def main() -> None:
aspect_ratio = 16 / 9
image_width = 720
image_height = int(image_width / aspect_ratio)
samples_per_pixel = 48
max_depth = 5
world = random_scene()
lookfrom = Point3(13, 2, 3)
lookat = Point3(0, 0, 0)
vup = Vec3(0, 1, 0)
vfov = 20
dist_to_focus = 10
aperture = 0.1
cam = Camera(lookfrom, lookat, vup, vfov, aspect_ratio, aperture,
dist_to_focus)
print("Start rendering.")
start_time = time.time()
img_list = Parallel(n_jobs=2, verbose=20)(
delayed(scan_frame)(world, cam, image_width, image_height, max_depth)
for s in range(samples_per_pixel))
end_time = time.time()
print(f"\nDone. Total time: {round(end_time - start_time, 1)} s.")
final_img = Img(image_width, image_height)
for img in img_list:
final_img.write_frame(img)
final_img.average(samples_per_pixel).gamma(2)
final_img.save("./output.png", True)
def main():
args = parse_args()
if args.category_num <= 0:
raise SystemExit('Bad category_num: %d!' % args.category_num)
cam = Camera(args)
cam.open()
if not cam.is_opened:
sys.exit('Failed to open camera!')
cls_dict = get_cls_dict(args.category_num)
yolo_dim = int(args.model.split('-')[-1])
if yolo_dim not in (288, 416, 608):
raise SystemExit('Bad yolo_dim: %d!\nPlease make sure the model file name contains the correct dimension...' % yolo_dim)
trt_yolov3 = TrtYOLOv3(args.model, (yolo_dim, yolo_dim), args.category_num)
cam.start()
open_window(WINDOW_NAME, args.image_width, args.image_height,
'Camera TensorRT YOLOv3 Demo')
vis = BBoxVisualization(cls_dict)
loop_and_detect(cam, trt_yolov3, conf_th=0.3, vis=vis)
cam.stop()
cam.release()
cv2.destroyAllWindows()
def main():
args = parse_args()
if args.category_num <= 0:
raise SystemExit('ERROR: bad category_num (%d)!' % args.category_num)
if not os.path.isfile('yolo/%s.trt' % args.model):
raise SystemExit('ERROR: file (yolo/%s.trt) not found!' % args.model)
cam = Camera(args)
if not cam.isOpened():
raise SystemExit('ERROR: failed to open camera!')
cls_dict = get_cls_dict(args.category_num)
yolo_dim = args.model.split('-')[-1]
if 'x' in yolo_dim:
dim_split = yolo_dim.split('x')
if len(dim_split) != 2:
raise SystemExit('ERROR: bad yolo_dim (%s)!' % yolo_dim)
w, h = int(dim_split[0]), int(dim_split[1])
else:
h = w = int(yolo_dim)
if h % 32 != 0 or w % 32 != 0:
raise SystemExit('ERROR: bad yolo_dim (%s)!' % yolo_dim)
trt_yolo = TrtYOLO(args.model, (h, w), args.category_num)
open_window(WINDOW_NAME, 'Camera TensorRT YOLO Demo', 640, 480)
vis = BBoxVisualization(cls_dict)
loop_and_detect(cam, trt_yolo, conf_th=0.3, vis=vis)
cam.release()
cv2.destroyAllWindows()
def main():
args = parse_args()
if args.category_num <= 0:
raise SystemExit('ERROR: bad category_num (%d)!' % args.category_num)
if not os.path.isfile('yolo/%s.trt' % args.model):
raise SystemExit('ERROR: file (yolo/%s.trt) not found!' % args.model)
cam = Camera(args)
if not cam.isOpened():
raise SystemExit('ERROR: failed to open camera!')
cls_dict = get_cls_dict(args.category_num)
vis = BBoxVisualization(cls_dict)
h, w = get_input_shape(args.model)
trt_yolo = TrtYOLO(args.model, (h, w), args.category_num, args.letter_box)
open_window(WINDOW_NAME, 'Camera TensorRT YOLO Demo', cam.img_width,
cam.img_height)
msg_queue = Queue(maxsize=100)
# msg_queue.put("0,0,0,-1".encode())
Thread(target=serArd, args=(msg_queue, )).start()
loop_and_detect(cam, trt_yolo, msg_queue, conf_th=0.7, vis=vis)
while True:
pass
cam.release()
cv2.destroyAllWindows()
def main():
args = parse_args()
cam = Camera(args)
cam.open()
if not cam.is_opened:
sys.exit('Failed to open camera!')
