22 lines
691 B
Python
22 lines
691 B
Python
|
import numpy as np
|
||
|
|
from tensorflow.keras import Sequential, Input, layers, optimizers
|
||
|
|
|
||
|
|
x = np.array([[0, 0, 0], [0, 0, 1], [0, 1, 0], [1, 0, 0], [0, 1, 1], [1, 0, 1], [1, 1, 0], [1, 1, 1]])
|
||
|
|
y = np.array([0, 1, 1, 1, 0, 0, 0, 1])
|
||
|
|
|
||
|
|
model = Sequential([
|
||
|
|
Input(shape=(3,)),
|
||
|
|
layers.Dense(3, activation="tanh"),
|
||
|
|
layers.Dense(1, activation="sigmoid"),
|
||
|
|
])
|
||
|
|
|
||
|
|
model.compile(optimizer=optimizers.Adam(learning_rate=0.05), loss="binary_crossentropy", metrics=["accuracy"])
|
||
|
|
model.fit(x, y, epochs=100)
|
||
|
|
|
||
|
|
loss, accuracy = model.evaluate(x, y)
|
||
|
|
print(f"Loss: {loss}")
|
||
|
|
print(f"Accuracy: {accuracy}")
|
||
|
|
|
||
|
|
prediction = model.predict(x)
|
||
|
|
for inp, pred in zip(x, prediction):
|
||
|
|
print(inp, round(pred[0]))
|