Spaces:
Running
Running
File size: 2,096 Bytes
3650c12 |
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 |
import time
import numpy as np
import cv2
import torch
from torchvision import transforms
from .nets import S3FDNet
from .box_utils import nms_
PATH_WEIGHT = 'checkpoints/auxiliary/sfd_face.pth'
img_mean = np.array([104., 117., 123.])[:, np.newaxis, np.newaxis].astype('float32')
class S3FD():
def __init__(self, device='cuda'):
tstamp = time.time()
self.device = device
print('[S3FD] loading with', self.device)
self.net = S3FDNet(device=self.device).to(self.device)
state_dict = torch.load(PATH_WEIGHT, map_location=self.device)
self.net.load_state_dict(state_dict)
self.net.eval()
print('[S3FD] finished loading (%.4f sec)' % (time.time() - tstamp))
def detect_faces(self, image, conf_th=0.8, scales=[1]):
w, h = image.shape[1], image.shape[0]
bboxes = np.empty(shape=(0, 5))
with torch.no_grad():
for s in scales:
scaled_img = cv2.resize(image, dsize=(0, 0), fx=s, fy=s, interpolation=cv2.INTER_LINEAR)
scaled_img = np.swapaxes(scaled_img, 1, 2)
scaled_img = np.swapaxes(scaled_img, 1, 0)
scaled_img = scaled_img[[2, 1, 0], :, :]
scaled_img = scaled_img.astype('float32')
scaled_img -= img_mean
scaled_img = scaled_img[[2, 1, 0], :, :]
x = torch.from_numpy(scaled_img).unsqueeze(0).to(self.device)
y = self.net(x)
detections = y.data
scale = torch.Tensor([w, h, w, h])
for i in range(detections.size(1)):
j = 0
while detections[0, i, j, 0] > conf_th:
score = detections[0, i, j, 0]
pt = (detections[0, i, j, 1:] * scale).cpu().numpy()
bbox = (pt[0], pt[1], pt[2], pt[3], score)
bboxes = np.vstack((bboxes, bbox))
j += 1
keep = nms_(bboxes, 0.1)
bboxes = bboxes[keep]
return bboxes
|