cls_dict = get_cls_dict('coco')
yolo_dim = int(args.model.split('-')[-1]) # 416 or 608
trt_yolov3 = TrtYOLOv3(args.model, (yolo_dim, yolo_dim))
cam.start()
# open_window(WINDOW_NAME, args.image_width, args.image_height,
# 'Camera TensorRT YOLOv3 Demo')
vis = BBoxVisualization(cls_dict)
# for video
# loop_and_detect(cam, trt_yolov3, conf_th=0.3, vis=vis)
# for single file
detect_demo(cam, trt_yolov3, conf_th=0.3, vis=vis)
cam.stop()
cam.release()
cv2.destroyAllWindows()
def main():
args = parse_args()
#YOLO INIT
#cls_dict = get_cls_dict('coco')
cls_dict = get_cls_dict('deepfamily')
print("classes count : ", len(cls_dict))
yolo_dim = int(args.model.split('-')[-1]) # 416 or 608
print("yolo_dim : ", yolo_dim)
trt_yolov3 = TrtYOLOv3(args.model, (yolo_dim, yolo_dim))
#CAMERA
cam = Camera(args)
cam.open()
if not cam.is_opened:
sys.exit('Failed to open camera!')
cam.start()
#CAM-WINDOW
open_window(WINDOW_NAME, args.image_width, args.image_height,
'DEEPFAMILY PROJECT - TensorRT YOLOv3')
vis = BBoxVisualization(cls_dict)
#DETECT-LOOP
loop_and_detect(cam, trt_yolov3, conf_th=0.95, vis=vis)
#loop_and_detect(cam, trt_yolov3, conf_th=0.95)
cam.stop()
cam.release()
cv2.destroyAllWindows()
def main():
args = parse_args()
cam = Camera(args)
cam.open()
if not cam.is_opened:
sys.exit('Failed to open camera!')
trt_ssd = TrtSSD(args.model)
cam.start()
# initialize bot
logger.info('initialize robot')
robot = Robot()
logger.info('starting to loop and detect')
loop_and_detect(cam=cam,
trt_ssd=trt_ssd,
conf_th=0.3,
robot=robot,
model=args.model)
logger.info('cleaning up')
robot.stop()
cam.stop()
cam.release()
def __init__(self,
width: int,
height: int,
title: str,
camera: bool = False):
self.__Daytime = True
self.__enableCamera = camera
glut.glutInit()
glut.glutInitDisplayMode(glut.GLUT_DOUBLE | glut.GLUT_RGBA)
glut.glutInitWindowSize(width, height)
glut.glutInitWindowPosition(0, 0)
glut.glutCreateWindow(title)
glut.glutReshapeFunc(self.__window_resize)
glut.glutDisplayFunc(self.__display)
glut.glutKeyboardFunc(self.__keyboardDown)
glut.glutKeyboardUpFunc(self.__keyboardUp)
glut.glutMotionFunc(self.__mouse_look_clb)
self._create_shader()
self.setSky(True)
glEnable(GL_DEPTH_TEST)
glEnable(GL_BLEND)
glBlendFunc(GL_SRC_ALPHA, GL_ONE_MINUS_SRC_ALPHA)
self.__ElementsList = []
self.__camera = Camera()
self.__lastX = width / 2
self.__lastY = height / 2
self.__first_mouse = True
self.__left = False
self.__right = False
self.__forward = False
self.__backward = False
def infer():
# Image source
cam = Camera()
stream = cam.get_stream()
# Load edge model
EDGE_MODEL = os.path.join(os.path.dirname(os.path.abspath(__file__)),
'../models/tpu/ohmnilabs_floornet_224_quant_postprocess_edgetpu.tflite')
inference = Inference(EDGE_MODEL)
# Prediction
while True:
start = time.time()
print("======================================")
# Infer
raw_img = stream.get()
img, mask = inference.predict(raw_img)
# Visualize
mask = cv.cvtColor(mask, cv.COLOR_GRAY2BGR)
cv.addWeighted(mask, 0.5, img, 0.5, 0, img)
cv.imshow('Camera', img)
# Calculate frames per second (FPS)
end = time.time()
print('Total estimated time: {:.4f}'.format(end-start))
fps = 1/(end-start)
print("FPS: {:.1f}".format(fps))
if cv.waitKey(10) & 0xFF == ord('q'):
break
# Clear resources
cv.destroyAllWindows()
cam.terminate()
def main() -> None:
aspect_ratio = 16 / 9
image_width = 256
image_height = int(image_width / aspect_ratio)
samples_per_pixel = 20
max_depth = 10
world: HittableList = three_ball_scene()
lookfrom = Point3(13, 2, 3)
lookat = Point3(0, 0, 0)
vup = Vec3(0, 1, 0)
vfov = 20
dist_to_focus: float = 10
aperture: float = 0.1
cam = Camera(lookfrom, lookat, vup, vfov, aspect_ratio, aperture,
dist_to_focus)
print("Start rendering.")
