Spaces:
Sleeping
Sleeping
File size: 5,032 Bytes
2673dcd c74a070 2673dcd c74a070 2673dcd c74a070 2673dcd c74a070 2673dcd c74a070 2673dcd c74a070 2673dcd c74a070 2673dcd c74a070 2673dcd c74a070 2673dcd c74a070 2673dcd c74a070 2673dcd c74a070 2673dcd c74a070 2673dcd c74a070 2673dcd c74a070 2673dcd c74a070 2673dcd c74a070 2673dcd |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 |
from pathlib import Path
import torch
import kornia
import cv2
import numpy as np
from typing import Union, List, Optional, Callable, Tuple
import collections.abc as collections
from types import SimpleNamespace
class ImagePreprocessor:
default_conf = {
"resize": None, # target edge length, None for no resizing
"side": "long",
"interpolation": "bilinear",
"align_corners": None,
"antialias": True,
"grayscale": False, # convert rgb to grayscale
}
def __init__(self, **conf) -> None:
super().__init__()
self.conf = {**self.default_conf, **conf}
self.conf = SimpleNamespace(**self.conf)
def __call__(self, img: torch.Tensor) -> Tuple[torch.Tensor, torch.Tensor]:
"""Resize and preprocess an image, return image and resize scale"""
h, w = img.shape[-2:]
if self.conf.resize is not None:
img = kornia.geometry.transform.resize(
img,
self.conf.resize,
side=self.conf.side,
antialias=self.conf.antialias,
align_corners=self.conf.align_corners,
)
scale = torch.Tensor([img.shape[-1] / w, img.shape[-2] / h]).to(img)
if self.conf.grayscale and img.shape[-3] == 3:
img = kornia.color.rgb_to_grayscale(img)
elif not self.conf.grayscale and img.shape[-3] == 1:
img = kornia.color.grayscale_to_rgb(img)
return img, scale
def map_tensor(input_, func: Callable):
string_classes = (str, bytes)
if isinstance(input_, string_classes):
return input_
elif isinstance(input_, collections.Mapping):
return {k: map_tensor(sample, func) for k, sample in input_.items()}
elif isinstance(input_, collections.Sequence):
return [map_tensor(sample, func) for sample in input_]
elif isinstance(input_, torch.Tensor):
return func(input_)
else:
return input_
def batch_to_device(batch: dict, device: str = "cpu", non_blocking: bool = True):
"""Move batch (dict) to device"""
def _func(tensor):
return tensor.to(device=device, non_blocking=non_blocking).detach()
return map_tensor(batch, _func)
def rbd(data: dict) -> dict:
"""Remove batch dimension from elements in data"""
return {
k: v[0] if isinstance(v, (torch.Tensor, np.ndarray, list)) else v
for k, v in data.items()
}
def read_image(path: Path, grayscale: bool = False) -> np.ndarray:
"""Read an image from path as RGB or grayscale"""
if not Path(path).exists():
raise FileNotFoundError(f"No image at path {path}.")
mode = cv2.IMREAD_GRAYSCALE if grayscale else cv2.IMREAD_COLOR
image = cv2.imread(str(path), mode)
if image is None:
raise IOError(f"Could not read image at {path}.")
if not grayscale:
image = image[..., ::-1]
return image
def numpy_image_to_torch(image: np.ndarray) -> torch.Tensor:
"""Normalize the image tensor and reorder the dimensions."""
if image.ndim == 3:
image = image.transpose((2, 0, 1)) # HxWxC to CxHxW
elif image.ndim == 2:
image = image[None] # add channel axis
else:
raise ValueError(f"Not an image: {image.shape}")
return torch.tensor(image / 255.0, dtype=torch.float)
def resize_image(
image: np.ndarray,
size: Union[List[int], int],
fn: str = "max",
interp: Optional[str] = "area",
) -> np.ndarray:
"""Resize an image to a fixed size, or according to max or min edge."""
h, w = image.shape[:2]
fn = {"max": max, "min": min}[fn]
if isinstance(size, int):
scale = size / fn(h, w)
h_new, w_new = int(round(h * scale)), int(round(w * scale))
scale = (w_new / w, h_new / h)
elif isinstance(size, (tuple, list)):
h_new, w_new = size
scale = (w_new / w, h_new / h)
else:
raise ValueError(f"Incorrect new size: {size}")
mode = {
"linear": cv2.INTER_LINEAR,
"cubic": cv2.INTER_CUBIC,
"nearest": cv2.INTER_NEAREST,
"area": cv2.INTER_AREA,
}[interp]
return cv2.resize(image, (w_new, h_new), interpolation=mode), scale
def load_image(path: Path, resize: int = None, **kwargs) -> torch.Tensor:
image = read_image(path)
if resize is not None:
image, _ = resize_image(image, resize, **kwargs)
return numpy_image_to_torch(image)
def match_pair(
extractor,
matcher,
image0: torch.Tensor,
image1: torch.Tensor,
device: str = "cpu",
**preprocess,
):
"""Match a pair of images (image0, image1) with an extractor and matcher"""
feats0 = extractor.extract(image0, **preprocess)
feats1 = extractor.extract(image1, **preprocess)
matches01 = matcher({"image0": feats0, "image1": feats1})
data = [feats0, feats1, matches01]
# remove batch dim and move to target device
feats0, feats1, matches01 = [batch_to_device(rbd(x), device) for x in data]
return feats0, feats1, matches01
|