如何將整個keras模型轉換爲theano函數

我想將我的keras模型轉換爲theano函數，以便我可以計算輸入上的梯度。我認爲這對於可視化網絡可能很酷。我想使用這些漸變來增強原始圖像中基於神經網絡認爲它們的特徵。我不明白我在做什麼錯了下面的代碼。如何將整個keras模型轉換爲theano函數

model = Sequential() 
model.add(InputLayer((3, H, W))) 
model.add(GaussianNoise(0.03)) 

model.add(Flatten()) 
model.add(Dense(512, activation = 'relu', name = 'dense')) 
model.add(Dropout(0.2)) 
model.add(Dense(20, activation = 'relu')) 
model.add(Dense(C, activation = 'softmax', W_regularizer = l2())) 
... 
f = theano.function([model.input], model.output)

我收到以下異常。

theano.gof.fg.MissingInputError: A variable that is an input to the graph was neither provided as an input to the function nor given a value. A chain of variables leading from this input to an output is [keras_learning_phase, DimShuffle{x,x}.0, Elemwise{switch,no_inplace}.0, dot.0, Elemwise{add,no_inplace}.0, Elemwise{add,no_inplace}.0, Elemwise{mul,no_inplace}.0, dot.0, Elemwise{add,no_inplace}.0, Softmax.0]. This chain may not be unique 
Backtrace when the variable is created: 
    File "<frozen importlib._bootstrap>", line 222, in _call_with_frames_removed 
    File "/usr/local/lib/python3.5/dist-packages/keras/backend/__init__.py", line 51, in <module> 
    from .theano_backend import * 
    File "<frozen importlib._bootstrap>", line 969, in _find_and_load 
    File "<frozen importlib._bootstrap>", line 958, in _find_and_load_unlocked 
    File "<frozen importlib._bootstrap>", line 673, in _load_unlocked 
    File "<frozen importlib._bootstrap_external>", line 662, in exec_module 
    File "<frozen importlib._bootstrap>", line 222, in _call_with_frames_removed 
    File "/usr/local/lib/python3.5/dist-packages/keras/backend/theano_backend.py", line 13, in <module> 
    _LEARNING_PHASE = T.scalar(dtype='uint8', name='keras_learning_phase') # 0 = test, 1 = train

來源

2016-05-14 chasep255

繼FAQ，請嘗試：

from keras import backend as K 
get_last_layer_output = K.function([model.layers[0].input], 
            [model.layers[-1].output])

有關最新版本Keras（1.0），使用

from keras import backend as K 
get_last_layer_output = K.function([model.layers[0].input], 
            [model.layers[-1].get_output(train=False)])

來源

2016-05-14 08:47:52

對於「老」 keras（0.3.X，例如）：

我不使用這個版本，但像this one這樣的例子應該可以工作。

對於「新」 keras（1.0+）：（0測試，1培訓）

由於您使用Dropout層，你將需要添加其他輸入K.learning_phase()並給它的值爲0

代碼：

from keras import backend as K 
K.function([model.layers[0].input, K.learning_phase()], [model.layers[-1].output])

參考：keras FAQ

來源

2016-06-08 11:42:05 sytrus

如何將整個keras模型轉換爲theano函數

回答

相關問題