def get(self):
template = JINJA_ENVIRONMENT.get_template('templates/caredit/list.html')
unknown = CarModel.all().filter('name =', 'Annet').fetch(5)
assert len(unknown)==1
unknown_cars = Car.all().filter('model =', unknown[0]).fetch(50)
other = CarModel.all().filter('name =', 'Annen Alfa Romeo').fetch(5)
assert len(other)==1
other_cars = Car.all().filter('model =', other[0]).fetch(50)
data = { 'cars': other_cars + unknown_cars, 'linker': LookupReg() }
self.response.write(template.render(data))
def get(self):
template = JINJA_ENVIRONMENT.get_template(
'templates/caredit/list.html')
unknown = CarModel.all().filter('name =', 'Annet').fetch(5)
assert len(unknown) == 1
unknown_cars = Car.all().filter('model =', unknown[0]).fetch(50)
other = CarModel.all().filter('name =', 'Annen Alfa Romeo').fetch(5)
assert len(other) == 1
other_cars = Car.all().filter('model =', other[0]).fetch(50)
data = {'cars': other_cars + unknown_cars, 'linker': LookupReg()}
self.response.write(template.render(data))
class Car(Model):
name = CarModel()
price = Price()
placa = LicensePlate()
def __repr__(self):
return '<%s %s>' % (self.name, self.price)
def import_member_cars(self, csv):
import traceback
from utils.carconversion import MemberCar
self.models = CarModel.all().fetch(2000)
cars = []
lines = csv.split('\n')
for line in lines:
if len(line.strip()) == 0:
continue
fields = line.split(';')
fields.reverse()
car = MemberCar(memberno=fields.pop())
car.description = fields.pop().strip()
car.registration = fields.pop().strip()
year = fields.pop().strip()
if year != '':
car.year = int(year)
else:
car.year = 0
cars.append(car)
print len(cars), 'cars imported'
print len(self.models), 'models to use'
try:
print utils.carconversion.CarRank.do_matching(
self.models, cars, self.create_member_car)
except Exception as ex:
print 'Exception matching car: ', ex
print '*' * 80
traceback.print_exc()
print '*' * 80
def import_member_cars(self, csv):
import traceback
from utils.carconversion import MemberCar
self.models = CarModel.all().fetch(2000)
cars = []
lines = csv.split('\n')
for line in lines:
if len(line.strip()) == 0:
continue
fields = line.split(';')
fields.reverse()
car = MemberCar(memberno=fields.pop())
car.description = fields.pop().strip()
car.registration = fields.pop().strip()
year = fields.pop().strip()
if year != '':
car.year = int(year)
else:
car.year = 0
cars.append(car)
print len(cars), 'cars imported'
print len(self.models), 'models to use'
try:
print utils.carconversion.CarRank.do_matching(self.models, cars, self.create_member_car)
except Exception as ex:
print 'Exception matching car: ',ex
print '*'*80
traceback.print_exc()
print '*'*80
def get(self, range_id, model_id):
template = JINJA_ENVIRONMENT.get_template(
'templates/carmodels/model_detail.html')
model_range = ModelRange.get(range_id)
car_model = CarModel.get(model_id)
data = {'range': model_range, 'model': car_model}
self.response.write(template.render(data))
def get(self, range_id, model_id):
template = JINJA_ENVIRONMENT.get_template('templates/carmodels/model_detail.html')
model_range = ModelRange.get(range_id)
car_model = CarModel.get(model_id)
data = {
'range': model_range,
'model': car_model
}
self.response.write(template.render(data))
def __init__(self, **kwargs):
"""
Initialize the game object
kwargs -- the keywords arguments are given to the carModel
"""
model = CarModel(**kwargs)
view = CarView(model)
behaviour = CarBehaviour('human', None, model)
super(Car, self).__init__(gameObjectModel=model,
gameObjectBehaviour=behaviour,
gameObjectView=view)
logging.log(1, "Trace: Car.__init__(%s)" % kwargs)
def post(self):
import datetime
car_key = self.request.get('car_key')
model_key = self.request.get('model_key')
car = Car.get(car_key)
car.model = CarModel.get(model_key)
car.notes = ''
car.put()
print 'Updated car model to', car.model.name
ts = datetime.datetime.now()
return self.redirect('/caredit?tag=' + str(ts.time().microsecond))
def post(self):
import datetime
car_key = self.request.get('car_key')
model_key = self.request.get('model_key')
car = Car.get(car_key)
car.model = CarModel.get(model_key)
car.notes = ''
car.put()
print 'Updated car model to',car.model.name
ts = datetime.datetime.now()
return self.redirect('/caredit?tag='+str(ts.time().microsecond))
def post(self, range_id, model_id):
model_range = ModelRange.get(range_id)
if self.request.get('cancel') == '1':
return self.redirect('/ranges/' + str(model_range.key()) + '/edit')
model = CarModel.get(model_id)
model.name = self.request.get('name')
model.year_from = int(self.request.get('yearfrom'))
model.year_to = int(self.request.get('yearto'))
model.typeno = self.request.get('tipo')
model.engine_code = self.request.get('engine')
url = self.request.get('image_url')
if url != '':
model.image_url = db.Link(url)
model.notes = self.request.get('notes')
model.put()
return self.redirect('/ranges/' + str(model_range.key()) + '/edit')
def initialize():
wpod_net_path = "model/wpod-net.json"
wpod_net = CarModel.load_model(wpod_net_path)
# Load model architecture, weight and labels
json_file = open('model/MobileNets_character_recognition.json', 'r')
loaded_model_json = json_file.read()
json_file.close()
model = model_from_json(loaded_model_json)
model.load_weights("model/License_character_recognition_weight.h5")
print("[INFO] Model loaded successfully...")