start_time = time.time()
n_processer = multiprocessing.cpu_count()
img_list: List[Img] = Parallel(n_jobs=n_processer)(
delayed(scan_line)(j, world, cam, image_width, image_height,
samples_per_pixel, max_depth)
for j in range(image_height - 1, -1, -1))
final_img = Img(image_width, image_height)
final_img.set_array(np.concatenate([img.frame for img in img_list]))
end_time = time.time()
print(f"\nDone. Total time: {round(end_time - start_time, 1)} s.")
final_img.save("./output.png", True)
def infer():
# Image source
cam = Camera()
stream = cam.get_stream()
floorNet = FloorNet()
# Prediction
while True:
start = time.time()
print("======================================")
# Infer
raw_img = stream.get()
img, mask = floorNet.predict(raw_img)
# Visualize
mask = cv.cvtColor(mask, cv.COLOR_GRAY2BGR)
cv.addWeighted(mask, 0.5, img, 0.5, 0, img)
cv.imshow('Camera', img)
# Calculate frames per second (FPS)
end = time.time()
print('Total estimated time: {:.4f}'.format(end-start))
fps = 1/(end-start)
print("FPS: {:.1f}".format(fps))
if cv.waitKey(10) & 0xFF == ord('q'):
break
# Clear resources
cv.destroyAllWindows()
cam.terminate()
def main():
args = parse_args()
if args.category_num <= 0:
raise SystemExit('ERROR: bad category_num (%d)!' % args.category_num)
if not os.path.isfile('yolo/%s.trt' % args.model):
raise SystemExit('ERROR: file (yolo/%s.trt) not found!' % args.model)
cam = Camera(args)
if not cam.isOpened():
raise SystemExit('ERROR: failed to open camera!')
cls_dict = get_cls_dict(args.category_num)
vis = BBoxVisualization(cls_dict)
h, w = get_input_shape(args.model)
trt_yolo = TrtYOLO(args.model, (h, w), args.category_num, args.letter_box)
mjpeg_server = MjpegServer(port=args.mjpeg_port)
print('MJPEG server started...')
try:
loop_and_detect(cam,
trt_yolo,
conf_th=0.3,
vis=vis,
mjpeg_server=mjpeg_server)
except Exception as e:
print(e)
finally:
mjpeg_server.shutdown()
cam.release()
def main():
args = parse_args()
cam = Camera(args)
cam.open()
# import pdb
# pdb.set_trace()
if not cam.is_opened:
sys.exit('[INFO] Failed to open camera!')
