def create_model(**kwargs):
model = Model(**kwargs)
model.add(number_of_neurons=6)
model.add(number_of_neurons=3)
model.add(number_of_neurons=1)
return model
"optimizer": parse_option_value("-o", dflt=None),
"epoch": parse_option_value("-e", dflt="100")
}
if check_option(options) is False:
usage()
return options
if __name__ == "__main__":
options = parse_options()
# print(options)
# dataset = Dataset("../data_training.csv")
# dataset_test = Dataset("../data_test.csv")
dataset = Dataset(None, 0.2)
model = Model()
model.add(Dense(64, activation="relu"))
model.add(Dense(32, activation="relu"))
model.add(Dense(2, activation="softmax"))
# model.add(64, activation="relu")
# model.add(32, activation="relu")
# model.add(2, activation="softmax")
model.compile(30, metrics=["accuracy"], optimizer="Adam")
print(dataset.features.shape)
print(dataset.test_features.shape)
# print(dataset.features.shape)
# print(numpy.min(model.weights[0]))
history = model.fit(
features=dataset.features,
targets=dataset.targets,
epochs=500,
batch_size=32,
sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
import numpy as np
from layers.activation import Activation
from layers.dense import Dense
from model.model import Model
X_train = np.array([[[0, 0]], [[0, 1]], [[1, 0]], [[1, 1]]])
y_train = np.array([
[[0]], # F
[[1]], # M
[[1]], # M
[[0]] # F
])
model = Model()
model.add(Dense(2, 2))
model.add(Activation('tanh'))
model.add(Dense(2, 2))
model.add(Activation('tanh'))
model.add(Activation('softmax'))
model.fit(X_train, y_train, epochs=1000, learning_rate=0.1)
frank = np.array(X_train) # 155 pounts, 68 inches
pred = model.predict(frank)
print(np.array(pred))
