Spaces:
Sleeping
Sleeping
File size: 4,669 Bytes
ddda863 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 |
import os
from typing import Union, Tuple
import base64
from pathlib import Path
# 3rd party
import numpy as np
import cv2
import requests
def load_image(img: Union[str, np.ndarray]) -> Tuple[np.ndarray, str]:
"""
Load image from path, url, base64 or numpy array.
Args:
img: a path, url, base64 or numpy array.
Returns:
image (numpy array): the loaded image in BGR format
image name (str): image name itself
"""
# The image is already a numpy array
if isinstance(img, np.ndarray):
return img, "numpy array"
if isinstance(img, Path):
img = str(img)
if not isinstance(img, str):
raise ValueError(f"img must be numpy array or str but it is {type(img)}")
# The image is a base64 string
if img.startswith("data:image/"):
return load_base64(img), "base64 encoded string"
# The image is a url
if img.lower().startswith("http://") or img.lower().startswith("https://"):
return load_image_from_web(url=img), img
# The image is a path
if os.path.isfile(img) is not True:
raise ValueError(f"Confirm that {img} exists")
# image must be a file on the system then
# image name must have english characters
if img.isascii() is False:
raise ValueError(f"Input image must not have non-english characters - {img}")
img_obj_bgr = cv2.imread(img)
# img_obj_rgb = cv2.cvtColor(img_obj_bgr, cv2.COLOR_BGR2RGB)
return img_obj_bgr, img
def load_image_from_web(url: str) -> np.ndarray:
"""
Loading an image from web
Args:
url: link for the image
Returns:
img (np.ndarray): equivalent to pre-loaded image from opencv (BGR format)
"""
response = requests.get(url, stream=True, timeout=60)
response.raise_for_status()
image_array = np.asarray(bytearray(response.raw.read()), dtype=np.uint8)
image = cv2.imdecode(image_array, cv2.IMREAD_COLOR)
return image
def load_base64(uri: str) -> np.ndarray:
"""Load image from base64 string.
Args:
uri: a base64 string.
Returns:
numpy array: the loaded image.
"""
encoded_data_parts = uri.split(",")
if len(encoded_data_parts) < 2:
raise ValueError("format error in base64 encoded string")
# similar to find functionality, we are just considering these extensions
if not (
uri.startswith("data:image/jpeg")
or uri.startswith("data:image/jpg")
or uri.startswith("data:image/png")
):
raise ValueError(f"input image can be jpg, jpeg or png, but it is {encoded_data_parts}")
encoded_data = encoded_data_parts[1]
nparr = np.fromstring(base64.b64decode(encoded_data), np.uint8)
img_bgr = cv2.imdecode(nparr, cv2.IMREAD_COLOR)
# img_rgb = cv2.cvtColor(img_bgr, cv2.COLOR_BGR2RGB)
return img_bgr
def normalize_input(img: np.ndarray, normalization: str = "base") -> np.ndarray:
"""Normalize input image.
Args:
img (numpy array): the input image.
normalization (str, optional): the normalization technique. Defaults to "base",
for no normalization.
Returns:
numpy array: the normalized image.
"""
# issue 131 declares that some normalization techniques improves the accuracy
if normalization == "base":
return img
# @trevorgribble and @davedgd contributed this feature
# restore input in scale of [0, 255] because it was normalized in scale of
# [0, 1] in preprocess_face
img *= 255
if normalization == "raw":
pass # return just restored pixels
elif normalization == "Facenet":
mean, std = img.mean(), img.std()
img = (img - mean) / std
elif normalization == "Facenet2018":
# simply / 127.5 - 1 (similar to facenet 2018 model preprocessing step as @iamrishab posted)
img /= 127.5
img -= 1
elif normalization == "VGGFace":
# mean subtraction based on VGGFace1 training data
img[..., 0] -= 93.5940
img[..., 1] -= 104.7624
img[..., 2] -= 129.1863
elif normalization == "VGGFace2":
# mean subtraction based on VGGFace2 training data
img[..., 0] -= 91.4953
img[..., 1] -= 103.8827
img[..., 2] -= 131.0912
elif normalization == "ArcFace":
# Reference study: The faces are cropped and resized to 112×112,
# and each pixel (ranged between [0, 255]) in RGB images is normalised
# by subtracting 127.5 then divided by 128.
img -= 127.5
img /= 128
else:
raise ValueError(f"unimplemented normalization type - {normalization}")
return img
|