be an integer for square images or a tuple (height, width).

None
batch_size Optional[int]

The batch size for inference. Defaults to 1.

None
**kwargs Dict[str, Any]

Additional arguments passed to the parent RBLNModelConfig.

{}

Raises:

Type Description
ValueError

If batch_size is not a positive integer.