def main():
parser = argparse.ArgumentParser()
parser.add_argument('--model_name',
default='test_model',
help='Model identifier.')
parser.add_argument('--model_path',
required=True,
help='Path to model file.')
parser.add_argument('--test_file', default=None, help='Path to test file.')
args = parser.parse_args()
model = ModelDescriptor(name=args.model_name,
input_shape=(1, 192, 192, 3),
input_normalizer=(0, 1),
compute_graph=utils.load_compute_graph(
args.model_path))
if args.test_file:
with ImageInference(model) as inference:
image = Image.open(args.test_file)
result = inference.run(image)
print(tensors_info(result.tensors))
return
with PiCamera(sensor_mode=4, framerate=30):
with CameraInference(model) as inference:
for result in inference.run():
print('#%05d (%5.2f fps): %s' %
(inference.count, inference.rate,
tensors_info(result.tensors)))
def model():
print(os.path.exists(_COMPUTE_GRAPH_NAME))
return ModelDescriptor(
name='FaceRecognition',
input_shape=(1, 160, 160, 3),
input_normalizer=(127.5, 128),
compute_graph=utils.load_compute_graph(_COMPUTE_GRAPH_NAME))
def model_descriptor(graph_name):
# Face detection model has special implementation in VisionBonnet firmware.
# input_shape, input_normalizer, and compute_graph params have on effect.
return ModelDescriptor(name='MODEL' + graph_name,
input_shape=(1, 0, 0, 3),
input_normalizer=(0, 0),
compute_graph=utils.load_compute_graph(graph_name))
def start_self_driving():
global on
model = inference.ModelDescriptor(
name='mobilenet_160',
input_shape=(1, 160, 160, 3),
input_normalizer=(128.0, 128.0),
compute_graph=utils.load_compute_graph(MODEL_NAME))
with PiCamera(sensor_mode=4, resolution=(160, 160),
framerate=30) as camera:
camera_thread = threading.Thread(target=capture, args=(camera, ))
camera_thread.daemon = True
camera_thread.start()
with inference.CameraInference(model) as inf:
print('Model is ready. Type on/off to start/stop self-driving')
sys.stdout.flush()
on_off_thread = threading.Thread(target=on_off, args=())
on_off_thread.daemon = True
on_off_thread.start()
for result in inf.run():
if on:
direction, probability = process(result)
print('prediction: {:.2f} {} {:.2f}'.format(
time.time(), direction, probability))
sys.stdout.flush()
def model():
# Face detection model has special implementation in VisionBonnet firmware.
# input_shape, input_normalizer, and compute_graph params have no effect.
return ModelDescriptor(
name='FaceDetection',
input_shape=(1, 0, 0, 3),
input_normalizer=(0, 0),
compute_graph=utils.load_compute_graph(_COMPUTE_GRAPH_NAME))
def model():
# Face detection model has special implementation in VisionBonnet firmware.
# input_shape, input_normalizer, and computate_graph params have on effect.
return ModelDescriptor(
name='FaceDetection',
input_shape=(1, 0, 0, 3),
input_normalizer=(0, 0),
compute_graph=utils.load_compute_graph(_COMPUTE_GRAPH_NAME))
def main():
parser = argparse.ArgumentParser()
parser.add_argument('--input_layer',
default='map/TensorArrayStack/TensorArrayGatherV3',
help='Name of input layer.')
parser.add_argument('--output_layer',
default="prediction",
help='Name of output layer.')
parser.add_argument(
'--num_frames',
type=int,
default=-1,
help='Sets the number of frames to run for, otherwise runs forever.')
parser.add_argument('--input_mean',
type=float,
default=128.0,
help='Input mean.')
parser.add_argument('--input_std',
type=float,
default=128.0,
help='Input std.')
parser.add_argument(
'--threshold',
type=float,
default=0.1,
help='Threshold for classification score (from output tensor).')
parser.add_argument('--top_k',
type=int,
default=3,
help='Keep at most top_k labels.')
parser.add_argument('--detecting_list',
type=list,
default=[
'Biston betularia (Peppered Moth)',
'Spodoptera litura (Oriental Leafworm Moth)'
],
help='Input a list of bugs that you want to keep.')
parser.add_argument('--message_threshold',
type=int,
default=1,
help='Input detection threshold for sending sms')
args = parser.parse_args()
model = inference.ModelDescriptor(
name='mobilenet_based_classifier',
input_shape=(1, 192, 192, 3),
input_normalizer=(128.0, 128.0),
compute_graph=utils.load_compute_graph(
'mobilenet_v2_192res_1.0_inat_insect.binaryproto'))
labels = read_labels(
"/home/pi/models/mobilenet_v2_192res_1.0_inat_insect_labels.txt")
detector = FawDetector()
detector.run(args.input_layer, args.output_layer, args.num_frames,
args.input_mean, args.input_std, args.threshold, args.top_k,
args.detecting_list, args.message_threshold, model, labels)
def main():
parser = argparse.ArgumentParser()
parser.add_argument('--model_path', required=True,
help='Path to converted model file that can run on VisionKit.')
parser.add_argument('--label_path', required=True,
help='Path to label file that corresponds to the model.')
parser.add_argument('--input_height', type=int, required=True, help='Input height.')
parser.add_argument('--input_width', type=int, required=True, help='Input width.')
