def straight_flames():
import os
os.chdir(os.path.dirname(os.path.abspath(__file__)))
model = Model(n_characters, n_hidden, n_characters, n_layers)
model.load("models/wtchrrnn.pt")
return " ".join(model.generate("Add ", 40).split(" ")[:-1]).strip() + "."
else: y = 0
h += 2 * CropPadding
if x > CropPadding: x = x - CropPadding
else: x = 0
w += 2 * CropPadding
return [x, y, w, h]
if __name__ == '__main__':
# Change working directory
os.chdir(os.path.dirname(os.path.realpath(__file__)))
cap = cv2.VideoCapture(0)
model = Model()
model.load()
# Get Cascade Classifier
cascade = cv2.CascadeClassifier(cascade_path)
isme = 0
notme = 0
nDelay = 0
# Run window in other thread
cv2.startWindowThread()
while True:
_, frame = cap.read()
from train import Model
from preprocess import constructTensors
model = Model()
model.load('parameters')
Input, Output = constructTensors()
print(model.forward(Input))
print(Output)
if file.endswith('.jpg') or file.endswith('.png'):
print('test %s' % file)
file_path = os.path.abspath(os.path.join(path, file))
image = read_image(file_path)
result = model.predict(image)
index = np.argmax(result)
print(classes[index], result[index])
if __name__ == '__main__':
classes = []
parser = argparse.ArgumentParser()
parser.add_argument('--predict_dir', type=str, help='folder of images')
args = parser.parse_args()
if args.predict_dir:
model = Model()
try:
model.load(file_path=args.predict_dir + '\model.h5')
with open(args.predict_dir + '\labels.txt', 'r') as f:
for line in f.readlines():
classes.append(line.strip())
except OSError as e:
print(
"<--------------------Unable to open file-------------------->\n",
e)
else:
prediction(args.predict_dir, classes)
else:
print(
'Input no found\nTry "python predict.py -h" for more information')
model = Model(n_characters, n_hidden, n_characters, n_layers)
model.load("models/wtchrrnn.pt")
return " ".join(model.generate("Add ", 40).split(" ")[:-1]).strip() + "."
if __name__ == "__main__":
argparser = argparse.ArgumentParser()
argparser.add_argument('--model',
type=str,
default="save/char-rnn-gru.pt",
help="Path to trained model")
argparser.add_argument(
'--prime',
type=str,
required=True,
help="Prime string to predict next sequence of characters")
argparser.add_argument('--len',
type=int,
default=1000,
help="Predict string length")
args = argparser.parse_args()
warnings.filterwarnings("ignore")
model = Model(n_characters, n_hidden, n_characters, n_layers)
model.load(args.model)
print(model.generate(args.prime, args.len))