Common¶
Common Vision Models 모듈은 RBLN NPU에서 다양한 비전 모델 구현에서 공유되는 기본 클래스와 유틸리티를 제공합니다.
주요 클래스¶
RBLNImageModel
: RBLN NPU에서 이미지 모델의 기본 클래스RBLNModelForDepthEstimation
: RBLN NPU에서 깊이 추정 모델의 기본 클래스RBLNModelForImageClassification
: RBLN NPU에서 이미지 분류 모델의 기본 클래스RBLNImageModelConfig
: 이미지 모델의 기본 구성 클래스RBLNModelForDepthEstimationConfig
: 깊이 추정 모델의 구성 클래스RBLNModelForImageClassificationConfig
: 이미지 분류 모델의 구성 클래스
API 참조¶
Classes¶
RBLNImageModel
¶
Bases: RBLNModel
Base class for RBLN vision models.
This class inherits from RBLNModel and serves as the foundation for specialized vision model implementations such as image classification and depth estimation models. It contains common functionalities shared across vision models optimized for 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., |
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., |
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:
- Compiles the PyTorch model into an optimized RBLN graph
- Configures the model for the specified NPU device
- Creates the necessary runtime objects if requested
- 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 |
RBLNModelForDepthEstimation
¶
Bases: RBLNImageModel
Base class for depth estimation models running on RBLN NPUs.
This class inherits from RBLNImageModel and provides specific functionality for models designed to predict depth information from input images.
Depth estimation models take images as input and output pixel-wise depth predictions, which can be used for 3D scene understanding, robotics, augmented reality, and more.
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., |
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., |
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:
- Compiles the PyTorch model into an optimized RBLN graph
- Configures the model for the specified NPU device
- Creates the necessary runtime objects if requested
- 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 |
RBLNModelForImageClassification
¶
Bases: RBLNImageModel
Base class for image classification models running on RBLN NPUs.
This class inherits from RBLNImageModel and provides specific functionality for models designed to classify images into predefined categories.
Image classification models take images as input and output class probabilities, which can be used for a wide range of computer vision applications.
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., |
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., |
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:
- Compiles the PyTorch model into an optimized RBLN graph
- Configures the model for the specified NPU device
- Creates the necessary runtime objects if requested
- 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¶
RBLNImageModelConfig
¶
Bases: RBLNModelConfig
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. |
RBLNModelForImageClassificationConfig
¶
Bases: RBLNImageModelConfig
Configuration class for image classification models running on RBLN NPUs.
This class inherits from _RBLNImageModelConfig and provides configuration options specific to image classification models. Image classification models categorize input images into one of several predefined classes.
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 _RBLNImageModelConfig. |
{}
|
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. |
RBLNModelForDepthEstimationConfig
¶
Bases: RBLNImageModelConfig
Configuration class for depth estimation models running on RBLN NPUs.
This class inherits from _RBLNImageModelConfig and provides configuration options specific to depth estimation models. Depth estimation models predict the distance of each pixel in an image from the camera, creating a depth map.
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). Recommended to specify this for optimal performance. |
None
|
batch_size
|
Optional[int]
|
The batch size for inference. Defaults to 1. |
None
|
**kwargs
|
Dict[str, Any]
|
Additional arguments passed to the parent _RBLNImageModelConfig. |
{}
|
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. |