parser.add_argument('--input_layer', required=True, help='Name of input layer.')
parser.add_argument('--output_layer', required=True, help='Name of output layer.')
parser.add_argument('--num_frames', type=int, default=None,
help='Sets the number of frames to run for, otherwise runs forever.')
parser.add_argument('--input_mean', type=float, default=128.0, help='Input mean.')
parser.add_argument('--input_std', type=float, default=128.0, help='Input std.')
parser.add_argument('--input_depth', type=int, default=3, help='Input depth.')
parser.add_argument('--threshold', type=float, default=0.1,
help='Threshold for classification score (from output tensor).')
parser.add_argument('--top_k', type=int, default=3, help='Keep at most top_k labels.')
parser.add_argument('--preview', action='store_true', default=False,
help='Enables camera preview in addition to printing result to terminal.')
parser.add_argument('--show_fps', action='store_true', default=False,
help='Shows end to end FPS.')
args = parser.parse_args()
model = inference.ModelDescriptor(
name='mobilenet_based_classifier',
input_shape=(1, args.input_height, args.input_width, args.input_depth),
input_normalizer=(args.input_mean, args.input_std),
compute_graph=utils.load_compute_graph(args.model_path))
labels = read_labels(args.label_path)
with PiCamera(sensor_mode=4, resolution=(1640, 1232), framerate=30) as camera:
if args.preview:
camera.start_preview()
with inference.CameraInference(model) as camera_inference:
for result in camera_inference.run(args.num_frames):
processed_result = process(result, labels, args.output_layer,
args.threshold, args.top_k)
send_signal_to_servos(processed_result[0])
message = get_message(processed_result, args.threshold, args.top_k)
if args.show_fps:
message += '\nWith %.1f FPS.' % camera_inference.rate
print(message)
if args.preview:
camera.annotate_foreground = Color('black')
camera.annotate_background = Color('white')
# PiCamera text annotation only supports ascii.
camera.annotate_text = '\n %s' % message.encode(
'ascii', 'backslashreplace').decode('ascii')
if args.preview:
camera.stop_preview()
def main():
parser = argparse.ArgumentParser()
parser.add_argument('--model_path', required=True,
help='Path to converted model file that can run on VisionKit.')
parser.add_argument('--label_path', required=True,
help='Path to label file that corresponds to the model.')
parser.add_argument('--input_height', type=int, required=True, help='Input height.')
parser.add_argument('--input_width', type=int, required=True, help='Input width.')
parser.add_argument('--input_layer', required=True, help='Name of input layer.')
parser.add_argument('--output_layer', required=True, help='Name of output layer.')
parser.add_argument('--num_frames', type=int, default=None,
help='Sets the number of frames to run for, otherwise runs forever.')
parser.add_argument('--input_mean', type=float, default=128.0, help='Input mean.')
parser.add_argument('--input_std', type=float, default=128.0, help='Input std.')
parser.add_argument('--input_depth', type=int, default=3, help='Input depth.')
parser.add_argument('--threshold', type=float, default=0.1,
help='Threshold for classification score (from output tensor).')
parser.add_argument('--top_k', type=int, default=3, help='Keep at most top_k labels.')
parser.add_argument('--preview', action='store_true', default=False,
help='Enables camera preview in addition to printing result to terminal.')
parser.add_argument('--show_fps', action='store_true', default=False,
help='Shows end to end FPS.')
args = parser.parse_args()
model = inference.ModelDescriptor(
name='mobilenet_based_classifier',
input_shape=(1, args.input_height, args.input_width, args.input_depth),
input_normalizer=(args.input_mean, args.input_std),
compute_graph=utils.load_compute_graph(args.model_path))
labels = read_labels(args.label_path)
with PiCamera(sensor_mode=4, resolution=(1640, 1232), framerate=30) as camera:
if args.preview:
camera.start_preview()
with inference.CameraInference(model) as camera_inference:
for result in camera_inference.run(args.num_frames):
processed_result = process(result, labels, args.output_layer,
args.threshold, args.top_k)
message = get_message(processed_result, args.threshold, args.top_k)
if args.show_fps:
message += '\nWith %.1f FPS.' % camera_inference.rate
print(message)
if args.preview:
camera.annotate_foreground = Color('black')
camera.annotate_background = Color('white')
# PiCamera text annotation only supports ascii.
camera.annotate_text = '\n %s' % message.encode(
'ascii', 'backslashreplace').decode('ascii')
if args.preview:
camera.stop_preview()
def main():
parser = argparse.ArgumentParser()
parser.add_argument(
'--model_path',
required=True,
help='Path to converted model file that can run on VisionKit.')
parser.add_argument('--input_height',
type=int,
required=True,
help='Input height.')
parser.add_argument('--input_width',
type=int,
required=True,
help='Input width.')
parser.add_argument('--input_mean',
type=float,
default=128.0,
help='Input mean.')
parser.add_argument('--input_std',
type=float,
default=128.0,
help='Input std.')
parser.add_argument('--input_depth',
type=int,
default=3,
help='Input depth.')
