def prep_image(img, inp_dim):
orig_im = img
dim = orig_im.shape[1], orig_im.shape[0]
img = (letterbox_image(orig_im, (inp_dim, inp_dim)))
img_ = img[:, :, ::-1].transpose((2, 0, 1)).copy()
img_ = torch.from_numpy(img_).float().div(255.0).unsqueeze(0)
return img_, orig_im, dim
def prep_image(img, model_dim):
"""
Prepare image for input to the neural network.
"""
orig_im = img
orig_dim = orig_im.shape[1], orig_im.shape[0]
img = (letterbox_image(orig_im, (model_dim, model_dim)))
img_ = img[:, :, ::-1].transpose((2, 0, 1)).copy()
img_ = torch.from_numpy(img_).float().div(255.0).unsqueeze(0)
return img_, orig_im, orig_dim
def prep_frame(
self, frame: np.ndarray
) -> Tuple[np.ndarray, np.ndarray, Tuple[int, int]]:
original_frame = frame
dim = original_frame.shape[1], original_frame.shape[0]
frame = (letterbox_image(original_frame,
(self.input_dim, self.input_dim)))
frame_ = frame[:, :, ::-1].transpose((2, 0, 1)).copy()
frame_ = torch.from_numpy(frame_).float().div(255.0).unsqueeze(0)
return frame_, original_frame, dim
def prep_image(img, inp_dim):
"""
Prepare image for inputting to the neural network.
Returns a Variable
"""
orig_im = img
dim = orig_im.shape[1], orig_im.shape[0]
img = (letterbox_image(orig_im, (inp_dim, inp_dim)))
img_ = img[:, :, ::-1].transpose((2, 0, 1)).copy() #实现从BGR到RGB的转换
img_ = torch.from_numpy(img_).float().div(255.0).unsqueeze(0)
return img_, orig_im, dim
def prep_image(img, inp_dim): #이미지변환
"""
Prepare image for inputting to the neural network.
Returns a Variable
"""
orig_im = img
dim = orig_im.shape[1], orig_im.shape[0]
img = (letterbox_image(orig_im, (inp_dim, inp_dim))) #이미지를 정보화
img_ = img[:, :, ::-1].transpose((2, 0, 1)).copy()
img_ = torch.from_numpy(img_).float().div(255.0).unsqueeze(0) #이미지를 숫자로 표현
return img_, orig_im, dim #img_ is divided!! -> value b2n 0 and 1
def prep_image(img, inp_dim, rotation):
"""
Prepare image for inputting to the neural network.
Returns a Variable
"""
rows,cols, channels = img.shape
M = cv2.getRotationMatrix2D((cols/2,rows/2),int(rotation),1)
orig_im = cv2.warpAffine(img,M,(cols,rows))
dim = orig_im.shape[1], orig_im.shape[0]
img = (letterbox_image(orig_im, (inp_dim, inp_dim)))
img_ = img[:,:,::-1].transpose((2,0,1)).copy()
img_ = torch.from_numpy(img_).float().div(255.0).unsqueeze(0)
return img_, orig_im, dim
def prep_image(img, inp_dim):
"""
Prepare image for inputting to the neural network.
Returns a Variable
OpenCV 会将图像载入为 numpy 数组，颜色通道的顺序为 BGR。PyTorch 的图像输入格式是（batch x 通道 x 高度 x 宽度），其通道顺序为 RGB。
因此，用 prep_image 来将 numpy 数组转换成 PyTorch 的输入格式。
"""
orig_im = img
dim = orig_im.shape[1], orig_im.shape[0]
img = (letterbox_image(orig_im, (inp_dim, inp_dim)))
img_ = img[:, :, ::-1].transpose((2, 0, 1)).copy()
img_ = torch.from_numpy(img_).float().div(255.0).unsqueeze(0)
return img_, orig_im, dim
def detect(self, image):
# Preprocess the image
w, h = image.shape[1], image.shape[0]
img = (letterbox_image(image, (self.inp_dim, self.inp_dim)))
img_ = img[:,:,::-1].transpose((2,0,1)).copy()
img_ = torch.from_numpy(img_).float().div(255.0).unsqueeze(0)
im_dim_list = torch.FloatTensor([ [w, h] ]).repeat(1,2)
# Send to the model for prediction
if self.CUDA:
img_ = img_.cuda()
with torch.no_grad():
prediction = self.model(Variable(img_), self.CUDA)
output = write_results(prediction, self.CONFIDENCE_THRESHOLD, self.NUM_CLASSES, nms=True, nms_conf=self.NMS_THRESHOLD) # This function does NMS and converts the format. Returns 0 if no results are found.
# output has the format of [ class, cx, cy, w, h, confidence ]
if type(output) == int:
return None
# Convert back to the coordinates in the original image before resizing
# We need somewhat complicated processing here because letter boxing was used in preprocessing
output = output.detach().cpu()
scaling_factor = torch.min(self.inp_dim/im_dim_list,1)[0].view(-1,1)
output[:,[1,3]] -= (self.inp_dim - scaling_factor*im_dim_list[:,0].view(-1,1))/2
output[:,[2,4]] -= (self.inp_dim - scaling_factor*im_dim_list[:,1].view(-1,1))/2
output[:,1:5] /= scaling_factor
for i in range(output.shape[0]):
output[i, [1,3]] = torch.clamp(output[i, [1,3]], 0.0, im_dim_list[0,0])
output[i, [2,4]] = torch.clamp(output[i, [2,4]], 0.0, im_dim_list[0,1])
return [ { 'l': int(output[i, 1].item()),
't': int(output[i, 2].item()),
'r': int(output[i, 3].item()),
'b': int(output[i, 4].item()),
'confidence': output[i, 5].item() } for i in range(output.shape[0]) ]
face_in_frame = 1
ret, frame = cap.read()
# Break if not correctly read
if not ret:
break
small_frame = imutils.resize(frame, width=small_frame_w)
r = frame.shape[1] / small_frame.shape[1]
############################################################
##### FOR YOLO #############################################
############################################################
orig_im = small_frame.copy()
dim = orig_im.shape[1], orig_im.shape[0]
img = (letterbox_image(orig_im, (inp_dim, inp_dim)))
img = img[:, :, ::-1].transpose((2, 0, 1)).copy()
img = torch.from_numpy(img).float().div(255.0).unsqueeze(0)
im_dim = torch.FloatTensor(dim).repeat(1, 2)
if CUDA:
im_dim = im_dim.cuda()
img = img.cuda()
with torch.no_grad():
output = model(Variable(img), CUDA)
output = write_results(output,
confidence,
num_classes,
nms=True,
nms_conf=nms_thesh)
im_dim = im_dim.repeat(output.size(0), 1)
scaling_factor = torch.min(inp_dim / im_dim, 1)[0].view(-1, 1)