cls_dict = get_cls_dict('coco')
yolo_dim = int(args.model.split('-')[-1]) # 416 or 608
trt_yolov3 = TrtYOLOv3(args.model, (yolo_dim, yolo_dim))
print('[INFO] Camera: starting')
cam.start()
open_window(WINDOW_NAME, args.image_width, args.image_height,
'TensorRT YOLOv3 Detector')
vis = BBoxVisualization(cls_dict)
loop_and_detect(cam,
args.runtime,
trt_yolov3,
conf_th=0.3,
vis=vis,
window_name=WINDOW_NAME)
print('[INFO] Program: stopped')
cam.stop()
cam.release()
cv2.destroyAllWindows()
def three_ball_scene(aspect_ratio: float, time0: float, time1: float) \
-> Tuple[BVHNode, Camera]:
world = HittableList()
world.add(
Sphere(Point3(0, 0, -1), 0.5, Lambertian(SolidColor(0.1, 0.2, 0.5))))
world.add(
Sphere(Point3(0, -100.5, -1), 100, Lambertian(SolidColor(0.8, 0.8,
0))))
world.add(Sphere(Point3(1, 0, -1), 0.5, Metal(Color(0.8, 0.6, 0.2), 0.3)))
world.add(Sphere(Point3(-1, 0, -1), 0.5, Dielectric(1.5)))
world.add(Sphere(Point3(-1, 0, -1), -0.45, Dielectric(1.5)))
world_bvh = BVHNode(world.objects, time0, time1)
lookfrom = Point3(3, 3, 2)
lookat = Point3(0, 0, -1)
vup = Vec3(0, 1, 0)
vfov = 20
dist_to_focus: float = (lookfrom - lookat).length()
aperture: float = 0
cam = Camera(lookfrom, lookat, vup, vfov, aspect_ratio, aperture,
dist_to_focus, time0, time1)
# lookfrom = Point3(13, 2, 3)
# lookat = Point3(0, 0, 0)
# vup = Vec3(0, 1, 0)
# vfov = 20
# dist_to_focus: float = 10
# aperture: float = 0.1
# cam = Camera(
# lookfrom, lookat, vup, vfov, aspect_ratio, aperture, dist_to_focus,
# time0, time1
# )
return world_bvh, cam
def main():
print(f"{datetime.datetime.now().isoformat()} start!", flush=True)
args = parse_args()
if args.category_num <= 0:
raise SystemExit('ERROR: bad category_num (%d)!' % args.category_num)
if not os.path.isfile('yolo/%s.trt' % args.model):
raise SystemExit('ERROR: file (yolo/%s.trt) not found!' % args.model)
cam = Camera(args)
if not cam.isOpened():
raise SystemExit('ERROR: failed to open camera!')
cls_dict = get_cls_dict(args.category_num)
yolo_dim = args.model.split('-')[-1]
if 'x' in yolo_dim:
dim_split = yolo_dim.split('x')
if len(dim_split) != 2:
raise SystemExit('ERROR: bad yolo_dim (%s)!' % yolo_dim)
w, h = int(dim_split[0]), int(dim_split[1])
else:
h = w = int(yolo_dim)
if h % 32 != 0 or w % 32 != 0:
raise SystemExit('ERROR: bad yolo_dim (%s)!' % yolo_dim)
trt_yolo = TrtYOLO(args.model, (h, w), args.category_num)
# open_window(
# WINDOW_NAME, 'Camera TensorRT YOLO Demo',
# cam.img_width, cam.img_height)
vis = BBoxVisualization(cls_dict)
loop_and_detect(cam, trt_yolo, conf_th=0.3, vis=vis)
cam.release()
def main():
args = parse_args()
cam = Camera(args)
cam.open()
if not cam.is_opened:
sys.exit('Failed to open camera!')
cls_dict = get_cls_dict(args.model)
trt_ssd = TrtSSD(args.model, INPUT_HW)
cam.start()
if args.use_console:
loop_and_detect_console(cam,
trt_ssd,
conf_th=0.3,
loop=args.loop,
cls_dict=cls_dict)
else:
open_window(WINDOW_NAME, args.image_width, args.image_height,
'Camera TensorRT SSD Demo for Jetson Nano')
vis = BBoxVisualization(cls_dict)
loop_and_detect(cam, trt_ssd, conf_th=0.3, vis=vis)
cam.stop()
cam.release()
cv2.destroyAllWindows()
def main() -> None:
aspect_ratio = 16 / 9
image_width = 256
image_height = int(image_width / aspect_ratio)
samples_per_pixel = 20
max_depth = 10
world: HittableList = three_ball_scene()
lookfrom = Point3(13, 2, 3)
lookat = Point3(0, 0, 0)
vup = Vec3(0, 1, 0)
vfov = 20
dist_to_focus: float = 10
aperture: float = 0.1
cam = Camera(lookfrom, lookat, vup, vfov, aspect_ratio, aperture,
dist_to_focus)
print("Start rendering.")