args = parser.parse_args()
model = ModelDescriptor(
name='test_run_model',
input_shape=(1, args.input_height, args.input_width, args.input_depth),
input_normalizer=(args.input_mean, args.input_std),
compute_graph=utils.load_compute_graph(args.model_path))
with PiCamera(sensor_mode=4, framerate=30) as camera:
with CameraInference(model) as camera_inference:
last_time = time.time()
for i, result in enumerate(camera_inference.run()):
output_tensor_str = [
'%s [%d elements]' % (k, len(v.data))
for k, v in result.tensors.items()
]
cur_time = time.time()
fps = 1.0 / (cur_time - last_time)
last_time = cur_time
print('%d-th inference, fps: %.1f FPS, %s' %
(i, fps, ','.join(output_tensor_str)))
def start_self_driving():
model = inference.ModelDescriptor(
name='mobilenet_160',
input_shape=(1, 160, 160, 3),
input_normalizer=(128.0, 128.0),
compute_graph=utils.load_compute_graph(MODEL_NAME))
print('Model loaded')
with PiCamera(sensor_mode=4, resolution=(160, 160), framerate=30) as camera:
print('Connected to the Pi Camera')
with inference.CameraInference(model) as inf:
for result in inf.run():
direction, probability = process(result)
RCool_drive.drive(direction)
print('{:.2f} {} {:.2f}'.format(time.time(), direction, probability))
def main():
model = inference.ModelDescriptor(
name='mobilenet_160',
input_shape=(1, 160, 160, 3),
input_normalizer=(128.0, 128.0),
compute_graph=utils.load_compute_graph('dumb.binaryproto'))
with inference.ImageInference(model) as inf:
print('Waiting for input...')
sys.stdout.flush()
for _ in sys.stdin:
now = time.time()
img = Image.open('{}/current.jpg'.format(os.getcwd()))
result = inf.run(img)
label, probability = process(result)
print('prediction: {} {} {}'.format(now, label, probability))
sys.stdout.flush()
def main():
parser = argparse.ArgumentParser()
parser.add_argument('--model_name',
default='test_model',
help='Model identifier.')
parser.add_argument('--model_path',
required=True,
help='Path to model file.')
parser.add_argument('--speed',
default=0.5,
type=float,
help='Reduction factor on speed')
args = parser.parse_args()
model = ModelDescriptor(name=args.model_name,
input_shape=(1, 192, 192, 3),
input_normalizer=(0, 1),
compute_graph=utils.load_compute_graph(
args.model_path))
left = Motor(PIN_A, PIN_B)
right = Motor(PIN_C, PIN_D)
print('spinning')
try:
with PiCamera(sensor_mode=4, framerate=30):
with CameraInference(model) as inference:
for result in inference.run():
data = [
tensor.data for _, tensor in result.tensors.items()
]
lspeed, rspeed = data[0]
print('#%05d (%5.2f fps): %1.2f/%1.2f' %
(inference.count, inference.rate, lspeed, rspeed))
if lspeed < 0:
left.reverse(-max(-1, lspeed) * args.speed)
else:
left.forward(min(1, lspeed) * args.speed)
if rspeed < 0:
right.reverse(-max(-1, rspeed) * args.speed)
else:
right.forward(min(1, rspeed) * args.speed)
except Exception as e:
left.stop()
right.stop()
print(e)
def initialize(self):
if Model.car is None:
car = Car()
if Car.connected:
Model.car = car
self.log('INFO', 'Car for self-driving is connected')
else:
self.log('ERROR', 'Car is not connected for self-driving')
return False
if Model.model is None:
try:
from aiy.vision import inference
from aiy.vision.models import utils
Model.model = inference.ModelDescriptor(
name='mobilenet_160',
input_shape=(1, 160, 160, 3),
input_normalizer=(128.0, 128.0),
compute_graph=utils.load_compute_graph(MODEL_NAME))
self.log('INFO', 'Self-driving model is loaded')
except Exception as e:
self.log(
'ERROR',
'Self-driving model cannot be loaded: {}'.format(str(e)))
return False
if Model.inference_engine is None:
try:
from aiy.vision import inference
Model.inference_engine = inference.InferenceEngine()
try:
Model.inference_engine.unload_model('mobilenet_160')
except:
pass
Model.model_name = Model.inference_engine.load_model(
Model.model)
Model.good = True
self.log('INFO', 'Image inference has started')
except Exception as e:
self.log(
'ERROR',
'Image inference cannot be started: {}'.format(str(e)))
return False
return True
def main():
parser = argparse.ArgumentParser()
parser.add_argument('--model_name',
default='test_model',
help='Model identifier.')
parser.add_argument('--model_path',
required=True,
help='Path to model file.')
parser.add_argument('--input_height',
type=int,
required=True,
help='Input height.')
parser.add_argument('--input_width',
type=int,
required=True,
help='Input width.')
parser.add_argument('--input_depth',
type=int,
default=3,
help='Input depth.')
parser.add_argument('--input_mean',
type=float,
default=128.0,
help='Input mean.')
parser.add_argument('--input_std',
type=float,
default=128.0,
help='Input std.')
args = parser.parse_args()
model = ModelDescriptor(
name=args.model_name,
input_shape=(1, args.input_height, args.input_width, args.input_depth),
input_normalizer=(args.input_mean, args.input_std),
compute_graph=utils.load_compute_graph(args.model_path))
with PiCamera(sensor_mode=4, framerate=30):
with CameraInference(model) as inference:
for result in inference.run():
print('#%05d (%5.2f fps): %s' %
(inference.count, inference.rate,
tensors_info(result.tensors)))
def main():
# Loading the model and label
model = inference.ModelDescriptor(
name='mobilenet_based_classifier',
input_shape=(1, 160, 160, 3),
input_normalizer=(128.0, 128.0),
compute_graph=utils.load_compute_graph('CrackClassification_graph.binaryproto'))
print("Model loaded.")
