def callback(self,data):
rospy.loginfo("detection")
with torch.no_grad():
gen = point_cloud2.read_points(data)
for idx, p in enumerate(gen):
print(idx)
print(p)
b = kitti_bev_utils.removePoints(gen, cnf.boundary)
imgs_bev = kitti_bev_utils.makeBVFeature(b, cnf.DISCRETIZATION, cnf.boundary)
input_imgs = imgs_bev.to(device=configs.device).float()
t1 = time_synchronized()
outputs = self.model(input_imgs)
t2 = time_synchronized()
detections = post_processing_v2(outputs, conf_thresh=configs.conf_thresh, nms_thresh=configs.nms_thresh)
img_detections = [] # Stores detections for each image index
img_detections.extend(detections)
img_bev = imgs_bev.squeeze() * 255
img_bev = img_bev.permute(1, 2, 0).numpy().astype(np.uint8)
img_bev = cv2.resize(img_bev, (configs.img_size, configs.img_size))
for detections in img_detections:
if detections is None:
continue
# Rescale boxes to original image
detections = rescale_boxes(detections, configs.img_size, img_bev.shape[:2])
for x, y, w, l, im, re, *_, cls_pred in detections:
yaw = np.arctan2(im, re)
# Draw rotated box
kitti_bev_utils.drawRotatedBox(img_bev, x, y, w, l, yaw, cnf.colors[int(cls_pred)])
img_bev = cv2.flip(cv2.flip(img_bev, 0), 1)
out_img = img_bev
cv2.imshow('test-img', out_img)
cv2.waitKey(1)
t2 = time_synchronized()
detections = post_processing(outputs,
conf_thresh=configs.conf_thresh,
nms_thresh=configs.nms_thresh)
img_detections = [] # Stores detections for each image index
img_detections.extend(detections)
img_bev = imgs_bev.squeeze() * 255
img_bev = img_bev.permute(1, 2, 0).numpy().astype(np.uint8)
img_bev = cv2.resize(img_bev, (configs.img_size, configs.img_size))
for detections in img_detections:
if detections is None:
continue
# Rescale boxes to original image
detections = rescale_boxes(detections, configs.img_size,
img_bev.shape[:2])
for x, y, w, l, im, re, cls_conf, cls_pred in detections:
yaw = np.arctan2(im, re)
# Draw rotated box
kitti_bev_utils.drawRotatedBox(img_bev, x, y, w, l, yaw,
cnf.colors[int(cls_pred)])
img_rgb = cv2.imread(img_paths[0])
calib = kitti_data_utils.Calibration(img_paths[0].replace(
".png", ".txt").replace("image_2", "calib"))
objects_pred = predictions_to_kitti_format(img_detections, calib,
img_rgb.shape,
configs.img_size)
img_rgb = show_image_with_boxes(img_rgb, objects_pred, calib,
False)
def client_recv(self, client, address):
while True:
# read message from socket
# client_msg_0\x00\x00\x00\x00\x00...
msg = client.recv(1024).decode("utf-8")
msg = msg.rstrip("\x00")
if msg == '':
return
if msg == "EOF":
return
elif msg == "quit_client":
client.close()
# self.sock.close()
print("> client exit...")
return
elif msg == "quit_server":
client.close()
self.sock.close()
print("> server exit...")
