def __init__(self,
wanted_labels=None,
model_file=None,
label_file=None,
num_threads=None,
edgetpu=False,
libedgetpu=None,
score_threshold=0.5):
if model_file is None:
model_file = 'detectors/mobilenet/ssd_mobilenet_v2_coco_quant_postprocess_edgetpu.tflite'
if label_file is None:
label_file = 'detectors/mobilenet/labels.txt'
self.use_edgetpu = True
self.num_threads = 1
self.engine = DetectionEngine(model_file)
self.labels = dataset_utils.ReadLabelFile(label_file)
if wanted_labels is None:
wanted_labels = ['person']
self.wanted_labels = wanted_labels
self.score_threshold = score_threshold
# newer versions of edgetpu library have a new interface
detect_op = getattr(self.engine, 'detect_with_image', None)
if callable(detect_op):
self.detector = detect_op
else:
self.detector = self.engine.DetectWithImage
def main():
parser = argparse.ArgumentParser()
parser.add_argument('--model',
help='File path of Tflite model.',
required=True)
parser.add_argument('--label',
help='File path of label file.',
required=True)
args = parser.parse_args()
labels = dataset_utils.ReadLabelFile(args.label)
engine = ClassificationEngine(args.model)
with picamera.PiCamera() as camera:
camera.resolution = (640, 480)
camera.framerate = 30
_, height, width, _ = engine.get_input_tensor_shape()
camera.start_preview()
try:
stream = io.BytesIO()
for _ in camera.capture_continuous(stream,
format='rgb',
use_video_port=True,
resize=(width, height)):
stream.truncate()
stream.seek(0)
input_tensor = np.frombuffer(stream.getvalue(), dtype=np.uint8)
start_ms = time.time()
results = engine.ClassifyWithInputTensor(input_tensor, top_k=1)
elapsed_ms = time.time() - start_ms
if results:
camera.annotate_text = '%s %.2f\n%.2fms' % (labels[
results[0][0]], results[0][1], elapsed_ms * 1000.0)
finally:
camera.stop_preview()
def main():
parser = argparse.ArgumentParser()
parser.add_argument(
'--model', help='File path of Tflite model.', required=True)
parser.add_argument('--label', help='File path of label file.', required=True)
parser.add_argument(
'--image', help='File path of the image to be recognized.', required=True)
args = parser.parse_args()
# Prepare labels.
labels = dataset_utils.ReadLabelFile(args.label)
# Initialize engine.
engine = ClassificationEngine(args.model)
# Run inference.
img = Image.open(args.image)
for result in engine.ClassifyWithImage(img, top_k=3):
print('---------------------------')
print(labels[result[0]])
print('Score : ', result[1])
def __init__(self):
MODEL_FILE_NAME = "mobilenet_ssd_v2_coco_quant_postprocess_edgetpu.tflite"
LABEL_FILE_NAME = "coco_labels.txt"
MODEL_URL = "https://dl.google.com/coral/canned_models/mobilenet_ssd_v2_coco_quant_postprocess_edgetpu.tflite"
LABEL_URL = "https://dl.google.com/coral/canned_models/coco_labels.txt"
self.download_file(MODEL_URL, MODEL_FILE_NAME)
self.download_file(LABEL_URL, LABEL_FILE_NAME)
self.last_5_scores = collections.deque(np.zeros(5), maxlen=5)
self.engine = DetectionEngine(MODEL_FILE_NAME)
self.labels = dataset_utils.ReadLabelFile(LABEL_FILE_NAME)
self.TRAFFIC_LIGHT_CLASS = 9
self.LAST_5_SCORE_THRESHOLD = 0.4
self.MIN_SCORE = 0.2
'--model',
help='File path of Tflite model.',
default=
'/home/pi/Desktop/AUTO_ML/models_edge_ICN6216886327266610278_2019-08-26_07-02-41-723_tflite_model.tflite',
required=False)
parser.add_argument(
'--label',
help='File path of label file.',
default=
'/home/pi/Desktop/AUTO_ML/models_edge_ICN6216886327266610278_2019-08-26_07-02-41-723_tflite_dict.txt',
required=False)
#parser.add_argument(
# '--image', help='File path of the image to be tested.', required=False)
args = parser.parse_args()
# Prepare labels.
labels = dataset_utils.ReadLabelFile(args.label)
# Initialize engine
engine = ClassificationEngine(args.model)
print("load model costs %s sec" % (time.time() - start_time))
dir_path = '/home/pi/Desktop/test-dataset/'
os.chdir(dir_path)
subdir_list = next(os.walk('.'))[1]
print(subdir_list)
acc = []
for subdir in subdir_list:
files = []
count = 0
sub_p = os.path.join(dir_path, subdir)
for r, d, f in os.walk(sub_p):
def main():
parser = argparse.ArgumentParser()
parser.add_argument(
'--model',
help=
'Path of the detection model, it must be a SSD model with postprocessing operator.',
required=True)
parser.add_argument('--label', help='Path of the labels file.')
