Skip to content

Grounding DINO

The Grounding DINO model extends a closed-set object detection model with a text encoder, enabling open-set object detection. RBLN NPUs can accelerate Grounding DINO model inference using Optimum RBLN.

API Reference

Classes

RBLNGroundingDinoTextModel

Bases: RBLNBertModel

RBLN optimized text backbone (BERT) of Grounding DINO.

the text self-attention mask is a prepared 4D additive float bias (upstream GroundingDinoModel applies a "3D -> 4D correction (add head dim)" before the text backbone).

Methods:

from_pretrained(model_id, export=None, 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 Optional[bool]

A boolean flag to indicate whether the model should be compiled. If None, it will be determined based on the existence of the compiled model files in the model_id.

 None
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 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
RBLNModel

A RBLN model instance ready for inference on RBLN NPU devices.
save_pretrained(save_directory, push_to_hub=False, **kwargs)

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

Parameters:

Name Type Description Default
save_directory Union[str, Path]

Directory where to save the model file.

 required
push_to_hub bool

Whether or not to push your model to the HuggingFace model hub after saving it.

 False
from_model(model, config=None, rbln_config=None, model_save_dir=None, subfolder='', **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
config Optional[PretrainedConfig]

The configuration object associated with the model.

 None
rbln_config Optional[Union[RBLNModelConfig, Dict]]

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 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
RBLNModel

A RBLN model instance ready for inference on RBLN NPU devices.
forward(input_ids=None, attention_mask=None, token_type_ids=None, position_ids=None, **kwargs)

Forward pass for the RBLN-optimized BERT model for feature extraction tasks.

Parameters:

Name Type Description Default
input_ids torch.Tensor of shape (batch_size, sequence_length)

Indices of input sequence tokens in the vocabulary.

 None
attention_mask torch.Tensor of shape (batch_size, sequence_length)

Mask to avoid performing attention on padding token indices.

 None
token_type_ids torch.Tensor of shape (batch_size, sequence_length)

Segment token indices to indicate first and second portions of the inputs.

 None
position_ids torch.Tensor of shape (batch_size, sequence_length)

Indices of positions of each input sequence tokens in the position embeddings.

 None

Returns:

Type Description
Union[BaseModelOutputWithPoolingAndCrossAttentions, Tuple]

The model outputs. If return_dict=False is passed, returns a tuple of tensors. Otherwise, returns a BaseModelOutputWithPoolingAndCrossAttentions object.

RBLNGroundingDinoForObjectDetection

Bases: RBLNModel

Methods:

from_model(model, config=None, rbln_config=None, model_save_dir=None, subfolder='', **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
config Optional[PretrainedConfig]

The configuration object associated with the model.

 None
rbln_config Optional[Union[RBLNModelConfig, Dict]]

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 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
RBLNModel

A RBLN model instance ready for inference on RBLN NPU devices.
forward(pixel_values, input_ids, token_type_ids=None, attention_mask=None, pixel_mask=None, encoder_outputs=None, output_attentions=None, output_hidden_states=None, return_dict=None, **kwargs)

Forward pass for the RBLN-optimized GroundingDinoForObjectDetection model.

Parameters:

Name Type Description Default
pixel_values torch.Tensor of shape (batch_size, num_channels, image_size, image_size)

The tensors corresponding to the input images.

 required
input_ids torch.LongTensor of shape (batch_size, text_sequence_length)

Indices of input sequence tokens in the vocabulary. Padding will be ignored by default should you provide it.

 required
token_type_ids torch.LongTensor of shape (batch_size, text_sequence_length)

Segment token indices to indicate first and second portions of the inputs.

 None
attention_mask torch.Tensor of shape (batch_size, sequence_length)

Mask to avoid performing attention on padding token indices.

 None
pixel_mask torch.Tensor of shape (batch_size, height, width)

Mask to avoid performing attention on padding pixel values.

 None
encoder_outputs Tuple consists of last_hidden_state of shape(batch_size, sequence_length, hidden_size)

A sequence of hidden-states at the output of the last layer of the encoder.

 None
output_attentions bool

Whether or not to return the attentions tensors of all attention layers.

 None
output_hidden_states bool

Whether or not to return the hidden states of all layers.

 None
return_dict bool

Whether or not to return a ModelOutput instead of a plain tuple.