sys.exit(0)
else:
print("> -------", time.strftime('%Y-%m-%d %H:%M:%S',
time.localtime(time.time())), "-------")
print("> receive the msg from client : {0}".format(msg))
print('> inference for {0}'.format(msg))
if(self.need_create_window):
# NOTE ObjSLAM
cv2.namedWindow("YOLO", flags=cv2.WINDOW_GUI_NORMAL)
self.need_create_window = False
# Inference
with torch.no_grad():
# img_paths, imgs_bev = self.test_dataloader_iter.next()
img_paths, imgs_bev = self.test_dataset[int(msg)]
img_paths = [img_paths]
imgs_bev = torch.from_numpy(
np.expand_dims(imgs_bev, axis=0))
input_imgs = imgs_bev.to(
device=self.configs.device).float()
outputs = self.model(input_imgs)
detections = post_processing_v2(
outputs, conf_thresh=self.configs.conf_thresh, nms_thresh=self.configs.nms_thresh)
img_detections = [] # Stores detections for each image index
img_detections.extend(detections)
img_bev = imgs_bev.squeeze() * 255
img_bev = img_bev.permute(1, 2, 0).numpy().astype(np.uint8)
img_bev = cv2.resize(
img_bev, (self.configs.img_size, self.configs.img_size))
for detections in img_detections:
if detections is None:
continue
# Rescale boxes to original image
detections = rescale_boxes(
detections, self.configs.img_size, img_bev.shape[:2])
for x, y, w, l, im, re, *_, cls_pred in detections:
yaw = np.arctan2(im, re)
# Draw rotated box
kitti_bev_utils.drawRotatedBox(
img_bev, x, y, w, l, yaw, cnf.colors[int(cls_pred)])
img_rgb = cv2.imread(img_paths[0])
calib = kitti_data_utils.Calibration(img_paths[0].replace(
".png", ".txt").replace("image_2", "calib"))
objects_pred = predictions_to_kitti_format(
img_detections, calib, img_rgb.shape, self.configs.img_size)
# NOTE: 输出json的代码
frame_object_list = []
for i in objects_pred:
frame_object = dict()
frame_object['type'] = i.type
frame_object['center'] = i.t
frame_object['length'] = i.l
frame_object['width'] = i.w
frame_object['height'] = i.h
frame_object['theta'] = i.ry
box3d_pts_2d, _ = kitti_data_utils.compute_box_3d(
i, calib.P)
if box3d_pts_2d is None:
frame_object['box3d_pts_2d'] = box3d_pts_2d
elif box3d_pts_2d.size == 16:
frame_object['box3d_pts_2d'] = box3d_pts_2d
else:
frame_object['box3d_pts_2d'] = box3d_pts_2d[:8, :]
frame_object_list.append(frame_object)
result = json.dumps(frame_object_list, cls=NumpyEncoder)
img_bev = cv2.flip(cv2.flip(img_bev, 0), 1)
scale = 1.5
cv2.resizeWindow("YOLO",
width=int(img_bev.shape[1] * scale),
height=int(img_bev.shape[0] * scale))
cv2.imshow('YOLO', img_bev)
cv2.waitKey(10)
self.batch_idx += 1
if len(result) > self.configs.max_length:
print("> WARNING: STRING IS TOO LONG! (MAX_LENGTH {0})".format(
self.configs.max_length))
client.send(result.encode(encoding='utf-8'))
print("> send the responce back to client, string length: {0}".format(
len(result)))
return
img_detections = [] # Stores detections for each image index
img_detections.extend(detections)
bev_maps = torch.squeeze(bev_maps).numpy()
RGB_Map = np.zeros((cnf.BEV_WIDTH, cnf.BEV_WIDTH, 3))
RGB_Map[:, :, 2] = bev_maps[0, :, :] # r_map
RGB_Map[:, :, 1] = bev_maps[1, :, :] # g_map
RGB_Map[:, :, 0] = bev_maps[2, :, :] # b_map
RGB_Map = (255 * RGB_Map).astype(np.uint8)
for detections in img_detections:
if detections is None:
continue
# Rescale boxes to original image
detections = np.array(detections)
print('detections shape: {}'.format(detections.shape))
detections = rescale_boxes(detections, configs.img_size, RGB_Map.shape[:2])
for x, y, w, l, im, re, cls_conf, cls_pred in detections:
yaw = np.arctan2(im, re)
# Draw rotated box
kitti_bev_utils.drawRotatedBox(RGB_Map, x, y, w, l, yaw, cnf.colors[int(cls_pred)])
img2d = cv2.imread(img_paths[0])
calib = kitti_data_utils.Calibration(img_paths[0].replace(".png", ".txt").replace("image_2", "calib"))
objects_pred = predictions_to_kitti_format(img_detections, calib, img2d.shape, configs.img_size)
img2d = show_image_with_boxes(img2d, objects_pred, calib, False)
cv2.imshow("bev img", RGB_Map)
cv2.imshow("img2d", img2d)
if cv2.waitKey(0) & 0xFF == 27:
break