parser.add_argument('--input',
help='File path of the input image.',
required=True)
parser.add_argument('--output', help='File path of the output image.')
parser.add_argument(
'--keep_aspect_ratio',
dest='keep_aspect_ratio',
action='store_true',
help=
('keep the image aspect ratio when down-sampling the image by adding '
'black pixel padding (zeros) on bottom or right. '
'By default the image is resized and reshaped without cropping. This '
'option should be the same as what is applied on input images during '
'model training. Otherwise the accuracy may be affected and the '
'bounding box of detection result may be stretched.'))
parser.set_defaults(keep_aspect_ratio=False)
args = parser.parse_args()
if not args.output:
output_name = 'object_detection_result.jpg'
else:
output_name = args.output
# Initialize engine.
engine = DetectionEngine(args.model)
labels = dataset_utils.ReadLabelFile(args.label) if args.label else None
# Open image.
img = Image.open(args.input)
draw = ImageDraw.Draw(img)
# Run inference.
ans = engine.DetectWithImage(img,
threshold=0.05,
keep_aspect_ratio=args.keep_aspect_ratio,
relative_coord=False,
top_k=10)
# Display result.
if ans:
for obj in ans:
print('-----------------------------------------')
if labels:
print(labels[obj.label_id])
print('score = ', obj.score)
box = obj.bounding_box.flatten().tolist()
print('box = ', box)
# Draw a rectangle.
draw.rectangle(box, outline='red')
img.save(output_name)
if platform.machine() == 'x86_64':
# For gLinux, simply show the image.
img.show()
elif platform.machine() == 'armv7l':
# For Raspberry Pi, you need to install 'feh' to display image.
subprocess.Popen(['feh', output_name])
else:
print('Please check ', output_name)
else:
print('No object detected!')
from edgetpu.utils import dataset_utils
from PIL import Image
import json
import picamera
import RPi.GPIO as GPIO
import datetime
import requests
import os
comebtn = 27
leavebtn = 22
url = "https://2a8043f9.ngrok.io/tag"
headers = {'content-type': 'application/json'}
filepath = '/home/pi/edgetpu/retrain-imprinting2/'
labels = dataset_utils.ReadLabelFile(
os.path.join(filepath, 'Attendance_model2.txt'))
engine = ClassificationEngine(
os.path.join(filepath, 'Attendance_model2.tflite'))
camera = picamera.PiCamera()
print('camera made')
GPIO.setmode(GPIO.BCM)
GPIO.setup(comebtn, GPIO.IN, pull_up_down=GPIO.PUD_DOWN)
GPIO.setup(leavebtn, GPIO.IN, pull_up_down=GPIO.PUD_DOWN)
print('Start camera')
print('Press red btn or blue btn')
def comein(channel):
def main():
parser = argparse.ArgumentParser()
parser.add_argument(
'--model',
help='Path of the detection model, it must be a SSD model with postprocessing operator.',
required=True)
parser.add_argument('--label', help='Path of the labels file.')
parser.add_argument('--output', help='File path of the output image.')
parser.add_argument(
'--keep_aspect_ratio',
dest='keep_aspect_ratio',
action='store_true',
help=(
'keep the image aspect ratio when down-sampling the image by adding '
'black pixel padding (zeros) on bottom or right. '
'By default the image is resized and reshaped without cropping. This '
'option should be the same as what is applied on input images during '
'model training. Otherwise the accuracy may be affected and the '
'bounding box of detection result may be stretched.'))
parser.set_defaults(keep_aspect_ratio=False)
args = parser.parse_args()
if not args.output:
output_name = 'object_detection_result.jpg'
else:
output_name = args.output
# Initialize engine.
engine = DetectionEngine(args.model)
labels = dataset_utils.ReadLabelFile(args.label) if args.label else None
# Open image.
# img = Image.open(args.input)
#draw = ImageDraw.Draw(img)
cap = cv2.VideoCapture(0)
while(True):
# 從攝影機擷取一張影像
ret, frame = cap.read()
# img = Image.open(im)
img = Image.fromarray(cv2.cvtColor(frame,cv2.COLOR_BGR2RGB))
draw = ImageDraw.Draw(img)
# Run inference.
ans = engine.DetectWithImage(
img,
threshold=0.05,
keep_aspect_ratio=args.keep_aspect_ratio,
relative_coord=False,
top_k=10)
# Display result.
if ans:
for obj in ans:
print('-----------------------------------------')
if labels:
print(labels[obj.label_id])
print('score = ', obj.score)
box = obj.bounding_box.flatten().tolist()
print('box = ', box)
# Draw a rectangle.
draw.rectangle(box, outline='red')
img_ = cv2.cvtColor(numpy.asarray(img),cv2.COLOR_RGB2BGR)
cv2.imshow('frame', img_)
# 若按下 q 鍵則離開迴圈
if cv2.waitKey(1) & 0xFF == ord('q'):
break
# 釋放攝影機
cap.release()
# 關閉所有 OpenCV 視窗
cv2.destroyAllWindows()