Keras (1.2.2) を使用して、最後のレイヤーが次のようなシーケンシャル モデルをロードしています。
model.add(Dense(512))
model.add(Activation('relu'))
model.add(Dense(nb_classes))
model.add(Activation('softmax'))
次に、最後のレイヤーをポップし、別の全結合レイヤーを追加して、分類レイヤーを再度追加します。
model = load_model('model1.h5')
layer1 = model.layers.pop() # Copy activation_6 layer
layer2 = model.layers.pop() # Copy classification layer (dense_2)
model.add(Dense(512, name='dense_3'))
model.add(Activation('softmax', name='activation_7'))
model.add(layer2)
model.add(layer1)
print(model.summary())
ご覧のとおり、dense_3 と activation_7 はネットワークに接続されていません (「Connected to」の summary() の空の値)。この問題の解決方法を説明しているドキュメントが見つかりません。何か案は？
dense_1 (Dense) (None, 512) 131584 flatten_1[0][0]
____________________________________________________________________________________________________
activation_5 (Activation) (None, 512) 0 dense_1[0][0]
____________________________________________________________________________________________________
dense_3 (Dense) (None, 512) 5632
____________________________________________________________________________________________________
activation_7 (Activation) (None, 512) 0
____________________________________________________________________________________________________
dense_2 (Dense) (None, 10) 5130 activation_5[0][0]
____________________________________________________________________________________________________
activation_6 (Activation) (None, 10) 0 dense_2[0][0]
====================================================================================================
以下の回答に従って、印刷する前にモデルをコンパイルしましたmodel.summary()が、いくつかの理由で、要約が示すように、レイヤーが正しくポップされていません: 最後のレイヤーの接続が間違っています:
dense_1 (Dense) (None, 512) 131584 flatten_1[0][0]
____________________________________________________________________________________________________
activation_5 (Activation) (None, 512) 0 dense_1[0][0]
____________________________________________________________________________________________________
dense_3 (Dense) (None, 512) 5632 activation_6[0][0]
____________________________________________________________________________________________________
activation_7 (Activation) (None, 512) 0 dense_3[0][0]
____________________________________________________________________________________________________
dense_2 (Dense) (None, 10) 5130 activation_5[0][0]
activation_7[0][0]
____________________________________________________________________________________________________
activation_6 (Activation) (None, 10) 0 dense_2[0][0]
dense_2[1][0]
====================================================================================================
しかし、そうあるべきです
dense_1 (Dense) (None, 512) 131584 flatten_1[0][0]
____________________________________________________________________________________________________
activation_5 (Activation) (None, 512) 0 dense_1[0][0]
____________________________________________________________________________________________________
dense_3 (Dense) (None, 512) 5632 activation_5[0][0]
____________________________________________________________________________________________________
activation_7 (Activation) (None, 512) 0 dense_3[0][0]
____________________________________________________________________________________________________
dense_2 (Dense) (None, 10) 5130
activation_7[0][0]
____________________________________________________________________________________________________
activation_6 (Activation) (None, 10) 0 dense_2[0][0]
====================================================================================================