我基于https://blog.keras.io/building-autoencoders-in-keras.html中的讨论，构建了一个用于mnist数据集的去噪自编码器。
我试图观察输入图像重建随时间的变化；我注意到有时DAE的损失会突然增加（无论是训练还是验证），例如从约0.12的损失增加到约3.0。为了避免在训练过程中使用这些“失误”，我尝试使用Keras的回调函数，保存最佳权重（基于验证损失），并在每次“段”训练后加载它们（在我这里，每段训练为10个epoch）。
然而，我收到了一个错误消息：
File "noise_e_mini.py", line 71, in <module> callbacks=([checkpointer])) File "/usr/local/lib/python2.7/dist-packages/keras/engine/training.py", line 1650, in fit validation_steps=validation_steps) File "/usr/local/lib/python2.7/dist-packages/keras/engine/training.py", line 1145, in _fit_loop callbacks.set_model(callback_model) File "/usr/local/lib/python2.7/dist-packages/keras/callbacks.py", line 48, in set_model callback.set_model(model)AttributeError: 'tuple' object has no attribute 'set_model'
我的代码是：
from keras.layers import Input, Densefrom keras.models import Modelfrom keras import regularizersfrom keras.callbacks import ModelCheckpointinput_img = Input(shape=(784,))filepath_for_w='denoise_by_AE_weights_1.h5'def autoencoder_block(input,l1_score_encode,l1_score_decode): # encoder: encoded = Dense(256, activation='relu',activity_regularizer=regularizers.l1(l1_score_encode))(input_img) encoded = Dense(128, activation='relu',activity_regularizer=regularizers.l1(l1_score_encode))(encoded) encoded = Dense(64, activation='relu',activity_regularizer=regularizers.l1(l1_score_encode))(encoded) encoded = Dense(32, activation='relu',activity_regularizer=regularizers.l1(l1_score_encode))(encoded) encoder = Model (input=input_img, output=encoded) # decoder: connection_layer= Input(shape=(32,)) decoded = Dense(64, activation='relu',activity_regularizer=regularizers.l1(l1_score_decode))(connection_layer) decoded = Dense(128, activation='relu',activity_regularizer=regularizers.l1(l1_score_decode))(decoded) decoded = Dense(256, activation='relu',activity_regularizer=regularizers.l1(l1_score_decode))(decoded) decoded = Dense(784, activation='sigmoid',activity_regularizer=regularizers.l1(l1_score_decode))(decoded) decoder = Model (input=connection_layer , output=decoded) crunched = encoder(input_img) final = decoder(crunched) autoencoder = Model(input=input_img, output=final) autoencoder.compile(optimizer='adadelta', loss='binary_crossentropy') return (autoencoder)from keras.datasets import mnistimport numpy as np(x_train, y_train), (x_test, y_test) = mnist.load_data()x_train = x_train.astype('float32') / 255.x_test = x_test.astype('float32') / 255.x_train = x_train.reshape((len(x_train), np.prod(x_train.shape[1:])))x_test = x_test.reshape((len(x_test), np.prod(x_test.shape[1:])))print x_train.shapeprint x_test.shapenoise_factor = 0.5x_test_noisy = x_test + noise_factor * np.random.normal(loc=0.0, scale=1.0, size=x_test.shape) x_test_noisy = np.clip(x_test_noisy, 0., 1.)autoencoder=autoencoder_block(input_img,0,0)for i in range (10): x_train_noisy = x_train + noise_factor * np.random.normal(loc=0.0, scale=1.0, size=x_train.shape) x_train_noisy = np.clip(x_train_noisy, 0., 1.) checkpointer=ModelCheckpoint(filepath_for_w, monitor='val_loss', verbose=0, save_best_only=True, save_weights_only=True, mode='auto', period=1), autoencoder.fit(x_train_noisy, x_train, epochs=10, batch_size=256, shuffle=True, validation_data=(x_test_noisy, x_test), callbacks=([checkpointer])) autoencoder.load_weights(filepath_for_w) # load weights from the best in the run decoded_imgs = autoencoder.predict(x_test_noisy) # save results for this stage for presentation np.save('decoded'+str(i)+'.npy',decoded_imgs) ####np.save('tested.npy',x_test_noisy)np.save ('true_catagories.npy',y_test)np.save('original.npy',x_test)autoencoder.save('denoise_by_AE_model_1.h5')我哪里做错了？非常感谢 🙂
回答：
你的问题可能出在这一行
callbacks=([checkpointer]))你需要删除括号，因为callbacks需要的是列表而不是元组，试试这样：
callbacks=[checkpointer]我还注意到你的checkpointer后面有一个逗号，你也应该删除它。
checkpointer=ModelCheckpoint(filepath_for_w, monitor='val_loss', verbose=0, save_best_only=True, save_weights_only=True, mode='auto', period=1),