labels = LabelEncoder()
labels.classes_ = np.load('model/license_character_classes.npy')
print("[INFO] Labels loaded successfully...")
return wpod_net, model, labels
def post(self, range_id, model_id):
model_range = ModelRange.get(range_id)
if self.request.get('cancel') == '1':
return self.redirect('/ranges/' + str(model_range.key()) + '/edit')
model = CarModel.get(model_id)
model.name = self.request.get('name')
model.year_from = int(self.request.get('yearfrom'))
model.year_to = int(self.request.get('yearto'))
model.typeno = self.request.get('tipo')
model.engine_code = self.request.get('engine')
url = self.request.get('image_url')
if url != '':
model.image_url = db.Link(url)
model.notes = self.request.get('notes')
model.put()
return self.redirect('/ranges/' + str(model_range.key()) + '/edit')
def post(self, member_id, car_id):
if self.request.get('cancel') == '1':
return self.redirect('/members/' + member_id + '/edit')
car = Car.get(car_id)
car.registration = self.request.get('registration')
yearstr = self.request.get('year')
year = 0
if yearstr != '':
year = int(self.request.get('year'))
if year > 0:
car.year = year
else:
car.year = None
yearstr = self.request.get('bought')
year = 0
if yearstr != '':
year = int(self.request.get('bought'))
if year > 0:
car.bought_year = year
else:
car.bought_year = None
yearstr = self.request.get('sold')
year = 0
if yearstr != '':
year = int(self.request.get('sold'))
if year > 0:
car.sold_year = year
else:
car.sold_year = None
model_key = self.request.get('model_key')
if not car.model or not str(car.model.key()) == model_key:
car.model = CarModel.get(model_key)
car.serial_no = self.request.get('serial_no')
car.notes = self.request.get('note')
car.put()
return self.redirect('/members/' + member_id + '/edit')
def post(self, member_id, car_id):
if self.request.get('cancel') == '1':
return self.redirect('/members/' + member_id + '/edit')
car = Car.get(car_id)
car.registration = self.request.get('registration')
yearstr = self.request.get('year')
year = 0
if yearstr != '':
year = int(self.request.get('year'))
if year > 0:
car.year = year
else:
car.year = None
yearstr = self.request.get('bought')
year = 0
if yearstr != '':
year = int(self.request.get('bought'))
if year > 0:
car.bought_year = year
else:
car.bought_year = None
yearstr = self.request.get('sold')
year = 0
if yearstr != '':
year = int(self.request.get('sold'))
if year > 0:
car.sold_year = year
else:
car.sold_year = None
model_key = self.request.get('model_key')
if not car.model or not str(car.model.key()) == model_key:
car.model = CarModel.get(model_key)
car.serial_no = self.request.get('serial_no')
car.notes = self.request.get('note')
car.put()
return self.redirect('/members/' + member_id + '/edit')
from model import CarModel
import matplotlib.pyplot as plt
# Config
n = 100 # Amount of model steps
car_count = 20 # Amount of cars in model
width = 100 # Road size
acceleration = 1
speed_limit = 5
randomization = 0.05
vision_range = speed_limit * 3
all_speeds = []
all_tracked_agent_speeds = []
model = CarModel(car_count, width, acceleration, vision_range, randomization,
speed_limit)
for i in range(n):
model.step()
total = 0
tracked_agent_total = 0
for agent in model.schedule.agents:
total += agent.speed
if agent.unique_id == round(car_count / 2):
tracked_agent_total += agent.speed
all_speeds.append(total / model.num_agents)
all_tracked_agent_speeds.append(tracked_agent_total)
print('all_speeds:', all_speeds)
plt.xlabel("Steps")
plt.ylabel("Average speed")
def get_default_model():
"""Return the default model name"""
return CarModel.all().filter('name', DEFAULT_MODEL_NAME).fetch(1)[0]
def evaluting(wpod_net, model, labels, test_image_path="Plate_examples/mul2.jpg"):
vehicle, LpImg,cor = CarHelpers.get_plate(test_image_path, wpod_net)
