njs03332 / ml_study

3 stars 0 forks source link

2024/04/08 ~ 2024/04/15 #83

Open givitallugot opened 5 months ago

givitallugot commented 5 months ago

1: 17.3.4 2: 17.3.5 3: 17.3.6

04.15(월) ~09:30~ pm 10:30

image

givitallugot commented 4 months ago

17.3.5 가중치 묶기

dense_1 = keras.layers.Dense(100, activation="selu") dense_2 = keras.layers.Dense(30, activation="selu")

tied_encoder = keras.models.Sequential([ keras.layers.Flatten(input_shape=[28, 28]), dense_1, dense_2 ])

tied_decoder = keras.models.Sequential([ DenseTranspose(dense_2, activation="selu"), DenseTranspose(dense_1, activation="sigmoid"), keras.layers.Reshape([28, 28]) ])

tied_ae = keras.models.Sequential([tied_encoder, tied_decoder])

tied_ae.compile(loss="binary_crossentropy", optimizer=keras.optimizers.SGD(learning_rate=1.5), metrics=[rounded_accuracy]) history = tied_ae.fit(X_train, X_train, epochs=10, validation_data=(X_valid, X_valid))

njs03332 commented 4 months ago

17.3.4 적층 오토인코더를 사용한 비지도 사전훈련

image

danbi5228 commented 4 months ago

17.3.6 한 번에 오토인코더 한 개씩 훈련하기