def detect(self):
model = BlazeFace()
model.load_weights(self.model_weights)
model.load_anchors(self.model_anchors)
# img = cv2.cvtColor(cv2.imread(self.img_path), cv2.COLOR_BGR2RGB)
# img_res = cv2.resize(img, (self.img_size, self.img_size))
img_res = cv2.resize(self.img_arr, (self.img_size, self.img_size))
results = model.predict_on_image(img_res)
self.detections = results
return results
net.load_anchors("anchors.npy")
# let's start the capture now
print("starting camera now....")
#adjust based on your device. For most cases, normally 0
cap = cv2.VideoCapture(0)
while (True):
# Capture frame-by-frame
ret, frame = cap.read()
# Our operations on the frame come here
#gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
img = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
img = cv2.resize(img, (128, 128))
detections = net.predict_on_image(img)
if isinstance(detections, torch.Tensor):
detections = detections.cpu().numpy()
if detections.ndim == 1:
detections = np.expand_dims(detections, axis=0)
print("Found %d faces" % detections.shape[0])
if detections.shape[0] > 0:
for i in range(detections.shape[0]):
# adjust the coordinates to the original image
ymin = detections[i, 0] * frame.shape[0]
xmin = detections[i, 1] * frame.shape[1]
ymax = detections[i, 2] * frame.shape[0]
xmax = detections[i, 3] * frame.shape[1]
cv2.rectangle(frame, (int(xmin), int(ymin)),
(int(xmax), int(ymax)), (255, 0, 0), 2)
xscale, yscale = 192 / face_img.shape[1], 192 / face_img.shape[0]
for i in range(detections.shape[0]):
x, y = int(detections[i, 0] / xscale), int(detections[i, 1] / yscale)
image = cv2.circle(image, (xmin + x, ymin + y), 1, (255, 0, 0), 1)
videoCapture = cv2.VideoCapture(0)
while True:
ret, image = videoCapture.read()
if not ret:
break
# preprocess image
face_img = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
face_img = cv2.resize(face_img, (128, 128))
# get face detection boxes
detections = blaze_net.predict_on_image(face_img).numpy()
xmin, ymin, face_img = get_crop_face(detections, image)
# get face mesh
mesh_img = cv2.resize(face_img, (192, 192))
detections = mesh_net.predict_on_image(mesh_img).numpy()
get_mesh_face(detections, face_img, image, xmin, ymin)
# show processed image
cv2.imshow("capture", image)
if cv2.waitKey(3) & 0xFF == 27:
break
hasFrame, frame = capture.read()
frame_ct = 0
else:
hasFrame = False
while hasFrame:
frame_ct += 1
if mirror_img:
frame = np.ascontiguousarray(frame[:, ::-1, ::-1])
else:
frame = np.ascontiguousarray(frame[:, :, ::-1]) # BRG to RGB
img1, img2, scale, pad = resize_pad(frame)
normalized_face_detections = face_detector.predict_on_image(img1)
face_detections = denormalize_detections(normalized_face_detections, scale,
pad)
xc, yc, scale, theta = face_detector.detection2roi(face_detections.cpu())
img, affine, box = face_regressor.extract_roi(frame, xc, yc, theta, scale)
flags, normalized_landmarks = face_regressor(img.to(gpu))
landmarks = face_regressor.denormalize_landmarks(
normalized_landmarks.cpu(), affine)
#frame = cv2.rectangle(frame, (0,0), (400,400), (120, 120, 120), 400)
for i in range(len(flags)):
landmark, flag = landmarks[i], flags[i]
if flag > .5:
cap = cv2.VideoCapture(0)
net = BlazeFace().to(device)
net.load_weights("blazeface.pth")
net.load_anchors("anchors.npy")
# Optionally change the thresholds:
net.min_score_thresh = 0.75
net.min_suppression_threshold = 0.3
while True:
ret, frame = cap.read()
frame = cv2.resize(frame, (128, 128)).astype(np.float32)
print(frame.shape)
detections = net.predict_on_image(frame)
img = plot_detections(frame, detections)
print(detections.shape)
# #detections = detections.squeeze()
# top_left = tuple((detections[0][0], detections[0][1]))
# bottom_right = tuple((detections[0][1], detections[0][3]))
# frame = frame/255.0
# cv2.rectangle(frame, top_left, bottom_right, (0, 0, 255))
# cv2.imshow('frame', frame)
cv2.namedWindow("output", cv2.WINDOW_NORMAL)
cv2.resizeWindow("output", 600, 600)
cv2.imshow('output', img)
cv2.waitKey(1)