if (len(LpImg)): #check if there is at least one license image
# Scales, calculates absolute values, and converts the result to 8-bit.
plate_image = cv2.convertScaleAbs(LpImg[0], alpha=(255.0))
# convert to grayscale and blur the image
gray = cv2.cvtColor(plate_image, cv2.COLOR_BGR2GRAY)
blur = cv2.GaussianBlur(gray,(7,7),0)
# Applied inversed thresh_binary
binary = cv2.threshold(blur, 140, 255,
cv2.THRESH_BINARY + cv2.THRESH_OTSU)[1]
kernel3 = cv2.getStructuringElement(cv2.MORPH_RECT, (3, 3))
thre_mor = cv2.morphologyEx(binary, cv2.MORPH_DILATE, kernel3)
# visualize results
fig = plt.figure(figsize=(12,7))
plt.rcParams.update({"font.size":18})
grid = gridspec.GridSpec(ncols=2,nrows=3,figure = fig)
plot_image = [plate_image, gray, blur, binary,thre_mor]
plot_name = ["plate_image","gray","blur","binary","dilation"]
for i in range(len(plot_image)):
fig.add_subplot(grid[i])
plt.axis(False)
plt.title(plot_name[i])
if i ==0:
plt.imshow(plot_image[i])
else:
plt.imshow(plot_image[i],cmap="gray")
plt.savefig('img/plot_image.jpg', dpi=300)
# Create sort_contours() function to grab the contour of each digit from left to right
def sort_contours(cnts,reverse = False):
i = 0
boundingBoxes = [cv2.boundingRect(c) for c in cnts]
(cnts, boundingBoxes) = zip(*sorted(zip(cnts, boundingBoxes),
key=lambda b: b[1][i], reverse=reverse))
return cnts
cont, _ = cv2.findContours(binary, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
# creat a copy version "test_roi" of plat_image to draw bounding box
test_roi = plate_image.copy()
# Initialize a list which will be used to append charater image
crop_characters = []
# define standard width and height of character
digit_w, digit_h = 30, 60
for c in sort_contours(cont):
(x, y, w, h) = cv2.boundingRect(c)
ratio = h/w
if 1<=ratio<=6.5: # Only select contour with defined ratio
if h/plate_image.shape[0]>=0.3: # Select contour which has the height larger than 50% of the plate
# Draw bounding box arroung digit number
cv2.rectangle(test_roi, (x, y), (x + w, y + h), (0, 255,0), 2)
# Sperate number and give prediction
curr_num = thre_mor[y:y+h,x:x+w]
curr_num = cv2.resize(curr_num, dsize=(digit_w, digit_h))
_, curr_num = cv2.threshold(curr_num, 140, 255, cv2.THRESH_BINARY + cv2.THRESH_OTSU) # 220 - 225
crop_characters.append(curr_num)
print("Detect {} letters...".format(len(crop_characters)))
fig = plt.figure(figsize=(10,6))
plt.axis(False)
plt.imshow(test_roi)
plt.savefig('img/test_roi.jpg', dpi=300,bbox_inches='tight')
#plt.savefig('grab_digit_contour.png',dpi=300)
fig = plt.figure(figsize=(14,4))
grid = gridspec.GridSpec(ncols=len(crop_characters),nrows=1,figure=fig)
for i in range(len(crop_characters)):
fig.add_subplot(grid[i])
plt.axis(False)
plt.imshow(crop_characters[i],cmap="gray")
plt.savefig('img/crop_characters.jpg')
#plt.savefig("segmented_leter.png",dpi=300,bbox_inches='tight')
fig = plt.figure(figsize=(15,3))
cols = len(crop_characters)
grid = gridspec.GridSpec(ncols=cols,nrows=1,figure=fig)
final_string = ''
for i,character in enumerate(crop_characters):
fig.add_subplot(grid[i])
title = np.array2string(CarModel.predict_from_model(character,model,labels))
plt.title('{}'.format(title.strip("'[]"),fontsize=20))
final_string+=title.strip("'[]")
plt.axis(False)
plt.imshow(character,cmap='gray')
plt.savefig('img/character.jpg', dpi=300,bbox_inches='tight')
print(final_string)
plt.savefig('img/final_result.jpg', dpi=300,bbox_inches='tight')
return final_string
import cv2 import numpy as np import matplotlib.pyplot as plt import matplotlib.gridspec as gridspec from local_utils import detect_lp from os.path import splitext,basename from keras.models import model_from_json from keras.preprocessing.image import load_img, img_to_array from keras.applications.mobilenet_v2 import preprocess_input from sklearn.preprocessing import LabelEncoder import glob from model import CarModel from helpers import CarHelpers wpod_net_path = "model/wpod-net.json" wpod_net = CarModel.load_model(wpod_net_path) test_image_path = "Plate_examples/2.jpg" vehicle, LpImg,cor = CarHelpers.get_plate(test_image_path, wpod_net) fig = plt.figure(figsize=(12,6)) grid = gridspec.GridSpec(ncols=2,nrows=1,figure=fig) fig.add_subplot(grid[0]) plt.axis(False) plt.imshow(vehicle) grid = gridspec.GridSpec(ncols=2,nrows=1,figure=fig) fig.add_subplot(grid[1]) plt.axis(False) plt.imshow(LpImg[0]) if (len(LpImg)): #check if there is at least one license image
