CNN負數參數

Question

我正在嘗試使用keras構建CNN模型。 當我添加兩個Conv3D和MaxPooling塊時，一切正常。 但是，一旦添加了第三個塊（如代碼中所示），則可訓練參數的數量將變為負值。 知道如何發生嗎？

model = keras.models.Sequential()

# # # First Block
model.add(Conv2D(filters=16, kernel_size=(5, 5), padding='valid', input_shape=(157, 462, 14), activation = 'tanh' ))
model.add(MaxPooling2D( (2,2) ))

# # # Second Block     
model.add(Conv2D(filters=32, kernel_size=(5, 5), padding='valid', activation = 'tanh'))
model.add(MaxPooling2D( (2, 2) ))

# # # Third Block   
model.add(Conv2D(filters=64, kernel_size=(5, 5), padding='valid', activation = 'tanh'))
model.add(MaxPooling2D( (2, 2) ))

model.add(Flatten())
model.add(Dense(157 * 462))
model.compile(loss='mean_squared_error',
              optimizer=keras.optimizers.Adamax(),
               metrics=['mean_absolute_error'])

print(model.summary())

該代碼的結果如下：

Layer (type)                 Output Shape              Param #   
=================================================================
conv2d_1 (Conv2D)            (None, 153, 458, 16)      5616      
_________________________________________________________________
max_pooling2d_1 (MaxPooling2 (None, 76, 229, 16)       0         
_________________________________________________________________
conv2d_2 (Conv2D)            (None, 72, 225, 32)       12832     
_________________________________________________________________
max_pooling2d_2 (MaxPooling2 (None, 36, 112, 32)       0         
_________________________________________________________________
conv2d_3 (Conv2D)            (None, 32, 108, 64)       51264     
_________________________________________________________________
max_pooling2d_3 (MaxPooling2 (None, 16, 54, 64)        0         
_________________________________________________________________
flatten_1 (Flatten)          (None, 55296)             0         
_________________________________________________________________
dense_1 (Dense)              (None, 72534)             -284054698
=================================================================
Total params: -283,984,986
Trainable params: -283,984,986
Non-trainable params: 0
_________________________________________________________________
None

Answer 1

是的，當然，您的Dense圖層的權重矩陣大小為55296 x 72534 ，其中包含4010840064數字，即401,000萬個參數。

在Keras代碼中的某個地方，參數數量存儲為int32，這意味着它可以存儲的數量是有限制的，即2^32 - 1 = 2147483647 ，現在您可以看到，您的401,000萬個參數更大大於2^32 - 1 ，因此數字溢出到整數的負數側。

我建議您不要建立具有如此大量參數的模型，否則，如果沒有大量的RAM，您將無法進行訓練。

Answer 2

問題是因為您正在CPU中運行代碼，因此keras tensorflow或theano的后端可以正常工作。 我能夠在Google colab中使用GPU完美地運行您的代碼，這就是我得到的

_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
conv2d_1 (Conv2D)            (None, 153, 458, 16)      5616      
_________________________________________________________________
max_pooling2d_1 (MaxPooling2 (None, 76, 229, 16)       0         
_________________________________________________________________
conv2d_2 (Conv2D)            (None, 72, 225, 32)       12832     
_________________________________________________________________
max_pooling2d_2 (MaxPooling2 (None, 36, 112, 32)       0         
_________________________________________________________________
conv2d_3 (Conv2D)            (None, 32, 108, 64)       51264     
_________________________________________________________________
max_pooling2d_3 (MaxPooling2 (None, 16, 54, 64)        0         
_________________________________________________________________
flatten_1 (Flatten)          (None, 55296)             0         
_________________________________________________________________
dense_1 (Dense)              (None, 72534)             4010912598
=================================================================
Total params: 4,010,982,310
Trainable params: 4,010,982,310
Non-trainable params: 0

我建議您使用GPU來訓練如此龐大的網絡。

希望這可以幫助！