labels = read_labels(label_path + 'crack_label.txt')
print("Labels loaded")
# Classifier parameters
top_k = 3
threshold = 0.4
num_frame = None
show_fps = False
# LED setup
ledRED = LED(PIN_B)
ledGREEN = LED(PIN_A)
ledRED.off()
ledGREEN.on()
with PiCamera(sensor_mode=4, resolution=(1640, 1232), framerate=30) as camera:
with inference.CameraInference(model) as camera_inference:
for result in camera_inference.run(num_frame):
processed_result = process(result, labels, 'final_result',threshold, top_k)
if processed_result[0][0] == 'positive':
print("CRACK")
ledGREEN.off()
ledRED.on()
else:
print("CLEAR")
ledRED.off()
ledGREEN.on()
print("Camera inference rate: " + str(camera_inference.rate))
def model():
return ModelDescriptor(
name='object_detection',
input_shape=(1, 256, 256, 3),
input_normalizer=(128.0, 128.0),
compute_graph=utils.load_compute_graph(_COMPUTE_GRAPH_NAME))
def compute_graph(self):
return utils.load_compute_graph(self.compute_graph_file)
def model():
return ModelDescriptor(
name='DishDetection',
input_shape=(1, 0, 0, 3),
input_normalizer=(0, 0),
compute_graph=utils.load_compute_graph(_COMPUTE_GRAPH_NAME))
frameHeight = 256
frameRate = 20
contrast = 40
rotation = 180
# Set the picamera parametertaob
camera = picamera.PiCamera()
camera.resolution = (frameWidth, frameHeight)
camera.framerate = frameRate
camera.contrast = contrast
model = ModelDescriptor(name="DarthVaderDetector",
input_shape=(1, 256, 256, 3),
input_normalizer=(128.0, 128.0),
compute_graph=utils.load_compute_graph(
os.path.join(os.getcwd(),
"darthvader.binaryproto")))
# Start the video process
with ImgCap(model, frameWidth, frameHeight, DEBUG) as img:
camera.start_recording(img, format='rgb', splitter_port=1)
try:
while True:
camera.wait_recording(
timeout=0
) # using timeout=0, default, it'll return immediately
# if img.output is not None:
# print(img.output[0,0,0])
except KeyboardInterrupt:
pass
def compute_graph(self):
return utils.load_compute_graph(self.compute_graph_file)
def model(model_type=MOBILENET):
return ModelDescriptor(name=model_type,
input_shape=(1, 160, 160, 3),
input_normalizer=(128.0, 128.0),
compute_graph=utils.load_compute_graph(
_COMPUTE_GRAPH_NAME_MAP[model_type]))
def model():
return ModelDescriptor(
name='dish_classification',
input_shape=(1, 192, 192, 3),
input_normalizer=(128.0, 128.0),
compute_graph=utils.load_compute_graph(_COMPUTE_GRAPH_NAME))
def main():
parser = argparse.ArgumentParser()
parser.add_argument(
'--model_path',
required=True,
help='Path to converted model file that can run on VisionKit.')
parser.add_argument(
'--label_path',
required=True,
help='Path to label file that corresponds to the model.')
parser.add_argument(
'--input_height', type=int, required=True, help='Input height.')
parser.add_argument(
'--input_width', type=int, required=True, help='Input width.')
parser.add_argument(
'--input_layer', required=True, help='Name of input layer.')
parser.add_argument(
'--output_layer', required=True, help='Name of output layer.')
parser.add_argument(
'--num_frames',
type=int,
default=-1,
help='Sets the number of frames to run for, otherwise runs forever.')
parser.add_argument(
'--input_mean', type=float, default=128.0, help='Input mean.')
parser.add_argument(
'--input_std', type=float, default=128.0, help='Input std.')
parser.add_argument(
'--input_depth', type=int, default=3, help='Input depth.')
parser.add_argument(
'--threshold', type=float, default=0.6,
help='Threshold for classification score (from output tensor).')
parser.add_argument(
'--preview',
action='store_true',
default=False,
help='Enables camera preview in addition to printing result to terminal.')
parser.add_argument(
'--gpio_logic',
default='NORMAL',
help='Indicates if NORMAL or INVERSE logic is used in GPIO pins.')
parser.add_argument(
'--show_fps',
action='store_true',
default=False,
help='Shows end to end FPS.')