 None

Returns:

Type Description
Union[GroundingDinoObjectDetectionOutput, Tuple]

The model outputs. If return_dict=False is passed, returns a tuple of tensors. Otherwise, returns a GroundingDinoObjectDetectionOutput object.
from_pretrained(model_id, export=None, 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 Optional[bool]

A boolean flag to indicate whether the model should be compiled. If None, it will be determined based on the existence of the compiled model files in the model_id.

 None
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 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
RBLNModel

A RBLN model instance ready for inference on RBLN NPU devices.
save_pretrained(save_directory, push_to_hub=False, **kwargs)

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

Parameters:

Name Type Description Default
save_directory Union[str, Path]

Directory where to save the model file.

 required
push_to_hub bool

Whether or not to push your model to the HuggingFace model hub after saving it.

 False

RBLNGroundingDinoEncoder

Bases: RBLNModel

Methods:

from_model(model, config=None, rbln_config=None, model_save_dir=None, subfolder='', **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
config Optional[PretrainedConfig]

The configuration object associated with the model.

 None
rbln_config Optional[Union[RBLNModelConfig, Dict]]

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 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
RBLNModel

A RBLN model instance ready for inference on RBLN NPU devices.
from_pretrained(model_id, export=None, 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 Optional[bool]

A boolean flag to indicate whether the model should be compiled. If None, it will be determined based on the existence of the compiled model files in the model_id.

 None
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 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
RBLNModel

A RBLN model instance ready for inference on RBLN NPU devices.
save_pretrained(save_directory, push_to_hub=False, **kwargs)

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

Parameters:

Name Type Description Default
save_directory Union[str, Path]

Directory where to save the model file.

 required
push_to_hub bool

Whether or not to push your model to the HuggingFace model hub after saving it.

 False

RBLNGroundingDinoDecoder

Bases: RBLNModel

Methods:

from_model(model, config=None, rbln_config=None, model_save_dir=None, subfolder='', **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
config Optional[PretrainedConfig]

The configuration object associated with the model.

 None
rbln_config Optional[Union[RBLNModelConfig, Dict]]

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 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
RBLNModel

A RBLN model instance ready for inference on RBLN NPU devices.
from_pretrained(model_id, export=None, 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 Optional[bool]

A boolean flag to indicate whether the model should be compiled. If None, it will be determined based on the existence of the compiled model files in the model_id.

 None
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 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
RBLNModel

A RBLN model instance ready for inference on RBLN NPU devices.
save_pretrained(save_directory, push_to_hub=False, **kwargs)

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

Parameters:

Name Type Description Default
save_directory Union[str, Path]

Directory where to save the model file.

 required
push_to_hub bool

Whether or not to push your model to the HuggingFace model hub after saving it.

 False

Classes

RBLNGroundingDinoTextModelConfig

Bases: RBLNModelConfig

Methods:

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

Parameters:

Name Type Description Default
batch_size Optional[int]

The batch size for text processing. Defaults to 1.

 None
max_text_len Optional[int]

Maximum text sequence length. Defaults to the parent GroundingDino config's max_text_len.

 None
kwargs Any

Additional arguments passed to the parent RBLNModelConfig.

 {}
from_pretrained(path, rbln_config=None, return_unused_kwargs=False, **kwargs) classmethod

Load a RBLNModelConfig from a path.

Parameters:

Name Type Description Default
path str

Path to the RBLNModelConfig file or directory containing the config file.

 required
rbln_config Optional[Dict[str, Any]]

Additional configuration to override.

 None
return_unused_kwargs bool

Whether to return unused kwargs.

 False
kwargs Optional[Dict[str, Any]]

Additional keyword arguments to override configuration values. Keys starting with 'rbln_' will have the prefix removed and be used to update the configuration.

 {}

Returns:

Name Type Description
RBLNModelConfig Union[RBLNModelConfig, Tuple[RBLNModelConfig, Dict[str, Any]]]

The loaded configuration instance.
Note

This method loads the configuration from the specified path and applies any provided overrides. If the loaded configuration class doesn't match the expected class, a warning will be logged.

Examples:

1
config = RBLNResNetForImageClassificationConfig.from_pretrained("/path/to/model")
load(path, rbln_config=None, return_unused_kwargs=False, **kwargs) classmethod

Load a RBLNModelConfig from a path.

Deprecated

This method is deprecated and will be removed in version 0.11.0. Use from_pretrained instead.

