from typing import List, Union from ..utils import ( add_end_docstrings, is_tf_available, is_torch_available, is_vision_available, logging, requires_backends, ) from .base import PIPELINE_INIT_ARGS, Pipeline if is_vision_available(): from PIL import Image from ..image_utils import load_image if is_tf_available(): import tensorflow as tf from ..models.auto.modeling_tf_auto import TF_MODEL_FOR_IMAGE_CLASSIFICATION_MAPPING_NAMES from ..tf_utils import stable_softmax if is_torch_available(): from ..models.auto.modeling_auto import MODEL_FOR_IMAGE_CLASSIFICATION_MAPPING_NAMES logger = logging.get_logger(__name__) @add_end_docstrings(PIPELINE_INIT_ARGS) class ImageClassificationPipeline(Pipeline): """ Image classification pipeline using any `AutoModelForImageClassification`. This pipeline predicts the class of an image. Example: ```python >>> from transformers import pipeline >>> classifier = pipeline(model="microsoft/beit-base-patch16-224-pt22k-ft22k") >>> classifier("https://huggingface.co/datasets/Narsil/image_dummy/raw/main/parrots.png") [{'score': 0.442, 'label': 'macaw'}, {'score': 0.088, 'label': 'popinjay'}, {'score': 0.075, 'label': 'parrot'}, {'score': 0.073, 'label': 'parodist, lampooner'}, {'score': 0.046, 'label': 'poll, poll_parrot'}] ``` Learn more about the basics of using a pipeline in the [pipeline tutorial](../pipeline_tutorial) This image classification pipeline can currently be loaded from [`pipeline`] using the following task identifier: `"image-classification"`. See the list of available models on [huggingface.co/models](https://huggingface.co/models?filter=image-classification). """ def __init__(self, *args, **kwargs): super().__init__(*args, **kwargs) requires_backends(self, "vision") self.check_model_type( TF_MODEL_FOR_IMAGE_CLASSIFICATION_MAPPING_NAMES if self.framework == "tf" else MODEL_FOR_IMAGE_CLASSIFICATION_MAPPING_NAMES ) def _sanitize_parameters(self, top_k=None, timeout=None): preprocess_params = {} if timeout is not None: preprocess_params["timeout"] = timeout postprocess_params = {} if top_k is not None: postprocess_params["top_k"] = top_k return preprocess_params, {}, postprocess_params def __call__(self, images: Union[str, List[str], "Image.Image", List["Image.Image"]], **kwargs): """ Assign labels to the image(s) passed as inputs. Args: images (`str`, `List[str]`, `PIL.Image` or `List[PIL.Image]`): The pipeline handles three types of images: - A string containing a http link pointing to an image - A string containing a local path to an image - An image loaded in PIL directly The pipeline accepts either a single image or a batch of images, which must then be passed as a string. Images in a batch must all be in the same format: all as http links, all as local paths, or all as PIL images. top_k (`int`, *optional*, defaults to 5): The number of top labels that will be returned by the pipeline. If the provided number is higher than the number of labels available in the model configuration, it will default to the number of labels. timeout (`float`, *optional*, defaults to None): The maximum time in seconds to wait for fetching images from the web. If None, no timeout is set and the call may block forever. Return: A dictionary or a list of dictionaries containing result. If the input is a single image, will return a dictionary, if the input is a list of several images, will return a list of dictionaries corresponding to the images. The dictionaries contain the following keys: - **label** (`str`) -- The label identified by the model. - **score** (`int`) -- The score attributed by the model for that label. """ return super().__call__(images, **kwargs) def preprocess(self, image, timeout=None): image = load_image(image, timeout=timeout) model_inputs = self.image_processor(images=image, return_tensors=self.framework) return model_inputs def _forward(self, model_inputs): model_outputs = self.model(**model_inputs) return model_outputs def postprocess(self, model_outputs, top_k=5): if top_k > self.model.config.num_labels: top_k = self.model.config.num_labels if self.framework == "pt": probs = model_outputs.logits.softmax(-1)[0] scores, ids = probs.topk(top_k) elif self.framework == "tf": probs = stable_softmax(model_outputs.logits, axis=-1)[0] topk = tf.math.top_k(probs, k=top_k) scores, ids = topk.values.numpy(), topk.indices.numpy() else: raise ValueError(f"Unsupported framework: {self.framework}") scores = scores.tolist() ids = ids.tolist() return [{"score": score, "label": self.model.config.id2label[_id]} for score, _id in zip(scores, ids)]