TensorFlow/Keras中间层的输出

Question

我试图在Keras中获取中间层的输出，下面是我的代码：

XX = model.input # Keras Sequential() model object
YY = model.layers[0].output
F = K.function([XX], [YY]) # K refers to keras.backend


Xaug = X_train[:9]
Xresult = F([Xaug.astype('float32')])

运行这个，我得到了一个错误：

InvalidArgumentError (see above for traceback): You must feed a value for placeholder tensor 'dropout_1/keras_learning_phase' with dtype bool

我逐渐认识到，由于我在模型中使用的是退出层，所以我必须按照keras 文档为我的函数指定一个learning_phase()标志。我将代码更改为：

XX = model.input
YY = model.layers[0].output
F = K.function([XX, K.learning_phase()], [YY])


Xaug = X_train[:9]
Xresult = F([Xaug.astype('float32'), 0])

现在我得到了一个新的错误，我无法弄清楚：

TypeError: Cannot interpret feed_dict key as Tensor: Can not convert a int into a Tensor.

任何帮助都将不胜感激。

PS :我是TensorFlow和Keras的新手。

编辑1 :下面是我正在使用的完整代码。我正在使用空间变压器网络，正如在这个NIPS 纸中所讨论的，它是Kera的实现这里

input_shape =  X_train.shape[1:]

# initial weights
b = np.zeros((2, 3), dtype='float32')
b[0, 0] = 1
b[1, 1] = 1
W = np.zeros((100, 6), dtype='float32')
weights = [W, b.flatten()]

locnet = Sequential()
locnet.add(Convolution2D(64, (3, 3), input_shape=input_shape, padding='same'))
locnet.add(Activation('relu'))
locnet.add(Convolution2D(64, (3, 3), padding='same'))
locnet.add(Activation('relu'))
locnet.add(MaxPooling2D(pool_size=(2, 2)))
locnet.add(Convolution2D(128, (3, 3), padding='same'))
locnet.add(Activation('relu'))
locnet.add(Convolution2D(128, (3, 3), padding='same'))
locnet.add(Activation('relu'))
locnet.add(MaxPooling2D(pool_size=(2, 2)))
locnet.add(Convolution2D(256, (3, 3), padding='same'))
locnet.add(Activation('relu'))
locnet.add(Convolution2D(256, (3, 3), padding='same'))
locnet.add(Activation('relu'))
locnet.add(MaxPooling2D(pool_size=(2, 2)))
locnet.add(Dropout(0.5))
locnet.add(Flatten())
locnet.add(Dense(100))
locnet.add(Activation('relu'))
locnet.add(Dense(6, weights=weights))


model = Sequential()

model.add(SpatialTransformer(localization_net=locnet,
                             output_size=(128, 128), input_shape=input_shape))

model.add(Convolution2D(64, (3, 3), padding='same'))
model.add(Activation('relu'))
model.add(Convolution2D(64, (3, 3), padding='same'))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Convolution2D(128, (3, 3), padding='same'))
model.add(Activation('relu'))
model.add(Convolution2D(128, (3, 3), padding='same'))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Convolution2D(256, (3, 3), padding='same'))
model.add(Activation('relu'))
model.add(Convolution2D(256, (3, 3), padding='same'))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Convolution2D(256, (3, 3), padding='same'))
model.add(Activation('relu'))
model.add(Convolution2D(256, (3, 3), padding='same'))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.5))
model.add(Flatten())
model.add(Dense(256))
model.add(Activation('relu'))

model.add(Dense(num_classes))
model.add(Activation('softmax'))

model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])

#==============================================================================
# Start Training
#==============================================================================
#define training results logger callback
csv_logger = keras.callbacks.CSVLogger(training_logs_path+'.csv')
model.fit(X_train, y_train,
          batch_size=batch_size,
          epochs=20,
          validation_data=(X_valid, y_valid),
          shuffle=True,
          callbacks=[SaveModelCallback(), csv_logger])




#==============================================================================
# Visualize what Transformer layer has learned
#==============================================================================

XX = model.input
YY = model.layers[0].output
F = K.function([XX, K.learning_phase()], [YY])


Xaug = X_train[:9]
Xresult = F([Xaug.astype('float32'), 0])

# input
for i in range(9):
    plt.subplot(3, 3, i+1)
    plt.imshow(np.squeeze(Xaug[i]))
    plt.axis('off')

for i in range(9):
    plt.subplot(3, 3, i + 1)
    plt.imshow(np.squeeze(Xresult[0][i]))
    plt.axis('off')

Answer 1

最简单的方法是在Keras中创建一个新模型，而不调用后端。为此，您需要函数模型API：

from keras.models import Model

XX = model.input 
YY = model.layers[0].output
new_model = Model(XX, YY)

Xaug = X_train[:9]
Xresult = new_model.predict(Xaug)

Answer 2

你可以试试：

model1 = tf.keras.models.Sequential(base_model.layers[:1])
model2 = tf.keras.models.Sequential(base_model.layers[1:])

Xaug = X_train[:9]
out = model1(Xaug)