start_time = time.time()
n_processer = multiprocessing.cpu_count()
img_list: List[Img] = Parallel(n_jobs=n_processer, verbose=10)(
delayed(scan_line)(j, world, cam, image_width, image_height,
samples_per_pixel, max_depth)
for j in range(image_height - 1, -1, -1))
# # Profile prologue
# import cProfile
# import pstats
# import io
# from pstats import SortKey
# pr = cProfile.Profile()
# pr.enable()
# img_list: List[Img] = list()
# for j in range(image_height-1, -1, -1):
# img_list.append(
# scan_line(
# j, world, cam,
# image_width, image_height,
# samples_per_pixel, max_depth
# )
# )
# # Profile epilogue
# pr.disable()
# s = io.StringIO()
# sortby = SortKey.CUMULATIVE
# ps = pstats.Stats(pr, stream=s).sort_stats(sortby)
# ps.print_stats()
# print(s.getvalue())
final_img = Img(image_width, image_height)
final_img.set_array(np.concatenate([img.frame for img in img_list]))
end_time = time.time()
print(f"\nDone. Total time: {round(end_time - start_time, 1)} s.")
final_img.save("./output.png", True)
def main():
logging.basicConfig(level=logging.INFO)
logger = logging.getLogger(__name__)
# Ask tensorflow logger not to propagate logs to parent (which causes
# duplicated logging)
logging.getLogger('tensorflow').propagate = False
global args
args = parse_args()
logger.info('called with args: %s' % args)
# build the class (index/name) dictionary from labelmap file
logger.info('reading label map')
cls_dict = read_label_map(args.labelmap_file)
pb_path = './data/{}_trt.pb'.format(args.model)
log_path = './logs/{}_trt'.format(args.model)
if args.do_build:
logger.info('building TRT graph and saving to pb: %s' % pb_path)
build_trt_pb(args.model, pb_path)
logger.info('opening camera device/file')
cam = Camera(args)
cam.open()
if not cam.is_opened:
sys.exit('Failed to open camera!')
logger.info('loading TRT graph from pb: %s' % pb_path)
trt_graph = load_trt_pb(pb_path)
logger.info('starting up TensorFlow session')
tf_config = tf.ConfigProto()
tf_config.gpu_options.allow_growth = True
#tf_sess = tf.Session(config=tf_config, graph=trt_graph) -- Vincent
#Solve : "unable to satfisfy explicit device /dev/CPU:0 -- Vincent
tf_sess = tf.Session(config=tf.ConfigProto(allow_soft_placement=True,
log_device_placement=True),
graph=trt_graph)
if args.do_tensorboard:
logger.info('writing graph summary to TensorBoard')
write_graph_tensorboard(tf_sess, log_path)
logger.info('warming up the TRT graph with a dummy image')
od_type = 'faster_rcnn' if 'faster_rcnn' in args.model else 'ssd'
dummy_img = np.zeros((720, 1280, 3), dtype=np.uint8)
_, _, _ = detect(dummy_img, tf_sess, conf_th=.3, od_type=od_type)
cam.start() # ask the camera to start grabbing images
# grab image and do object detection (until stopped by user)
logger.info('starting to loop and detect')
vis = BBoxVisualization(cls_dict)
open_display_window(cam.img_height, cam.img_width)
result = loop_and_detect(cam, tf_sess, args.conf_th, vis, od_type=od_type)
logger.info('cleaning up')
cam.stop() # terminate the sub-thread in camera
tf_sess.close()
cam.release()
cv2.destroyAllWindows()
def random_scene(aspect_ratio: float, time0: float, time1: float) \
-> Tuple[BVHNode, Camera]:
world = HittableList()
# ground_material = Lambertian(SolidColor(0.5, 0.5, 0.5))
ground_material = Lambertian(
