我已經實作了一個沒有方形輸入的 CNN 自動編碼器。我有點困惑。是否必須為自動編碼器提供方形輸入？每個 2D 影像的形狀為 800x20。我已經根據形狀輸入了資料。但不知何故，在構建模型時形狀不匹配。我已經分享了模型的代碼和下面的錯誤訊息。需要您的專家建議。謝謝。
x = Input(shape=(800, 20,1))
# Encoder
conv1_1 = Conv2D(16, (3, 3), activation='relu', padding='same')(x)
pool1 = MaxPooling2D((2, 2), padding='same')(conv1_1)
conv1_2 = Conv2D(8, (3, 3), activation='relu', padding='same')(pool1)
pool2 = MaxPooling2D((2, 2), padding='same')(conv1_2)
conv1_3 = Conv2D(8, (3, 3), activation='relu', padding='same')(pool2)
h = MaxPooling2D((2, 2), padding='same')(conv1_3)
# Decoder
conv2_1 = Conv2D(8, (3, 3), activation='relu', padding='same')(h)
up1 = UpSampling2D((2, 2))(conv2_1)
conv2_2 = Conv2D(8, (3, 3), activation='relu', padding='same')(up1)
up2 = UpSampling2D((2, 2))(conv2_2)
conv2_3 = Conv2D(16, (3, 3), activation='relu', padding='same')(up2)
up3 = UpSampling2D((2, 2))(conv2_3)
r = Conv2D(1, (3, 3), activation='sigmoid', padding='same')(up3)
model = Model(inputs=x, outputs=r)
model.compile(optimizer='adadelta', loss='binary_crossentropy', metrics=['accuracy'])
results = model.fit(x_train, x_train, epochs = 500, batch_size=16,validation_data= (x_test, x_test))
這是錯誤：
ValueError: logits and labels must have the same shape ((16, 800, 24, 1) vs (16, 800, 20, 1))
uj5u.com熱心網友回復：
正如錯誤跟蹤所示，您在嘗試使用此自動編碼器時面臨的問題是模型期望輸入形狀為(?, 800, 20, 1)，但輸出形狀為(?, 796, 20, 1). 雖然它將每個影像輸入和輸出作為
(800, 20, 1). （檢查模型摘要的輸入和輸出形狀！）
我的推薦——
我已經修復
padding = 'same'并重新調整了形狀，以便輸入張量形狀和輸出相同。查看我修改的內核大小以根據需要獲得輸出形狀。最重要的是，對于堆疊的 conv 編碼器-解碼器架構（例如自動編碼器），建議您將空間資訊轉換為具有后續層的特征圖/過濾器/通道。現在您從 8 個過濾器開始，然后在編碼器中移動到 4 個。應該更像
4->8->16。檢查此圖以參考直覺。
根據上述建議，我在此處進行了更改。
x = Input(shape=(800, 20,1))
# Encoder
conv1_1 = Conv2D(4, (3, 3), activation='relu', padding='same')(x)
pool1 = MaxPooling2D((2, 2), padding='same')(conv1_1)
conv1_2 = Conv2D(8, (3, 3), activation='relu', padding='same')(pool1)
pool2 = MaxPooling2D((2, 2), padding='same')(conv1_2)
conv1_3 = Conv2D(16, (3, 3), activation='relu', padding='same')(pool2)
h = MaxPooling2D((2, 1), padding='same')(conv1_3) #<------
# # Decoder
conv2_1 = Conv2D(16, (3, 3), activation='relu', padding='same')(h)
up1 = UpSampling2D((2, 2))(conv2_1)
conv2_2 = Conv2D(8, (3, 3), activation='relu', padding='same')(up1)
up2 = UpSampling2D((2, 2))(conv2_2)
conv2_3 = Conv2D(4, (3, 3), activation='sigmoid', padding='same')(up2) #<--- ADD PADDING HERE
up3 = UpSampling2D((2, 1))(conv2_3)
r = Conv2D(1, (3, 3), activation='sigmoid', padding='same')(up3)
model = Model(inputs=x, outputs=r)
model.compile(optimizer='adadelta', loss='binary_crossentropy', metrics=['accuracy'])
model.summary()
Model: "model_13"
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
input_16 (InputLayer) [(None, 800, 20, 1)] 0
_________________________________________________________________
conv2d_101 (Conv2D) (None, 800, 20, 4) 40
_________________________________________________________________
max_pooling2d_45 (MaxPooling (None, 400, 10, 4) 0
_________________________________________________________________
conv2d_102 (Conv2D) (None, 400, 10, 8) 296
_________________________________________________________________
max_pooling2d_46 (MaxPooling (None, 200, 5, 8) 0
_________________________________________________________________
conv2d_103 (Conv2D) (None, 200, 5, 16) 1168
_________________________________________________________________
max_pooling2d_47 (MaxPooling (None, 100, 5, 16) 0
_________________________________________________________________
conv2d_104 (Conv2D) (None, 100, 5, 16) 2320
_________________________________________________________________
up_sampling2d_43 (UpSampling (None, 200, 10, 16) 0
_________________________________________________________________
conv2d_105 (Conv2D) (None, 200, 10, 8) 1160
_________________________________________________________________
up_sampling2d_44 (UpSampling (None, 400, 20, 8) 0
_________________________________________________________________
conv2d_106 (Conv2D) (None, 400, 20, 4) 292
_________________________________________________________________
up_sampling2d_45 (UpSampling (None, 800, 20, 4) 0
_________________________________________________________________
conv2d_107 (Conv2D) (None, 800, 20, 1) 37
=================================================================
Total params: 5,313
Trainable params: 5,313
Non-trainable params: 0
_________________________________________________________________
為了顯示模型現在正在運行，讓我創建一個與您正在查看的相同的隨機資料集。
x_train = np.random.random((16,800,20,1))
model.fit(x_train, x_train, epochs=2)
Epoch 1/2
1/1 [==============================] - 0s 180ms/step - loss: 0.7526 - accuracy: 0.0000e 00
Epoch 2/2
1/1 [==============================] - 0s 189ms/step - loss: 0.7526 - accuracy: 0.0000e 00
<tensorflow.python.keras.callbacks.History at 0x7fa85a9896d0>
轉載請註明出處，本文鏈接：https://www.uj5u.com/qianduan/318299.html
上一篇：kerasLSTM應該在沒有input_shape引數的情況下作業嗎？
下一篇：如何將sample_weights與3D醫療資料一起使用，而不會有model.fit(x=tf.data.Dataset)導致無法擠壓最后一個暗淡之類的錯誤