mart9992's picture
m
4c65bff
raw
history blame
4.66 kB
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