RyzenAIModel

optimum.amd.ryzenai.pipeline

( task model: Optional = None vaip_config: Optional = None model_type: Optional = None feature_extractor: Union = None image_processor: Union = None use_fast: bool = True token: Union = None revision: Optional = None **kwargs ) → Pipeline

Parameters

task (str) — The task defining which pipeline will be returned. Available tasks include:
- “image-classification”
- “object-detection”
model (Optional[Any], defaults to None) — The model that will be used by the pipeline to make predictions. This can be a model identifier or an actual instance of a pretrained model. If not provided, the default model for the specified task will be loaded.
vaip_config (Optional[str], defaults to None) — Runtime configuration file for inference with Ryzen IPU. A default config file can be found in the Ryzen AI VOE package, extracted during installation under the name vaip_config.json.
model_type (Optional[str], defaults to None) — Model type for the model
feature_extractor (Union[str, "PreTrainedFeatureExtractor"], defaults to None) — The feature extractor that will be used by the pipeline to encode data for the model. This can be a model identifier or an actual pretrained feature extractor.
image_processor (Union[str, BaseImageProcessor], defaults to None) — The image processor that will be used by the pipeline for image-related tasks.
use_fast (bool, defaults to True) — Whether or not to use a Fast tokenizer if possible.
token (Union[str, bool], defaults to None) — The token to use as HTTP bearer authorization for remote files. If True, will use the token generated when running huggingface-cli login (stored in ~/.huggingface).
revision (str, defaults to None) — The specific model version to use, specified as a branch name, tag name, or commit id. **kwargs — Additional keyword arguments passed to the underlying pipeline class.

Returns

Pipeline

An instance of the specified pipeline for the given task and model.

Utility method to build a pipeline for various RyzenAI tasks.

This function creates a pipeline for a specified task, utilizing a given model or loading the default model for the task. The pipeline includes components such as a image processor and model.

Computer vision

class optimum.amd.ryzenai.pipelines.TimmImageClassificationPipeline

< source >

( model: Union tokenizer: Optional = None feature_extractor: Optional = None image_processor: Optional = None processor: Optional = None modelcard: Optional = None framework: Optional = None task: str = '' args_parser: ArgumentHandler = None device: Union = None torch_dtype: Union = None binary_output: bool = False **kwargs )

Example usage:

import requests
from PIL import Image

from optimum.amd.ryzenai import pipeline

url = "http://images.cocodataset.org/val2017/000000039769.jpg"
image = Image.open(requests.get(url, stream=True).raw)

model_id = "mohitsha/timm-resnet18-onnx-quantized-ryzen"

pipe = pipeline("image-classification", model=model_id, vaip_config="vaip_config.json")
print(pipe(image))

class optimum.amd.ryzenai.pipelines.YoloObjectDetectionPipeline