File size: 4,573 Bytes
d1ceb73 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 |
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, build_pipeline_init_args
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(build_pipeline_init_args(has_image_processor=True))
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="LiheYoung/depth-anything-base-hf")
>>> 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):
"""
Predict the depth(s) of 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.
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:
- **predicted_depth** (`torch.Tensor`) -- The predicted depth by the model as a `torch.Tensor`.
- **depth** (`PIL.Image`) -- The predicted depth by the model as a `PIL.Image`.
"""
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)
if self.framework == "pt":
model_inputs = model_inputs.to(self.torch_dtype)
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
|