CNN负数参数

Question

我正在尝试使用keras构建CNN模型。 当我添加两个Conv3D和MaxPooling块时，一切正常。 但是，一旦添加了第三个块（如代码中所示），则可训练参数的数量将变为负值。 知道如何发生吗？

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())

该代码的结果如下：

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，当然，您的Dense图层的权重矩阵大小为55296 x 72534 ，其中包含4010840064数字，即401,000万个参数。

在Keras代码中的某个地方，参数数量存储为int32，这意味着它可以存储的数量是有限制的，即2^32 - 1 = 2147483647 ，现在您可以看到，您的401,000万个参数更大大于2^32 - 1 ，因此数字溢出到整数的负数侧。

我建议您不要建立具有如此大量参数的模型，否则，如果没有大量的RAM，您将无法进行训练。

Answer 2

问题是因为您正在CPU中运行代码，因此keras tensorflow或theano的后端可以正常工作。 我能够在Google colab中使用GPU完美地运行您的代码，这就是我得到的

_________________________________________________________________
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

我建议您使用GPU来训练如此庞大的网络。

希望这可以帮助！