args = parser.parse_args()
# Model & labels
model = ModelDescriptor(
name='mobilenet_based_classifier',
input_shape=(1, args.input_height, args.input_width, args.input_depth),
input_normalizer=(args.input_mean, args.input_std),
compute_graph=utils.load_compute_graph(args.model_path))
labels = read_labels(args.label_path)
with PiCamera() as camera:
# Forced sensor mode, 1640x1232, full FoV. See:
# https://picamera.readthedocs.io/en/release-1.13/fov.html#sensor-modes
# This is the resolution inference run on.
camera.sensor_mode = 4
# Scaled and cropped resolution. If different from sensor mode implied
# resolution, inference results must be adjusted accordingly. This is
# true in particular when camera.start_recording is used to record an
# encoded h264 video stream as the Pi encoder can't encode all native
# sensor resolutions, or a standard one like 1080p may be desired.
camera.resolution = (1640, 1232)
# Start the camera stream.
camera.framerate = 30
camera.start_preview()
while True:
while True:
long_buffer = []
short_buffer = []
pinStatus(pin_A,'LOW',args.gpio_logic)
pinStatus(pin_B,'LOW',args.gpio_logic)
pinStatus(pin_C,'LOW',args.gpio_logic)
leds.update(Leds.rgb_on(GREEN))
face_box = detect_face()
print("Entered the loop of face classifier")
hand_box_params = determine_hand_box_params(face_box)
if image_boundary_check(hand_box_params):
print("Hand gesture identified")
break
# Start hand classifier
is_active = False
leds.update(Leds.rgb_on(PURPLE))
start_timer = time.time()
with ImageInference(model) as img_inference:
while True:
print("Entered the loop of gesture classifier")
#check_termination_trigger()
if is_active:
leds.update(Leds.rgb_on(RED))
hands_image = capture_hands_image(camera,hand_box_params)
output = classify_hand_gestures(img_inference,hands_image,model=model,labels=labels,output_layer=args.output_layer,threshold = args.threshold)
short_guess, num_short_guess = buffer_update(output,short_buffer,short_buffer_length)
long_guess, num_long_guess = buffer_update(output,long_buffer,long_buffer_length)
# Activation of classifier
if (long_guess == activation_index or long_guess == deactivation_index) and not is_active and num_long_guess >= (long_buffer_length - 3):
is_active = True
leds.update(Leds.rgb_on(RED))
send_signal_to_pins(activation_index,args.gpio_logic)
long_buffer = []
num_long_guess = 0
time.sleep(1)
# Deactivation of classifier (go back to stable face detection)
if (long_guess == activation_index or long_guess == deactivation_index) and is_active and num_long_guess >= (long_buffer_length - 3):
is_active = False
leds.update(Leds.rgb_off())
long_buffer = []
num_long_guess = 0
send_signal_to_pins(deactivation_index,args.gpio_logic)
time.sleep(1)
break
# If not activated within max_no_activity_period seconds, go back to stable face detection
if not is_active:
timer = time.time()-start_timer
if timer >= max_no_activity_period:
leds.update(Leds.rgb_off())
send_signal_to_pins(deactivation_index,args.gpio_logic)
time.sleep(1)
break
else:
start_timer = time.time()
# Displaying classified hand gesture commands
if num_short_guess >= (short_buffer_length-1) and is_active:
print_hand_command(short_guess)
send_signal_to_pins(short_guess,args.gpio_logic)
camera.stop_preview()
def main():
parser = argparse.ArgumentParser()
parser.add_argument('--dog_park_model_path',
help='Path to the model file for the dog park.')
parser.add_argument('--vb1_model_path',
help='Path to the model file for volley ball court 1.')
parser.add_argument('--vb2_model_path',
help='Path to the model file for volley ball court 1.')
parser.add_argument(
'--label_path',
required=True,
help='Path to label file that corresponds to the model.')
parser.add_argument('--input_mean',
type=float,
default=128.0,
help='Input mean.')
parser.add_argument('--input_std',
type=float,
default=128.0,
help='Input std.')
parser.add_argument('--input_depth',
type=int,
default=3,
help='Input depth.')
parser.add_argument('--enable_streaming',
default=False,
action='store_true',
help='Enable streaming server')
parser.add_argument('--streaming_bitrate',
type=int,
default=1000000,
help='Streaming server video bitrate (kbps)')
parser.add_argument('--mdns_name',
default='',
help='Streaming server mDNS name')
parser.add_argument(
'--preview',
action='store_true',
default=False,
help=
'Enables camera preview in addition to printing result to terminal.')
parser.add_argument(
'--time_interval',
type=int,
default=10,
help='Time interval at which to store data in seconds.')
parser.add_argument(
'--gather_data',
action='store_true',
default=False,
help='Also save images according to the assigned category.')
parser.add_argument(
'--timelapse',
action='store_true',
default=False,
help='Also save some timelapses of the entire scene, every 120 seconds.'
)
parser.add_argument('--image_folder',
default='/home/pi/Pictures/Data',
help='Folder to save captured images')
args = parser.parse_args()
labels = read_labels(args.label_path)
# At least one model needs to be passed in.
assert args.dog_park_model_path or args.vb1_model_path or args.vb2_model_path
# Check that the folder exists
if args.gather_data:
expected_subfolders = ['dog_park', 'court_one', 'court_two']
subfolders = os.listdir(args.image_folder)
for folder in expected_subfolders:
assert folder in subfolders
with ExitStack() as stack:
