Open raouflamari opened 6 years ago
hi there, I am trying to implement an autoencoder to reconstruct 76 input features.
Here is my code:
features = ['f1', 'f2', ...., 'f76'] assembler = VectorAssembler(inputCols=features, outputCol="features") dataset = assembler.transform(df) scaler = MinMaxScaler(inputCol="features", outputCol="features_scaled") scaler_model = scaler.fit(dataset) dataset = scaler_model.transform(dataset) nb_features = len(features) model = Sequential() model.add(Dense(50, activation='relu', input_shape=(nb_features,))) model.add(Dense(nb_features, activation='sigmoid')) model.summary() Layer (type) Output Shape Param # ================================================================= dense_1 (Dense) (None, 50) 3850 _________________________________________________________________ dense_2 (Dense) (None, 76) 3876 ================================================================= Total params: 7,726 Trainable params: 7,726 Non-trainable params: 0 _________________________________________________________________ trainer = SingleTrainer(keras_model=model, worker_optimizer="adam", loss="mae", features_col="features_scaled", label_col="features_scaled", num_epoch=5, batch_size=32) trained_model = trainer.train(dataset)
The training is taking more than 10 hours and still running! Am I missing some thing?
hi there, I am trying to implement an autoencoder to reconstruct 76 input features.
Here is my code:
The training is taking more than 10 hours and still running! Am I missing some thing?