Spaces:
Build error
Build error
File size: 4,748 Bytes
de51c6d |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 |
import cv2
import torch
from model import U2NET
from torch.autograd import Variable
import numpy as np
from glob import glob
import os
def detect_single_face(face_cascade,img):
# Convert into grayscale
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
# Detect faces
faces = face_cascade.detectMultiScale(gray, 1.1, 4)
if(len(faces)==0):
print("Warming: no face detection, the portrait u2net will run on the whole image!")
return None
# filter to keep the largest face
wh = 0
idx = 0
for i in range(0,len(faces)):
(x,y,w,h) = faces[i]
if(wh<w*h):
idx = i
wh = w*h
return faces[idx]
# crop, pad and resize face region to 512x512 resolution
def crop_face(img, face):
# no face detected, return the whole image and the inference will run on the whole image
if(face is None):
return img
(x, y, w, h) = face
height,width = img.shape[0:2]
# crop the face with a bigger bbox
hmw = h - w
# hpad = int(h/2)+1
# wpad = int(w/2)+1
l,r,t,b = 0,0,0,0
lpad = int(float(w)*0.4)
left = x-lpad
if(left<0):
l = lpad-x
left = 0
rpad = int(float(w)*0.4)
right = x+w+rpad
if(right>width):
r = right-width
right = width
tpad = int(float(h)*0.6)
top = y - tpad
if(top<0):
t = tpad-y
top = 0
bpad = int(float(h)*0.2)
bottom = y+h+bpad
if(bottom>height):
b = bottom-height
bottom = height
im_face = img[top:bottom,left:right]
if(len(im_face.shape)==2):
im_face = np.repeat(im_face[:,:,np.newaxis],(1,1,3))
im_face = np.pad(im_face,((t,b),(l,r),(0,0)),mode='constant',constant_values=((255,255),(255,255),(255,255)))
# pad to achieve image with square shape for avoding face deformation after resizing
hf,wf = im_face.shape[0:2]
if(hf-2>wf):
wfp = int((hf-wf)/2)
im_face = np.pad(im_face,((0,0),(wfp,wfp),(0,0)),mode='constant',constant_values=((255,255),(255,255),(255,255)))
elif(wf-2>hf):
hfp = int((wf-hf)/2)
im_face = np.pad(im_face,((hfp,hfp),(0,0),(0,0)),mode='constant',constant_values=((255,255),(255,255),(255,255)))
# resize to have 512x512 resolution
im_face = cv2.resize(im_face, (512,512), interpolation = cv2.INTER_AREA)
return im_face
def normPRED(d):
ma = torch.max(d)
mi = torch.min(d)
dn = (d-mi)/(ma-mi)
return dn
def inference(net,input):
# normalize the input
tmpImg = np.zeros((input.shape[0],input.shape[1],3))
input = input/np.max(input)
tmpImg[:,:,0] = (input[:,:,2]-0.406)/0.225
tmpImg[:,:,1] = (input[:,:,1]-0.456)/0.224
tmpImg[:,:,2] = (input[:,:,0]-0.485)/0.229
# convert BGR to RGB
tmpImg = tmpImg.transpose((2, 0, 1))
tmpImg = tmpImg[np.newaxis,:,:,:]
tmpImg = torch.from_numpy(tmpImg)
# convert numpy array to torch tensor
tmpImg = tmpImg.type(torch.FloatTensor)
if torch.cuda.is_available():
tmpImg = Variable(tmpImg.cuda())
else:
tmpImg = Variable(tmpImg)
# inference
d1,d2,d3,d4,d5,d6,d7= net(tmpImg)
# normalization
pred = 1.0 - d1[:,0,:,:]
pred = normPRED(pred)
# convert torch tensor to numpy array
pred = pred.squeeze()
pred = pred.cpu().data.numpy()
del d1,d2,d3,d4,d5,d6,d7
return pred
def main():
# get the image path list for inference
im_list = glob('./test_data/test_portrait_images/your_portrait_im/*')
print("Number of images: ",len(im_list))
# indicate the output directory
out_dir = './test_data/test_portrait_images/your_portrait_results'
if(not os.path.exists(out_dir)):
os.mkdir(out_dir)
# Load the cascade face detection model
face_cascade = cv2.CascadeClassifier('./saved_models/face_detection_cv2/haarcascade_frontalface_default.xml')
# u2net_portrait path
model_dir = './saved_models/u2net_portrait/u2net_portrait.pth'
# load u2net_portrait model
net = U2NET(3,1)
net.load_state_dict(torch.load(model_dir))
if torch.cuda.is_available():
net.cuda()
net.eval()
# do the inference one-by-one
for i in range(0,len(im_list)):
print("--------------------------")
print("inferencing ", i, "/", len(im_list), im_list[i])
# load each image
img = cv2.imread(im_list[i])
height,width = img.shape[0:2]
face = detect_single_face(face_cascade,img)
im_face = crop_face(img, face)
im_portrait = inference(net,im_face)
# save the output
cv2.imwrite(out_dir+"/"+im_list[i].split('/')[-1][0:-4]+'.png',(im_portrait*255).astype(np.uint8))
if __name__ == '__main__':
main()
|