2023-04-18 22:46:57 +00:00
|
|
|
import numpy as np
|
|
|
|
|
2023-04-21 22:01:17 +00:00
|
|
|
from keras_core import Model
|
2023-04-18 22:46:57 +00:00
|
|
|
from keras_core import layers
|
|
|
|
from keras_core import losses
|
|
|
|
from keras_core import metrics
|
|
|
|
from keras_core import optimizers
|
|
|
|
|
2023-05-03 05:44:46 +00:00
|
|
|
inputs = layers.Input((100,), batch_size=32)
|
2023-04-21 22:01:17 +00:00
|
|
|
x = layers.Dense(256, activation="relu")(inputs)
|
|
|
|
x = layers.Dense(256, activation="relu")(x)
|
|
|
|
x = layers.Dense(256, activation="relu")(x)
|
2023-04-18 22:46:57 +00:00
|
|
|
outputs = layers.Dense(16)(x)
|
2023-04-20 21:50:03 +00:00
|
|
|
model = Model(inputs, outputs)
|
2023-04-21 22:01:17 +00:00
|
|
|
|
2023-04-18 22:46:57 +00:00
|
|
|
model.summary()
|
|
|
|
|
2023-05-03 05:44:46 +00:00
|
|
|
x = np.random.random((50000, 100))
|
2023-04-18 22:46:57 +00:00
|
|
|
y = np.random.random((50000, 16))
|
|
|
|
batch_size = 32
|
2023-05-03 05:44:46 +00:00
|
|
|
epochs = 5
|
2023-04-18 22:46:57 +00:00
|
|
|
|
|
|
|
model.compile(
|
|
|
|
optimizer=optimizers.SGD(learning_rate=0.001),
|
|
|
|
loss=losses.MeanSquaredError(),
|
|
|
|
metrics=[metrics.MeanSquaredError()],
|
|
|
|
)
|
2023-04-21 22:01:17 +00:00
|
|
|
history = model.fit(
|
|
|
|
x, y, batch_size=batch_size, epochs=epochs, validation_split=0.2
|
|
|
|
)
|
2023-04-18 22:46:57 +00:00
|
|
|
|
|
|
|
print("History:")
|
|
|
|
print(history.history)
|