CheckerTexture(SolidColor(0.2, 0.3, 0.1), SolidColor(0.9, 0.9, 0.9)))
world.add(Sphere(Point3(0, -1000, 0), 1000, ground_material))
for a in range(-11, 11):
for b in range(-11, 11):
choose_mat = random_float()
center = Point3(a + 0.9 * random_float(), 0.2,
b + 0.9 * random_float())
if (center - Vec3(4, 0.2, 0)).length() > 0.9:
if choose_mat < 0.6:
# Diffuse
albedo = Color.random() * Color.random()
sphere_material_diffuse = Lambertian(SolidColor(albedo))
center2 = center + Vec3(0, random_float(0, 0.5), 0)
world.add(
MovingSphere(center, center2, 0, 1, 0.2,
sphere_material_diffuse))
elif choose_mat < 0.8:
# Metal
albedo = Color.random(0.5, 1)
fuzz = random_float(0, 0.5)
sphere_material_metal = Metal(albedo, fuzz)
world.add(Sphere(center, 0.2, sphere_material_metal))
else:
# Glass
sphere_material_glass = Dielectric(1.5)
world.add(Sphere(center, 0.2, sphere_material_glass))
material_1 = Dielectric(1.5)
world.add(Sphere(Point3(0, 1, 0), 1, material_1))
material_2 = Lambertian(SolidColor(0.4, 0.2, 0.1))
world.add(Sphere(Point3(-4, 1, 0), 1, material_2))
material_3 = Metal(Color(0.7, 0.6, 0.5), 0)
world.add(Sphere(Point3(4, 1, 0), 1, material_3))
world_bvh = BVHNode(world.objects, time0, time1)
lookfrom = Point3(13, 2, 3)
lookat = Point3(0, 0, 0)
vup = Vec3(0, 1, 0)
vfov = 20
dist_to_focus: float = 10
aperture: float = 0.1
cam = Camera(lookfrom, lookat, vup, vfov, aspect_ratio, aperture,
dist_to_focus, time0, time1)
return world_bvh, cam
def shot(w=224, h=224):
cam = Camera()
cam.resolution = (w, h)
cam.vflip, cam.hflip = True, True
try:
cam.capture('./test.png', resize=(w, h))
# cam.capture('./test.png')
finally:
cam.close()
return send_file('./test.png')
def main() -> None:
aspect_ratio = 16 / 9
image_width = 1920
image_height = int(image_width / aspect_ratio)
samples_per_pixel = 48
max_depth = 10
world: HittableList = random_scene()
lookfrom = Point3(13, 2, 3)
lookat = Point3(0, 0, 0)
vup = Vec3(0, 1, 0)
vfov = 20
dist_to_focus: float = 10
aperture: float = 0.1
cam = Camera(lookfrom, lookat, vup, vfov, aspect_ratio, aperture,
dist_to_focus)
print("Start rendering.")
start_time = time.time()
img_list: List[Vec3List] = Parallel(n_jobs=4, verbose=20)(
delayed(scan_frame)(world, cam, image_width, image_height, max_depth)
for s in range(samples_per_pixel))
# # Profile prologue
# import cProfile
# import pstats
# import io
# from pstats import SortKey
# pr = cProfile.Profile()
# pr.enable()
# img_list: List[Vec3List] = list()
# for sample_num in range(samples_per_pixel):
# img_list.append(
# scan_frame(world, cam, image_width, image_height, max_depth)
# )
# # Profile epilogue
# pr.disable()
# s = io.StringIO()
# sortby = SortKey.CUMULATIVE
# ps = pstats.Stats(pr, stream=s).sort_stats(sortby)
# ps.print_stats()
# print(s.getvalue())
end_time = time.time()
print(f"\nDone. Total time: {round(end_time - start_time, 1)} s.")
final_img = Img(image_width, image_height)
for img in img_list:
final_img.write_frame(img)
final_img.average(samples_per_pixel).gamma(2).up_side_down()
final_img.save("./output.png", True)
def warp_ref_image(self, depth, ref_image, K, ref_K, pose):
"""
Warps a reference image to produce a reconstruction of the original one.