def import_car_models(self, csv):
ranges = ModelRange.all().fetch(100)
imported = 0
lines = csv.split('\n')
for line in lines:
if len(line.strip()) == 0:
print 'Skipping line',line
continue
model = CarModel()
fields = line.strip().split(';')
model.model_range = self.get_range(ranges, fields[0].strip())
model.name = fields[1].strip()
model.engine_code = fields[2].strip()
model.typeno = fields[3].strip()
if fields[4].strip() != '':
model.image_url = db.Link(fields[4].strip())
model.year_from = int(fields[5])
model.year_to = int(fields[6])
model.notes = fields[7].strip()
model.put()
imported = imported + 1
print imported,'models imported'
def import_car_models(self, csv):
ranges = ModelRange.all().fetch(100)
imported = 0
lines = csv.split('\n')
for line in lines:
if len(line.strip()) == 0:
print 'Skipping line', line
continue
model = CarModel()
fields = line.strip().split(';')
model.model_range = self.get_range(ranges, fields[0].strip())
model.name = fields[1].strip()
model.engine_code = fields[2].strip()
model.typeno = fields[3].strip()
if fields[4].strip() != '':
model.image_url = db.Link(fields[4].strip())
model.year_from = int(fields[5])
model.year_to = int(fields[6])
model.notes = fields[7].strip()
model.put()
imported = imported + 1
print imported, 'models imported'
def task_model_restore(items):
model_count = 0
for item in items:
mrange = ModelRange()
mrange.name = item['name']
mrange.year_start = item['yearStart']
mrange.year_end = item['yearEnd']
mrange.notes = item['notes']
mrange.put()
for model in item['carModels']:
carmodel = CarModel(key_name=model['modelId'])
carmodel.name = model['name']
carmodel.engine_code = model['engineCode']
carmodel.typeno = model['typeNo']
if model['imageUrl'] != None:
carmodel.imageUrl = db.Link(model['imageUrl'])
carmodel.year_from = model['yearFrom']
carmodel.year_to = model['yearTo']
carmodel.notes = model['notes']
carmodel.model_range = mrange
carmodel.put()
model_count = model_count + 1
def task_model_restore(items):
model_count = 0
for item in items:
mrange = ModelRange()
mrange.name = item['name']
mrange.year_start = item['yearStart']
mrange.year_end = item['yearEnd']
mrange.notes = item['notes']
mrange.put()
for model in item['carModels']:
carmodel = CarModel(key_name=model['modelId'])
carmodel.name = model['name']
carmodel.engine_code = model['engineCode']
carmodel.typeno = model['typeNo']
if model['imageUrl'] != None:
carmodel.imageUrl = db.Link(model['imageUrl'])
carmodel.year_from = model['yearFrom']
carmodel.year_to = model['yearTo']
carmodel.notes = model['notes']
carmodel.model_range = mrange
carmodel.put()
model_count = model_count + 1
def get_default_model():
"""Return the default model name"""
return CarModel.all().filter('name', DEFAULT_MODEL_NAME).fetch(1)[0]
results_delay = []
for num, cars in enumerate(traffic_occupations, start=0):
print("Running: " + str(cars) + " cars..")
results_speed.append([])
results_delay.append([])
settings = []
for x in speed_limits:
settings.append([cars, 100, acceleration, 50, randomization, x])
for num_setting, setting in enumerate(settings, start=0):
results_speed[num].append([])
results_delay[num].append([])
all_delay = []
all_speeds = []
model = CarModel(*setting)
for i in range(n):
model.step()
# Store the results
total = 0
for agent in model.schedule.agents:
total += agent.speed
ave_speed = total / model.num_agents
all_delay.append(abs(setting[5] - ave_speed))
all_speeds.append(ave_speed)
results_speed[num][num_setting] = np.mean(all_speeds)
results_delay[num][num_setting] = np.mean(all_delay)
def plot_line(x_data, y_data, y_label):