Parameters:

Name Type Description Default
path str

Path to the RBLNModelConfig file or directory containing the config file.

 required
rbln_config Optional[Dict[str, Any]]

Additional configuration to override.

 None
return_unused_kwargs bool

Whether to return unused kwargs.

 False
kwargs Optional[Dict[str, Any]]

Additional keyword arguments to override configuration values. Keys starting with 'rbln_' will have the prefix removed and be used to update the configuration.

 {}

Returns:

Name Type Description
RBLNModelConfig Union[RBLNModelConfig, Tuple[RBLNModelConfig, Dict[str, Any]]]

The loaded configuration instance.
Note

This method loads the configuration from the specified path and applies any provided overrides. If the loaded configuration class doesn't match the expected class, a warning will be logged.

Examples:

1
2
3
4
# Deprecated usage:
config = RBLNResNetForImageClassificationConfig.load("/path/to/model")
# Recommended usage:
config = RBLNResNetForImageClassificationConfig.from_pretrained("/path/to/model")

RBLNGroundingDinoForObjectDetectionConfig

Bases: RBLNImageModelConfig

Methods:

__init__(batch_size=None, encoder=None, decoder=None, text_backbone=None, backbone=None, output_attentions=None, output_hidden_states=None, **kwargs)

Parameters:

Name Type Description Default
batch_size Optional[int]

The batch size for image and text processing. Defaults to 1.

 None
encoder Optional[RBLNModelConfig]

The encoder configuration. Defaults to None.

 None
decoder Optional[RBLNModelConfig]

The decoder configuration. Defaults to None.

 None
text_backbone Optional[RBLNModelConfig]

The text backbone configuration. Defaults to None.

 None
backbone Optional[RBLNModelConfig]

The backbone configuration. Defaults to None.

 None
output_attentions Optional[bool]

Whether to output attentions. Defaults to None.

 None
output_hidden_states Optional[bool]

Whether to output hidden states. Defaults to None.

 None
kwargs Any

Additional arguments passed to the parent RBLNModelConfig.

 {}

Raises:

Type Description
ValueError

If batch_size is not a positive integer.
from_pretrained(path, rbln_config=None, return_unused_kwargs=False, **kwargs) classmethod

Load a RBLNModelConfig from a path.

Parameters:

Name Type Description Default
path str

Path to the RBLNModelConfig file or directory containing the config file.

 required
rbln_config Optional[Dict[str, Any]]

Additional configuration to override.

 None
return_unused_kwargs bool

Whether to return unused kwargs.

 False
kwargs Optional[Dict[str, Any]]

Additional keyword arguments to override configuration values. Keys starting with 'rbln_' will have the prefix removed and be used to update the configuration.

 {}

Returns:

Name Type Description
RBLNModelConfig Union[RBLNModelConfig, Tuple[RBLNModelConfig, Dict[str, Any]]]

The loaded configuration instance.
Note

This method loads the configuration from the specified path and applies any provided overrides. If the loaded configuration class doesn't match the expected class, a warning will be logged.

Examples:

1
config = RBLNResNetForImageClassificationConfig.from_pretrained("/path/to/model")
load(path, rbln_config=None, return_unused_kwargs=False, **kwargs) classmethod

Load a RBLNModelConfig from a path.

Deprecated

This method is deprecated and will be removed in version 0.11.0. Use from_pretrained instead.

Parameters:

Name Type Description Default
path str

Path to the RBLNModelConfig file or directory containing the config file.

 required
rbln_config Optional[Dict[str, Any]]

Additional configuration to override.

 None
return_unused_kwargs bool

Whether to return unused kwargs.

 False
kwargs Optional[Dict[str, Any]]

Additional keyword arguments to override configuration values. Keys starting with 'rbln_' will have the prefix removed and be used to update the configuration.

 {}

Returns:

Name Type Description
RBLNModelConfig Union[RBLNModelConfig, Tuple[RBLNModelConfig, Dict[str, Any]]]

The loaded configuration instance.
Note

This method loads the configuration from the specified path and applies any provided overrides. If the loaded configuration class doesn't match the expected class, a warning will be logged.

Examples:

1
2
3
4
# Deprecated usage:
config = RBLNResNetForImageClassificationConfig.load("/path/to/model")
# Recommended usage:
config = RBLNResNetForImageClassificationConfig.from_pretrained("/path/to/model")