dog_park = {
'location_name': 'dog_park',
'path': args.dog_park_model_path,
} if args.dog_park_model_path else None
vb1 = {
'location_name': 'court_one',
'path': args.vb1_model_path,
} if args.vb1_model_path else None
vb2 = {
'location_name': 'court_two',
'path': args.vb2_model_path,
} if args.vb2_model_path else None
# Get the list of models, filter to only the ones that were passed in.
models = [dog_park, vb1, vb2]
models = list(filter(lambda model: model, models))
# Initialize models and add them to the context
for model in models:
print('Initializing {model_name}...'.format(
model_name=model["location_name"]))
descriptor = inference.ModelDescriptor(
name='mobilenet_based_classifier',
input_shape=(1, 160, 160, args.input_depth),
input_normalizer=(args.input_mean, args.input_std),
compute_graph=utils.load_compute_graph(model['path']))
model['descriptor'] = descriptor
if dog_park:
dog_park['image_inference'] = stack.enter_context(
inference.ImageInference(dog_park['descriptor']))
if vb1:
vb1['image_inference'] = stack.enter_context(
inference.ImageInference(vb1['descriptor']))
if vb2:
vb2['image_inference'] = stack.enter_context(
inference.ImageInference(vb2['descriptor']))
camera = stack.enter_context(
PiCamera(sensor_mode=4, resolution=(820, 616), framerate=30))
server = None
if args.enable_streaming:
server = stack.enter_context(
StreamingServer(camera,
bitrate=args.streaming_bitrate,
mdns_name=args.mdns_name))
if args.preview:
# Draw bounding boxes around locations
# Load the arbitrarily sized image
img = Image.new('RGB', (820, 616))
draw = ImageDraw.Draw(img)
for location in LOCATIONS.values():
x1, y1, x2, y2 = location
draw_rectangle(draw, x1, y1, x2, y2, 3, outline='white')
# Create an image padded to the required size with
# mode 'RGB'
pad = Image.new('RGB', (
((img.size[0] + 31) // 32) * 32,
((img.size[1] + 15) // 16) * 16,
))
# Paste the original image into the padded one
pad.paste(img, (0, 0))
# Add the overlay with the padded image as the source,
# but the original image's dimensions
camera.add_overlay(pad.tobytes(), alpha=64, layer=3, size=img.size)
camera.start_preview()
data_filename = _make_filename(args.image_folder, 'data', None, 'json')
data_generator = commit_data_to_long_term(args.time_interval,
data_filename)
data_generator.send(None)
# Capture one picture of entire scene each time it's started again.
time.sleep(2)
date = time.strftime('%Y-%m-%d')
scene_filename = _make_filename(args.image_folder, date, None)
camera.capture(scene_filename)
# Draw bounding box on image showing the crop locations
with Image.open(scene_filename) as scene:
draw = ImageDraw.Draw(scene)
for location in LOCATIONS.values():
x1, y1, x2, y2 = location
draw_rectangle(draw, x1, y1, x2, y2, 3, outline='white')
scene.save(scene_filename)
# Constantly get cropped images
for cropped_images in get_cropped_images(camera, args.timelapse):
svg_doc = None
if args.enable_streaming:
width = 820 * SVG_SCALE_FACTOR
height = 616 * SVG_SCALE_FACTOR
svg_doc = svg.Svg(width=width, height=height)
for location in LOCATIONS.values():
x, y, x2, y2 = location
w = (x2 - x) * SVG_SCALE_FACTOR
h = (y2 - y) * SVG_SCALE_FACTOR
x = x * SVG_SCALE_FACTOR
y = y * SVG_SCALE_FACTOR
svg_doc.add(
svg.Rect(
x=int(x),
y=int(y),
width=int(w),
height=int(h),
rx=10,
ry=10,
fill_opacity=0.3,
style='fill:none;stroke:white;stroke-width:4px'))
# For each inference model, crop and process a different thing.
for model in models:
location_name = model['location_name']
image_inference = model['image_inference']
cropped_image = cropped_images[location_name]
# TODO: (Image Comparison) If False,return no activity.
if cropped_image:
# then run image_inference on them.
result = image_inference.run(cropped_image)
processed_result = process(result, labels, 'final_result')
data_generator.send(
(location_name, processed_result, svg_doc))
message = get_message(processed_result)
# Print the message
# print('\n')
# print('{location_name}:'.format(location_name=location_name))
# print(message)
else:
# Fake processed_result
processed_result = [('inactive', 1.00), ('active', 0.00)]
data_generator.send(
(location_name, processed_result, svg_doc))
label = processed_result[0][0]
timestamp = time.strftime('%Y-%m-%d_%H.%M.%S')
# print(timestamp)
# print('\n')
if args.gather_data and cropped_image:
# Gather 1% data on 'no activity' since it's biased against that.
# Gather 0.1% of all images.
if (
# (label == 'no activity' and random.random() > 0.99) or
# (random.random() > 0.999)
# (location_name != 'dog_park' and random.random() > 0.99) or
(random.random() > 0.9)):
subdir = '{location_name}/{label}'.format(
location_name=location_name, label=label)
filename = _make_filename(args.image_folder, timestamp,
subdir)
cropped_image.save(filename)