Parameters
----------
inv_depths : torch.Tensor [B,1,DH,DW]
Inverse depth map of the original image
ref_image : torch.Tensor [B,3,H,W]
Reference RGB image
K : torch.Tensor [B,3,3]
Original camera intrinsics
ref_K : torch.Tensor [B,3,3]
Reference camera intrinsics
pose : Pose
Original -> Reference camera transformation
Returns
-------
ref_warped : torch.Tensor [B,3,H,W]
Warped reference image (reconstructing the original one)
"""
B, _, H, W = ref_image.shape
device = ref_image.get_device()
# Generate cameras
_, _, DH, DW = depth.shape
scale_factor = DW / float(W)
cam = Camera(K=K.float()).scaled(scale_factor).to(device)
ref_cam = Camera(K=ref_K.float(),
Tcw=pose).scaled(scale_factor).to(device)
ref_warped = view_synthesis(ref_image,
depth,
ref_cam,
cam,
padding_mode=self.padding_mode)
# Return warped reference image
return ref_warped
def yolo_detection():
# dev = cuda.Device(0)
# ctx = dev.make_context()
args = parse_args()
print(args)
"""
config assert
"""
if args.category_num <= 0:
raise SystemExit('ERROR: bad category_num (%d)!' % args.category_num)
if not os.path.isfile('yolo/darknet/%s.trt' % args.model):
raise SystemExit('ERROR: file (yolo/darknet/%s.trt) not found!' %
args.model)
cls_dict = get_cls_dict(args.category_num)
yolo_dim = args.model.split('-')[-1]
if 'x' in yolo_dim:
dim_split = yolo_dim.split('x')
if len(dim_split) != 2:
raise SystemExit('ERROR: bad yolo_dim (%s)!' % yolo_dim)
w, h = int(dim_split[0]), int(dim_split[1])
else:
h = w = int(yolo_dim)
if h % 32 != 0 or w % 32 != 0:
raise SystemExit('ERROR: bad yolo_dim (%s)!' % yolo_dim)
"""
capture the image
"""
cam = Camera(args)
if not cam.isOpened():
raise SystemExit('ERROR: failed to open camera!')
"""
deploy the yolo model
"""
trt_yolo = TrtYOLO(args.model, (h, w), args.category_num)
# open_window(
# WINDOW_NAME, 'Camera TensorRT YOLO Demo',
# cam.img_width, cam.img_height)
"""
detect the insulator using model
"""
vis = BBoxVisualization(cls_dict)
loop_and_detect(cam, trt_yolo, conf_th=0.3, vis=vis)
"""
release the image
"""
cam.release()
def main():
args = parse_args()
if args.category_num <= 0:
raise SystemExit(f'ERROR: bad category_num ({args.category_num})!')
if not os.path.isfile(args.model):
raise SystemExit(f'ERROR: file {args.model} not found!')
# Process valid coco json file
process_valid_json(args.valid_coco)
if args.write_images:
if not os.path.exists(args.image_output): os.mkdir(args.image_output)
# Create camera for video/image input
cam = Camera(args)
if not cam.get_is_opened():
raise SystemExit('ERROR: failed to open camera!')
class_dict = get_cls_dict(args.category_num)
yolo_dim = (args.model.replace(".trt", "")).split('-')[-1]
if 'x' in yolo_dim:
dim_split = yolo_dim.split('x')
if len(dim_split) != 2:
raise SystemExit(f'ERROR: bad yolo_dim ({yolo_dim})!')
w, h = int(dim_split[0]), int(dim_split[1])
else:
h = w = int(yolo_dim)
if h % 32 != 0 or w % 32 != 0:
raise SystemExit(f'ERROR: bad yolo_dim ({yolo_dim})!')
