def main():
args = parser.parse_args()
casc_type = os.path.abspath('./data/lbpcascade_frontalface.xml')
# casc_type = os.path.abspath('./data/haarcascade_frontalface_default.xml')
face_cascade = cv2.CascadeClassifier(casc_type)
# Training data
# face_recognizer = cv2.face.createLBPHFaceRecognizer()
# face_recognizer = cv2.face.LBPHFaceRecognizer_create()
# or use EigenFaceRecognizer by replacing above line with
# face_recognizer = cv2.face.createEigenFaceRecognizer()
# face_recognizer = cv2.face.EigenFaceRecognizer_create()
# or use FisherFaceRecognizer by replacing above line with
# face_recog = cv2.face.createFisherFaceRecognizer()
face_recog = cv2.face.FisherFaceRecognizer_create()
folder_path = os.path.abspath('./training_sets')
if args.add != 'none':
get_photos.main(args.add, args.num)
if args.train:
print("Preparing data...")
faces, labels, names = train_model.prepare_training_data(
face_cascade, folder_path)
print("Data prepared")
# print total faces and labels
print("Total faces: ", len(faces))
print("Total labels: ", len(labels))
print(names)
face_recog = train_model.recognizer(faces, labels)
else:
face_recog.read(args.model)
names = getNamesMap(folder_path)
vid = cv2.VideoCapture(0)
in_row_count = 0
while True:
ret, frame = vid.read()
image, conf, name = train_model.predict(face_cascade, frame,
face_recog, names)
if image is not None:
cv2.imshow("Faces found", image)
if conf < 350:
in_row_count += 1
else:
in_row_count = 0
if in_row_count > 10:
print("Unlocked user %s!" % name)
in_row_count = 0
if cv2.waitKey(1) & 0xFF == ord('q'):
break
vid.release()
cv2.destroyAllWindows()
def main():
detector = dlib.get_frontal_face_detector()
cam = cv2.VideoCapture(0)
success, frame = cam.read()
while success and cv2.waitKey(1) == -1:
success, frame = cam.read()
gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
faces = detector(gray, 1)
for i, d in enumerate(faces):
x = d.top() if d.top() > 0 else 0
w = d.bottom() if d.bottom() > 0 else 0
y = d.left() if d.left() > 0 else 0
h = d.right() if d.right() > 0 else 0
det = frame[x:x + w, y:y + h]
det = cv2.resize(det, (img_size, img_size),
interpolation=cv2.INTER_LINEAR)
label, prob = predict(model, det)
if prob > 0.9:
show_name = name_list[label]
else:
show_name = 'Unknown'
cv2.putText(frame, show_name, (y, w - 20),
cv2.FONT_HERSHEY_SIMPLEX, 1, 255, 2)
frame = cv2.rectangle(frame, (y, x), (h, w), (255, 0, 0), 2)
cv2.imshow("Camera", frame)
cam.release()
cv2.destroyAllWindows()
def main():
cam = cv2.VideoCapture(0)
success, frame = cam.read()
while success and cv2.waitKey(1) == -1:
success, frame = cam.read()
det = cv2.resize(frame, (img_size, img_size),
interpolation=cv2.INTER_LINEAR)
# det = image.array_to_img(det)
label, prob = predict(model, det)
if prob > 0.9:
show_name = name_list[label]
else:
show_name = 'Unknown'
cv2.putText(frame, show_name, (20, img_size - 20),
cv2.FONT_HERSHEY_SIMPLEX, 1, 255, 2)
# frame = cv2.rectangle(frame, (y, x), (h, w), (255, 0, 0), 2)
cv2.imshow("Camera", frame)
cam.release()
cv2.destroyAllWindows()
import train_model
import DataPreprocessing
hidden_layer_dims = [7, 8]
layer_types = ['relu', 'relu', 'sigmoid']
learning_rate = 0.001
num_iterations = 1000
# num_batches = 6
lambd = 0
prob = 1
threshold = 0.5
X_train_scaled, X_test_scaled, Y_train, Y_test = DataPreprocessing.opendata(
"wine.csv", "DNN")
X_train_tr = X_train_scaled.T
Y_train_tr = Y_train.T
Y_test = Y_test.T
X_test_scaled = X_test_scaled.T
params = train_model.model(X_train_tr, Y_train_tr, hidden_layer_dims,
layer_types, learning_rate, num_iterations, prob)
yptest, accuracytest = train_model.predict(X_test_scaled, Y_test, params,
hidden_layer_dims, layer_types, 0.5)
print('The accuracy of training set is: %d' % accuracytest)
yptrain, accuracytrain = train_model.predict(X_train_tr, Y_train_tr, params,
hidden_layer_dims, layer_types,
0.5)
print('The accuracy of testing set is: %d' % accuracytrain)
st.warning(
"Tell us which nootropics you have tried. For each substance, please rate your subjective experience on a scale of 0 to 10. 0 means a substance was totally useless, or had so many side effects you couldn't continue taking it. 1 - 4 means for subtle effects, maybe placebo but still useful. 5 - 9 means strong effects, definitely not placebo. 10 means life-changing."
)
slider_dic = {}
checkbox_dic = {}
for nootropic in nootropics_list:
checkbox_dic[nootropic] = st.checkbox("I've tried {}".format(nootropic))
if checkbox_dic[nootropic]:
slider_dic[nootropic] = st.slider("{} rating".format(nootropic),
min_value=0,
max_value=10)
# form = st.form(key=nootropic)
# form.text_input(label="{} rating".format(nootropic))
# form_dic[nootropic] = form
# submit_button = st.form_submit_button(label='Submit')
if st.button("I'm done rating and would like to see predictions"):
new_result_df = predict(slider_dic)
st.write("Our model predicted this ratings for you:")
st.write(new_result_df)
if st.button("How accurate is your model ?"):
if len(slider_dic) < 2:
st.error("Please rate at least two nootropics")
else:
accuracy_df = evaluate(slider_dic)
st.write(
"For each nootropic, we hid your rating to our model, and had the model try to guess it."
)
st.write(accuracy_df)
import insta_api
import train_model
# Train the RF classifier
print()
print("Training results: ")
train_model.train()
print()
# Driver
while (True):
username = input(
"Enter username of user you want to verify whether they are a bot or not: "
)
if (username):
features = insta_api.features(username)
if features:
print(train_model.predict(features))