# if svg_doc:
# ## Plot points out
# ## 160 x 80 grid
# ## 16px width
# ## 20, 40, 60 for 0, 1, 2
# lines = message.split('\n')
# y_correction = len(lines) * 20
# for line in lines:
# svg_doc.add(svg.Text(line,
# x=(LOCATIONS[location_name][0]) * SVG_SCALE_FACTOR,
# y=(LOCATIONS[location_name][1] - y_correction) * SVG_SCALE_FACTOR,
# fill='white', font_size=20))
# y_correction = y_correction - 20
# TODO: Figure out how to annotate at specific locations.
# if args.preview:
# camera.annotate_foreground = Color('black')
# camera.annotate_background = Color('white')
# # PiCamera text annotation only supports ascii.
# camera.annotate_text = '\n %s' % message.encode(
# 'ascii', 'backslashreplace').decode('ascii')
if server:
server.send_overlay(str(svg_doc))
if args.preview:
camera.stop_preview()
def model():
return ModelDescriptor(
name='dish_classifier',
input_shape=(1, 192, 192, 3),
input_normalizer=(128.0, 128.0),
compute_graph=utils.load_compute_graph(_COMPUTE_GRAPH_NAME))
fp = open(filename)
tmp_shutter_numb = fp.readlines()
tmp_shutter_numb = tmp_shutter_numb[0].rstrip()
shutter_numb = int(tmp_shutter_numb)
def read_labels(label_path):
with open(label_path) as label_file:
return [label.strip() for label in label_file.readlines()]
model = inference.ModelDescriptor(
name='mobilenet_based_classifier',
input_shape=(1, args.input_height, args.input_width, args.input_depth),
input_normalizer=(args.input_mean, args.input_std),
compute_graph=utils.load_compute_graph(args.model_path))
labels = read_labels(args.label_path)
def get_message(result, threshold, top_k):
if result:
return '%s' % '\n'.join(result)
else:
return 'Nothing detected when threshold=%.2f, top_k=%d' % (threshold,
top_k)
def process(result, labels, tensor_name, threshold, top_k):
"""Processes inference result and returns labels sorted by confidence."""
# MobileNet based classification model returns one result vector.
assert len(result.tensors) == 1
def main():
model_path = '/opt/aiy/models/retrained_graph.binaryproto'
#model_path = '/opt/aiy/models/mobilenet_v1_160res_0.5_imagenet.binaryproto'
label_path = '/opt/aiy/models/retrained_labels_new.txt'
#label_path = '/opt/aiy/models/mobilenet_v1_160res_0.5_imagenet_labels.txt'
model_path = '/opt/aiy/models/rg_v3_new.binaryproto'
label_path = '/opt/aiy/models/retrained_labels_new.txt'
input_height = 160
input_width = 160
input_layer = 'input'
output_layer = 'final_result'
threshold = 0.8
# Model & labels
model = ModelDescriptor(
name='mobilenet_based_classifier',
input_shape=(1, input_height, input_width, 3),
input_normalizer=(128.0, 128.0),
compute_graph=utils.load_compute_graph(model_path))
labels = read_labels(label_path)
new_labels = []
for eachLabel in labels:
if len(eachLabel)>1:
new_labels.append(eachLabel)
labels = new_labels
#print(labels)
s = xmlrpc.client.ServerProxy("http://aiy.mdzz.info:8000/")
player = TonePlayer(BUZZER_GPIO, 10)
player.play(*MODEL_LOAD_SOUND)
while True:
while True:
if s.camera() == 1:
print('vision kit is woken up')
with Leds() as leds:
leds.pattern = Pattern.blink(100)
leds.update(Leds.rgb_pattern(Color.RED))
time.sleep(2.0)
start_time = round(time.time())
break
time.sleep(0.2)
print('no signal, sleeping...')
with PiCamera() as camera:
# Configure camera
camera.sensor_mode = 4
camera.resolution = (1664, 1232) # Full Frame, 16:9 (Camera v2)
camera.framerate = 30
camera.start_preview()
while True:
# Do inference on VisionBonnet
#print('Start capturing')
with CameraInference(face_detection.model()) as inference:
for result in inference.run():
#print(type(result))
faces = face_detection.get_faces(result)
if len(faces) >= 1:
#print('camera captures...')
extension = '.jpg'
filename = time.strftime('%Y-%m-%d %H:%M:%S') + extension
camera.capture(filename)
image_npp = np.empty((1664 * 1232 * 3,), dtype=np.uint8)
camera.capture(image_npp, 'rgb')
image_npp = image_npp.reshape((1232, 1664, 3))
image_npp = image_npp[:1232, :1640, :]
# image = Image.open('jj.jpg')
# draw = ImageDraw.Draw(image)
faces_data = []
faces_cropped = []
for i, face in enumerate(faces):
# print('Face #%d: %s' % (i, face))
x, y, w, h = face.bounding_box
#print(x,y,w,h)
w_rm = int(0.3 * w / 2)
face_cropped = crop_np((x, y, w, h), w_rm, image_npp)
if face_cropped is None: continue #print('face_cropped None'); continue
# faces_data.append(image[y: y + h, x + w_rm: x + w - w_rm])
# image[y: y + h, x + w_rm: x + w - w_rm].save('1.jpg')
face_cropped.save('face_cropped_'+str(i)+'.jpg')
faces_cropped.append(face_cropped)
#break
break
# else:
# tt = round(time.time()) - start_time
# if tt > 10:
# break
#print('face cutting finishes')
#print(type(faces_cropped), len(faces_cropped))
player.play(*BEEP_SOUND)
flag = 0
for eachFace in faces_cropped:
#print(type(eachFace))
if eachFace is None: flag = 1
if (len(faces_cropped)) <= 0: flag = 1
if flag == 1: continue
with ImageInference(model) as img_inference:
#with CameraInference(model) as img_inference:
print('Entering classify_hand_gestures()')
output = classify_hand_gestures(img_inference, faces_cropped, model=model, labels=labels,
output_layer=output_layer, threshold=threshold)
#print(output)
if (output == 3):
player.play(*JOY_SOUND)
print('Yani face detected')
print(s.result("Owner", filename))
else:
player.play(*SAD_SOUND)
print('Suspicious face detected')
print(s.result("Unknown Face", filename))
upload(filename)
# Stop preview #
#break
while (s.camera()==0):
print('sleeping')
time.sleep(.2)
print('Waken up')
def model_roll():
return ModelDescriptor(name='roll_inference',input_shape=(1, 64, 64, 3),input_normalizer=(128, 128),compute_graph=utils.load_compute_graph(_ROLL_GRAPH_NAME))
def main():
parser = argparse.ArgumentParser()
parser.add_argument(
'--model_path',
required=True,
help='Path to converted model file that can run on VisionKit.')
