def run(self):
print "Preparing the environment"
self.prepareEnvironment()
print "Reading in the training data"
imageCollections = data_io.get_train_df()
wndchrmWorker = WndchrmWorkerTrain()
print "Getting features"
if not self.loadWndchrm: #Last wndchrm set of features
featureGetter = FeatureGetter()
fileName = data_io.get_savez_name()
if not self.load: #Last features calculated from candidates
(namesObservations, coordinates, train) = Utils.calculateFeatures(fileName, featureGetter, imageCollections)
else:
(namesObservations, coordinates, train) = Utils.loadFeatures(fileName)
print "Getting target vector"
(indexes, target, obs) = featureGetter.getTargetVector(coordinates, namesObservations, train)
print "Saving images"
imageSaver = ImageSaver(coordinates[indexes], namesObservations[indexes],
imageCollections, featureGetter.patchSize, target[indexes])
imageSaver.saveImages()
print "Executing wndchrm algorithm and extracting features"
(train, target) = wndchrmWorker.executeWndchrm()
else:
(train, target) = wndchrmWorker.loadWndchrmFeatures()
print "Training the model"
model = RandomForestClassifier(n_estimators=500, verbose=2, n_jobs=1, min_samples_split=30, random_state=1, compute_importances=True)
model.fit(train, target)
print model.feature_importances_
print "Saving the classifier"
data_io.save_model(model)
def run(self):
print "Preparing the environment"
self.prepareEnvironment()
print "Reading in the training data"
imageCollections = data_io.get_train_df()
wndchrmWorker = WndchrmWorkerTrain()
print "Getting features"
if not self.loadWndchrm: #Last wndchrm set of features
featureGetter = FeatureGetter()
fileName = data_io.get_savez_name()
if not self.load: #Last features calculated from candidates
(namesObservations, coordinates,
train) = Utils.calculateFeatures(fileName, featureGetter,
imageCollections)
else:
(namesObservations, coordinates,
train) = Utils.loadFeatures(fileName)
print "Getting target vector"
(indexes, target,
obs) = featureGetter.getTargetVector(coordinates,
namesObservations, train)
print "Saving images"
imageSaver = ImageSaver(coordinates[indexes],
namesObservations[indexes],
imageCollections, featureGetter.patchSize,
target[indexes])
imageSaver.saveImages()
print "Executing wndchrm algorithm and extracting features"
(train, target) = wndchrmWorker.executeWndchrm()
else:
(train, target) = wndchrmWorker.loadWndchrmFeatures()
print "Training the model"
model = RandomForestClassifier(n_estimators=500,
verbose=2,
n_jobs=1,
min_samples_split=30,
random_state=1,
compute_importances=True)
model.fit(train, target)
print model.feature_importances_
print "Saving the classifier"
data_io.save_model(model)
def start(self):
# Do not change
width = 352
height = 352
# output to capture image
output = np.empty((height, width, 3), dtype=np.uint8)
# Init camera
camera = Camera(width, height)
# Init image saver
imageSaver = ImageSaver()
# Init model
model = self.getModel()
# Init notificator
notificator = Notificator()
# Start predicting
tempCount = 1
while True:
#print("Step...")
#start = time.time()
# Capture image to output
camera.capture(output)
imageToCrop = Image.fromarray(output)
image = self.cropImage(imageToCrop, 110, 87, 224)
tempName = 'temp{}.jpg'.format(tempCount)
image.save(tempName)
tempCount += 1
if tempCount > Notificator.PREDICTIONS_LENGTH:
tempCount = 1
# Predict
prediction = model.predict(imagePath=tempName)
# Save image to disk with label and probability
imageSaver.save(image, prediction)
# Manage Notification
notificator.manageNotification(prediction)
#print("Step took {} seconds".format(time.time()-start))
camera.close()
def run(self):
print "Preparing the environment"
self.prepareEnvironment()
print "Loading the classifier"
classifier = data_io.load_model()
imageCollections = data_io.get_valid_df()
featureGetter = FeatureGetter()
wndchrmWorker = WndchrmWorkerPredict()
print "Getting the features"
if not self.loadWndchrm: #Last wndchrm set of features
fileName = data_io.get_savez_name_test()
if not self.load: #Last features calculated from candidates
(namesObservations, coordinates,
_) = Utils.calculateFeatures(fileName, featureGetter,
imageCollections)
else:
(namesObservations, coordinates,
_) = Utils.loadFeatures(fileName)
print "Saving images"
imageSaver = ImageSaver(coordinates, namesObservations,
imageCollections, featureGetter.patchSize)
imageSaver.saveImages()
print "Executing wndchrm algorithm"
valid = wndchrmWorker.executeWndchrm(namesObservations)
else:
(valid, namesObservations) = wndchrmWorker.loadWndchrmFeatures()
print "Making predictions"
predictions = classifier.predict(valid)
predictions = predictions.reshape(len(predictions), 1)
print "Writing predictions to file"
data_io.write_submission(namesObservations, coordinates, predictions)
data_io.write_submission_nice(namesObservations, coordinates,
predictions)
print "Calculating final results"
return Predictor.finalResults(namesObservations, predictions,
coordinates)
from MainCrawler import MainCrawler from CakeCrawler import CakeCrawler from XlsWrite import XlsWrite from ImageSaver import ImageSaver m = MainCrawler() print "Crawling main page..." m.crawl() c = CakeCrawler(m.cake_list) print "Crawling cake pages..." c.crawl() x = XlsWrite(c.cake_list) print "Writing Excel sheet..." x.populate_excel() i = ImageSaver(c.cake_list) print "Saving cake images..." i.save_images()
