def model(X_train,
Y_train,
X_test,
Y_test,
num_iterations=2000,
learning_rate=0.5,
print_cost=False):
w, b = inicializarconcero(X_train.shape[0])
parameters, grads, costs = optimizar(w, b, X_train, Y_train,
num_iterations, learning_rate,
print_cost)
w = parameters["w"]
b = parameters["b"]
Y_prediction_test = predict4(w, b, X_test)
Y_prediction_train = predict4(w, b, X_train)
d = {
"costos": costs,
"Y_pred_test": Y_prediction_test,
"Y_pred_variable": Y_prediction_train,
"w": w,
"b": b,
"learning_rate": learning_rate,
"cantidad_iteraciones": num_iterations
}
return d
print("db = " + str(grads["db"]))
print("cost = " + str(cost))
print("-----------------------------------")
params, grads, costs = optimizar(w,
b,
X,
y,
num_iterations=10,
learning_rate=0.009,
print_costo=False)
print("w = " + str(params["w"]))
print("b = " + str(params["b"]))
print("dw = " + str(grads["dw"]))
print("db = " + str(grads["db"]))
print("-----------------------------------")
print("predictions = " + str(predict4(w, b, X)))
def gradiente_aprendisaje(X,
y,
dimensiones,
curvaaprendisaje=0.01,
num_iterations=200,
print_costo=True,
theta="relu",
initialization_method="he"):
np.random.seed(1)
costo_list = []
print("db = " + str(grads["db"]))
print("cost = " + str(cost))
print("-----------------------------------")
params, grads, costs = optimizar(w,
b,
X,
y,
num_iterations=10,
learning_rate=0.009,
print_costo=False)
print("w = " + str(params["w"]))
print("b = " + str(params["b"]))
print("dw = " + str(grads["dw"]))
print("db = " + str(grads["db"]))
print("-----------------------------------")
print("predictions = " + str(predict4(w, b, X)))
def gradiente_aprendisaje(X,
y,
dimensiones,
curvaaprendisaje=0.01,
num_iterations=200,
print_costo=True,
theta="relu",
initialization_method="he"):
np.random.seed(1)
costo_list = []
print("db = " + str(grads["db"]))
print("cost = " + str(cost))
print("-----------------------------------")
params, grads, costs = optimizar(w,
b,
X,
y,
num_iterations=10,
learning_rate=0.009,
print_costo=False)
print("w = " + str(params["w"]))
print("b = " + str(params["b"]))
print("dw = " + str(grads["dw"]))
print("db = " + str(grads["db"]))
print("-----------------------------------")
print("predictions = " + str(predict4(w, b, X)))
def gradiente_aprendisaje(X,
y,
dimensiones,
curvaaprendisaje=0.01,
num_iterations=200,
print_costo=True,
theta="relu",
initialization_method="he"):
np.random.seed(1)
costo_list = []
print("db = " + str(grads["db"]))
print("cost = " + str(cost))
print("-----------------------------------")
params, grads, costs = optimizar(w,
b,
X,
y,
num_iterations=10,
learning_rate=0.009,
print_costo=False)
print("w = " + str(params["w"]))
print("b = " + str(params["b"]))
print("dw = " + str(grads["dw"]))
print("db = " + str(grads["db"]))
print("-----------------------------------")
print("predictions = " + str(predict4(w, b, X)))
def gradiente_aprendisaje(X,
y,
dimensiones,
curvaaprendisaje=0.01,
num_iterations=200,
print_costo=True,
theta="relu",
initialization_method="he"):
np.random.seed(1)
costo_list = []