# Create yolo
trt_yolo = TrtYOLO(args.model, (h, w), args.category_num)
if args.activate_display:
open_window(WINDOW_NAME, 'Camera TensorRT YOLO Demo', cam.img_width,
cam.img_height)
visual = BBoxVisualization(class_dict)
# Run detection
loop_and_detect(cam,
trt_yolo,
args,
confidence_thresh=args.confidence_threshold,
visual=visual)
# Clean up
cam.release()
if args.activate_display:
cv2.destroyAllWindows()
def main():
camera = Camera(1, True)
while True:
blocks, frame = camera.get_block_coords()
position, angle, frame2 = camera.get_robot_position()
nav = Navigate()
if blocks and position:
block_data = nav.calculate_distances_angles(
blocks, position, angle)
print(nav.add_block_to_rejects(block_data, position, angle))
cv2.imshow('frame', frame)
cv2.imshow('frame2', frame2)
k = cv2.waitKey(5) & 0xFF
if k == 27:
break
def main():
args = parse_args()
cam = Camera(args)
if not cam.get_is_opened():
raise SystemExit('ERROR: failed to open camera!')
mtcnn = TrtMtcnn()
open_window(
WINDOW_NAME, 'Camera TensorRT MTCNN Demo for Jetson Nano',
cam.img_width, cam.img_height)
loop_and_detect(cam, mtcnn, args.minsize)
cam.release()
cv2.destroyAllWindows()
def __init__(self):
self.camera = Camera(camera_suffixes=Config.camera_suffixes)
self.history = EpisodeHistory()
self.gripper = Gripper('172.16.0.2', Config.gripper_speed,
Config.gripper_force)
self.robot = Robot('panda_arm', Config.general_dynamics_rel)
self.saver = Saver(Config.database_url, Config.collection)
self.current_bin = Config.start_bin
self.md = MotionData().with_dynamics(1.0)
self.overall_start = 0
self.last_after_images: Optional[List[OrthographicImage]] = None
def main():
# Parse arguments and get input
args = parse_args()
cam = Camera(args)
if not cam.isOpened():
raise SystemExit('ERROR: failed to open camera!')
# Create NN1 and NN2 models and load into memory
cls_dict = get_cls_dict(args.model.split('_')[-1])
trt_ssd = TrtSSD(args.model, INPUT_HW)
mtcnn = TrtMtcnn()
# Create Preview Window
open_window(WINDOW_NAME, 'Camera Preview', cam.img_width, cam.img_height)
vis = BBoxVisualization(cls_dict)
# Enter Detection Mode
while True:
# Get Image
img = cam.read()
out.write(img)
nn1_results = []
# Run Neural Networks
img, nn1_results, nn2_results, nn3_results = loop_and_detect(
img, mtcnn, args.minsize, trt_ssd, conf_th=0.3, vis=vis)
# Communicate to Arduino
if (nn1_results != []):
img = robot_drive(img, nn1_results)
else:
serial_port.write("N".encode())
print("N")
# Display and save output
cv2.imshow(WINDOW_NAME, img)
outNN.write(img)
# User/Keyboard Input
key = cv2.waitKey(1)
if key == ord('q'):
out.release()
outNN.release()
break
# Clean up and exit
cam.release()
cv2.destroyAllWindows()
serial_port.close()
def main():
args = parse_args()
labels = np.loadtxt('googlenet/synset_words.txt', str, delimiter='\t')
cam = Camera(args)
if not cam.get_is_opened():
raise SystemExit('ERROR: failed to open camera!')
# initialize the tensorrt googlenet engine
net = PyTrtGooglenet(DEPLOY_ENGINE, ENGINE_SHAPE0, ENGINE_SHAPE1)
open_window(WINDOW_NAME, 'Camera TensorRT GoogLeNet Demo', cam.img_width,
cam.img_height)
loop_and_classify(cam, net, labels, args.crop_center)
cam.release()
cv2.destroyAllWindows()
def main():
args = parse_args()
cam = Camera(args)
if not cam.get_is_opened():
raise SystemExit('ERROR: failed to open camera!')
cls_dict = get_cls_dict(args.model.split('_')[-1])
trt_ssd = TrtSSD(args.model, INPUT_HW)
open_window(WINDOW_NAME, 'Camera TensorRT SSD Demo', cam.img_width,
cam.img_height)
vis = BBoxVisualization(cls_dict)
loop_and_detect(cam, trt_ssd, conf_th=0.3, vis=vis)
cam.release()
cv2.destroyAllWindows()
