[英]Disappearing Dimensions in Multi-Output Keras Model
當我嘗試訓練如下所述的自動編碼器時,收到一個錯誤,即在將形狀( 256、28、28、1 )的目標數組用作形狀(None, 0、28、1 )的輸出時傳遞了目標數組`binary_crossentropy。 這種損失預計目標將具有與輸出相同的形狀。” 輸入和輸出尺寸都應為(28,28,1),其中256為批次大小。 運行.summary()確認解碼器模型的輸出正確(28、28、1),但是當編碼器和解碼器一起編譯時,這似乎有所改變。 知道這里發生了什么嗎? 生成網絡時,將依次調用這三個功能。
def buildEncoder():
input1 = Input(shape=(28,28,1))
input2 = Input(shape=(28,28,1))
merge = concatenate([input1,input2])
convEncode1 = Conv2D(16, (3,3), activation = 'relu', padding = 'same')(merge)
maxPoolEncode1 = MaxPooling2D(pool_size=(2, 1))(convEncode1)
convEncode2 = Conv2D(16, (3,3), activation = 'sigmoid', padding = 'same')(maxPoolEncode1)
convEncode3 = Conv2D(1, (3,3), activation = 'sigmoid', padding = 'same')(convEncode2)
model = Model(inputs = [input1,input2], outputs = convEncode3)
model.compile(loss='binary_crossentropy', optimizer=adam)
return model
def buildDecoder():
input1 = Input(shape=(28,28,1))
upsample1 = UpSampling2D((2,1))(input1)
convDecode1 = Conv2D(16, (3,3), activation = 'relu', padding = 'same')(upsample1)
crop1 = Cropping2D(cropping = ((0,28),(0,0)))(convDecode1)
crop2 = Cropping2D(cropping = ((28,0),(0,0)))(convDecode1)
convDecode2_1 = Conv2D(16, (3,3), activation = 'relu', padding = 'same')(crop1)
convDecode3_1 = Conv2D(16, (3,3), activation = 'relu', padding = 'same')(crop2)
convDecode2_2 = Conv2D(1, (3,3), activation = 'sigmoid', padding = 'same')(convDecode2_1)
convDecode3_2 = Conv2D(1, (3,3), activation = 'sigmoid', padding = 'same')(convDecode3_1)
model = Model(inputs=input1, outputs=[convDecode2_2,convDecode3_2])
model.compile(loss='binary_crossentropy', optimizer=adam)
return model
def buildAutoencoder():
autoInput1 = Input(shape=(28,28,1))
autoInput2 = Input(shape=(28,28,1))
encode = encoder([autoInput1,autoInput2])
decode = decoder(encode)
model = Model(inputs=[autoInput1,autoInput2], outputs=[decode[0],decode[1]])
model.compile(loss='binary_crossentropy', optimizer=adam)
return model
運行model.summary()函數可確認此對象的最終輸出尺寸
看起來您的編碼器中形狀計算錯誤。 您假設解碼器將獲得(None,28,28,1),但您的編碼器實際輸出(None,14,28,28,1)。
print(encoder) # Tensor("model_1/conv2d_3/Sigmoid:0", shape=(?, 14, 28, 1), dtype=float32)
現在,在您的解碼器中,您正在裁剪等,假設您有(28,28,1)可能會將其切為0。這些模型是獨立工作的,連接它們時會發生不匹配的情況。
聲明:本站的技術帖子網頁,遵循CC BY-SA 4.0協議,如果您需要轉載,請注明本站網址或者原文地址。任何問題請咨詢:yoyou2525@163.com.