transformers_4_35_0/pipelines/depth_estimation.py

from typing import List, Union

import numpy as np

from ..utils import add_end_docstrings, 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_torch_available():
    import torch

    from ..models.auto.modeling_auto import MODEL_FOR_DEPTH_ESTIMATION_MAPPING_NAMES

logger = logging.get_logger(__name__)


@add_end_docstrings(PIPELINE_INIT_ARGS)
class DepthEstimationPipeline(Pipeline):
    """
    Depth estimation pipeline using any `AutoModelForDepthEstimation`. This pipeline predicts the depth of an image.

    Example:

    ```python
    >>> from transformers import pipeline

    >>> depth_estimator = pipeline(task="depth-estimation", model="Intel/dpt-large")
    >>> output = depth_estimator("http://images.cocodataset.org/val2017/000000039769.jpg")
    >>> # This is a tensor with the values being the depth expressed in meters for each pixel
    >>> output["predicted_depth"].shape
    torch.Size([1, 384, 384])
    ```

    Learn more about the basics of using a pipeline in the [pipeline tutorial](../pipeline_tutorial)


    This depth estimation pipeline can currently be loaded from [`pipeline`] using the following task identifier:
    `"depth-estimation"`.

    See the list of available models on [huggingface.co/models](https://huggingface.co/models?filter=depth-estimation).
    """

    def __init__(self, *args, **kwargs):
        super().__init__(*args, **kwargs)
        requires_backends(self, "vision")
        self.check_model_type(MODEL_FOR_DEPTH_ESTIMATION_MAPPING_NAMES)

    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 _sanitize_parameters(self, timeout=None, **kwargs):
        preprocess_params = {}
        if timeout is not None:
            preprocess_params["timeout"] = timeout
        return preprocess_params, {}, {}

    def preprocess(self, image, timeout=None):
        image = load_image(image, timeout)
        self.image_size = image.size
        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):
        predicted_depth = model_outputs.predicted_depth
        prediction = torch.nn.functional.interpolate(
            predicted_depth.unsqueeze(1), size=self.image_size[::-1], mode="bicubic", align_corners=False
        )
        output = prediction.squeeze().cpu().numpy()
        formatted = (output * 255 / np.max(output)).astype("uint8")
        depth = Image.fromarray(formatted)
        output_dict = {}
        output_dict["predicted_depth"] = predicted_depth
        output_dict["depth"] = depth
        return output_dict