File size: 5,256 Bytes
2878079 db1d921 2878079 db1d921 2878079 db1d921 2878079 db1d921 2878079 db1d921 2878079 db1d921 2878079 |
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 |
# These HF deployment codes refer to https://huggingface.co/not-lain/BiRefNet/raw/main/handler.py.
from typing import Dict, List, Any, Tuple
import os
import requests
from io import BytesIO
import cv2
import numpy as np
from PIL import Image
import torch
from torchvision import transforms
from transformers import AutoModelForImageSegmentation
torch.set_float32_matmul_precision(["high", "highest"][0])
device = "cuda" if torch.cuda.is_available() else "cpu"
### image_proc.py
def refine_foreground(image, mask, r=90):
if mask.size != image.size:
mask = mask.resize(image.size)
image = np.array(image) / 255.0
mask = np.array(mask) / 255.0
estimated_foreground = FB_blur_fusion_foreground_estimator_2(image, mask, r=r)
image_masked = Image.fromarray((estimated_foreground * 255.0).astype(np.uint8))
return image_masked
def FB_blur_fusion_foreground_estimator_2(image, alpha, r=90):
# Thanks to the source: https://github.com/Photoroom/fast-foreground-estimation
alpha = alpha[:, :, None]
F, blur_B = FB_blur_fusion_foreground_estimator(image, image, image, alpha, r)
return FB_blur_fusion_foreground_estimator(image, F, blur_B, alpha, r=6)[0]
def FB_blur_fusion_foreground_estimator(image, F, B, alpha, r=90):
if isinstance(image, Image.Image):
image = np.array(image) / 255.0
blurred_alpha = cv2.blur(alpha, (r, r))[:, :, None]
blurred_FA = cv2.blur(F * alpha, (r, r))
blurred_F = blurred_FA / (blurred_alpha + 1e-5)
blurred_B1A = cv2.blur(B * (1 - alpha), (r, r))
blurred_B = blurred_B1A / ((1 - blurred_alpha) + 1e-5)
F = blurred_F + alpha * \
(image - alpha * blurred_F - (1 - alpha) * blurred_B)
F = np.clip(F, 0, 1)
return F, blurred_B
class ImagePreprocessor():
def __init__(self, resolution: Tuple[int, int] = (1024, 1024)) -> None:
self.transform_image = transforms.Compose([
transforms.Resize(resolution),
transforms.ToTensor(),
transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225]),
])
def proc(self, image: Image.Image) -> torch.Tensor:
image = self.transform_image(image)
return image
usage_to_weights_file = {
'General': 'BiRefNet',
'General-HR': 'BiRefNet_HR',
'Matting-HR': 'BiRefNet_HR-matting',
'Matting': 'BiRefNet-matting',
'Portrait': 'BiRefNet-portrait',
'General-reso_512': 'BiRefNet_512x512',
'General-Lite': 'BiRefNet_lite',
'General-Lite-2K': 'BiRefNet_lite-2K',
# 'Anime-Lite': 'BiRefNet_lite-Anime',
'DIS': 'BiRefNet-DIS5K',
'HRSOD': 'BiRefNet-HRSOD',
'COD': 'BiRefNet-COD',
'DIS-TR_TEs': 'BiRefNet-DIS5K-TR_TEs',
'General-legacy': 'BiRefNet-legacy',
'General-dynamic': 'BiRefNet_dynamic',
'Matting-dynamic': 'BiRefNet_dynamic-matting',
}
# Choose the version of BiRefNet here.
usage = 'General-dynamic'
# Set resolution
if usage in ['General-Lite-2K']:
resolution = (2560, 1440)
elif usage in ['General-reso_512']:
resolution = (512, 512)
elif usage in ['General-HR', 'Matting-HR']:
resolution = (2048, 2048)
else:
if '-dynamic' in usage:
resolution = None
print('Using the original size (div by 32) for inference.')
else:
resolution = (1024, 1024)
half_precision = True
class EndpointHandler():
def __init__(self, path=''):
self.birefnet = AutoModelForImageSegmentation.from_pretrained(
'/'.join(('zhengpeng7', usage_to_weights_file[usage])), trust_remote_code=True
)
self.birefnet.to(device)
self.birefnet.eval()
if half_precision:
self.birefnet.half()
def __call__(self, data: Dict[str, Any]):
"""
data args:
inputs (:obj: `str`)
date (:obj: `str`)
Return:
A :obj:`list` | `dict`: will be serialized and returned
"""
print('data["inputs"] = ', data["inputs"])
image_src = data["inputs"]
if isinstance(image_src, str):
if os.path.isfile(image_src):
image_ori = Image.open(image_src)
else:
response = requests.get(image_src)
image_data = BytesIO(response.content)
image_ori = Image.open(image_data)
else:
image_ori = Image.fromarray(image_src)
image = image_ori.convert('RGB')
# Preprocess the image
if resolution is None:
resolution_div_by_32 = [int(int(reso)//32*32) for reso in image.size]
if resolution_div_by_32 != resolution:
resolution = resolution_div_by_32
image_preprocessor = ImagePreprocessor(resolution=tuple(resolution))
image_proc = image_preprocessor.proc(image)
image_proc = image_proc.unsqueeze(0)
# Prediction
with torch.no_grad():
preds = self.birefnet(image_proc.to(device).half() if half_precision else image_proc.to(device))[-1].sigmoid().cpu()
pred = preds[0].squeeze()
# Show Results
pred_pil = transforms.ToPILImage()(pred)
image_masked = refine_foreground(image, pred_pil)
image_masked.putalpha(pred_pil.resize(image.size))
return image_masked
|