parser.add_argument(
'--label_path',
required=True,
help='Path to label file that corresponds to the model.')
parser.add_argument('--input_height',
type=int,
required=True,
help='Input height.')
parser.add_argument('--input_width',
type=int,
required=True,
help='Input width.')
parser.add_argument('--input_layer',
required=True,
help='Name of input layer.')
parser.add_argument('--output_layer',
required=True,
help='Name of output layer.')
parser.add_argument('--input_mean',
type=float,
default=128.0,
help='Input mean.')
parser.add_argument('--input_std',
type=float,
default=128.0,
help='Input std.')
parser.add_argument('--input_depth',
type=int,
default=3,
help='Input depth.')
parser.add_argument(
'--threshold',
type=float,
default=0.1,
help='Threshold for classification score (from output tensor).')
parser.add_argument('--top_k',
type=int,
default=1,
help='Keep at most top_k labels.')
args = parser.parse_args()
model = inference.ModelDescriptor(
name='mobilenet_based_classifier',
input_shape=(1, args.input_height, args.input_width, args.input_depth),
input_normalizer=(args.input_mean, args.input_std),
compute_graph=utils.load_compute_graph(args.model_path))
labels = read_labels(args.label_path)
print("Taking photo")
with PiCamera() as camera:
camera.resolution = (640, 480)
camera.start_preview()
sleep(3.000)
camera.capture(photo_filename)
with inference.ImageInference(model) as image_inference:
image = Image.open(photo_filename)
result = image_inference.run(image)
processed_result = process(result, labels, args.output_layer,
args.threshold, args.top_k)
message = get_message(processed_result, args.threshold, args.top_k)
return message
def model():
return ModelDescriptor(
name='image_classification',
input_shape=(1, 160, 160, 3),
input_normalizer=(128.0, 128.0),
compute_graph=utils.load_compute_graph(_COMPUTE_GRAPH_NAME))
def model():
return ModelDescriptor(
name='cifar10_classification',
input_shape=(1, 32, 32, 3),
input_normalizer=(127.5, 127.5),
compute_graph=utils.load_compute_graph(_COMPUTE_GRAPH_NAME))
def main():
parser = argparse.ArgumentParser()
parser.add_argument('--input_layer',
default='map/TensorArrayStack/TensorArrayGatherV3',
help='Name of input layer.')
parser.add_argument('--output_layer',
default="prediction",
help='Name of output layer.')
parser.add_argument(
'--num_frames',
type=int,
default=-1,
help='Sets the number of frames to run for, otherwise runs forever.')
parser.add_argument('--input_mean',
type=float,
default=128.0,
help='Input mean.')
parser.add_argument('--input_std',
type=float,
default=128.0,
help='Input std.')
parser.add_argument(
'--threshold',
type=float,
default=0.6,
help='Threshold for classification score (from output tensor).')
parser.add_argument('--top_k',
type=int,
default=3,
help='Keep at most top_k labels.')
parser.add_argument(
'--detecting_list',
type=list,
default=[
'Biston betularia (Peppered Moth)',
'Spodoptera litura (Oriental Leafworm Moth)',
'Utetheisa ornatrix (Ornate Bella Moth)',
'Polygrammate hebraeicum (Hebrew Moth)',
'Palpita magniferalis (Splendid Palpita Moth) (0.14)',
'Hyles lineata (White-lined Sphinx Moth)',
'Hemileuca eglanterina (Western Sheep Moth)',
'Ceratomia undulosa (Waved Sphinx Moth)',
'Nadata gibbosa (White-dotted Prominent Moth)',
'Lophocampa caryae (Hickory Tussock Moth)',
'Spodoptera ornithogalli (Yellow-striped Armyworm Moth)',
'Spodoptera litura (Oriental Leafworm Moth)',
'Charadra deridens (Laugher Moth)'
],
help='Input a list of bugs that you want to keep.')
parser.add_argument('--message_threshold',
type=int,
default=4,
help='Input detection threshold for sending sms')
args = parser.parse_args()
model = inference.ModelDescriptor(
name='mobilenet_based_classifier',
input_shape=(1, 192, 192, 3),
input_normalizer=(128.0, 128.0),
compute_graph=utils.load_compute_graph(
'mobilenet_v2_192res_1.0_inat_insect.binaryproto'))
labels = read_labels(
"/home/pi/models/mobilenet_v2_192res_1.0_inat_insect_labels.txt")
detector = FawDetector()
detector.run(args.input_layer, args.output_layer, args.num_frames,
args.input_mean, args.input_std, args.threshold, args.top_k,
args.detecting_list, args.message_threshold, model, labels)
