Keras 使用过多内存

debugcn 发表于 Dev

圣甲虫

我有一个 keras（带有 tensorflow 后端）模型，其定义如下：

INPUT_SHAPE = [4740, 3540, 1]

model = Sequential()
model.add(Conv2D(32, kernel_size=(3, 3),
                 activation='relu',
                 input_shape=INPUT_SHAPE))
model.add(Conv2D(2, (4, 4), strides=(1, 1), activation='relu'))
model.add(MaxPooling2D(pool_size=(4, 4)))
model.add(Conv2D(4, (4, 4), strides=(1, 1), activation='relu'))
model.add(MaxPooling2D(pool_size=(4, 4)))
model.add(Conv2D(8, (4, 4), strides=(1, 1), activation='relu'))
model.add(MaxPooling2D(pool_size=(4, 4)))
model.add(Conv2D(16, (4, 4), strides=(1, 1), activation='relu'))
model.add(MaxPooling2D(pool_size=(4, 4)))
model.add(Conv2D(32, (4, 4), strides=(1, 1), activation='relu'))
model.add(MaxPooling2D(pool_size=(4, 4)))
model.add(Dropout(0.25))
model.add(Flatten())
model.add(Dense(128, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(num_classes, activation='softmax'))

model.compile(loss=keras.losses.categorical_crossentropy,
              optimizer=keras.optimizers.Adadelta(),
              metrics=['accuracy'])

该模型只有 37,506 个可训练参数。然而，如果批量大小大于 1，它会以某种方式耗尽 K80 在 model.fit() 上的 12GB vram 资源。为什么这个模型需要这么多内存？以及如何正确计算内存需求？如何确定 Keras 模型所需的内存中的函数？批处理中每 1 个元素给我 2.15 GB。所以至少我应该能够制作一批 5。

编辑：model.summary()

Layer (type)                 Output Shape              Param #   
=================================================================
conv2d_1 (Conv2D)            (None, 4738, 3538, 32)    320       
_________________________________________________________________
conv2d_2 (Conv2D)            (None, 4735, 3535, 2)     1026      
_________________________________________________________________
max_pooling2d_1 (MaxPooling2 (None, 1183, 883, 2)      0         
_________________________________________________________________
conv2d_3 (Conv2D)            (None, 1180, 880, 4)      132       
_________________________________________________________________
max_pooling2d_2 (MaxPooling2 (None, 295, 220, 4)       0         
_________________________________________________________________
conv2d_4 (Conv2D)            (None, 292, 217, 8)       520       
_________________________________________________________________
max_pooling2d_3 (MaxPooling2 (None, 73, 54, 8)         0         
_________________________________________________________________
conv2d_5 (Conv2D)            (None, 70, 51, 16)        2064      
_________________________________________________________________
max_pooling2d_4 (MaxPooling2 (None, 17, 12, 16)        0         
_________________________________________________________________
conv2d_6 (Conv2D)            (None, 14, 9, 32)         8224      
_________________________________________________________________
max_pooling2d_5 (MaxPooling2 (None, 3, 2, 32)          0         
_________________________________________________________________
dropout_1 (Dropout)          (None, 3, 2, 32)          0         
_________________________________________________________________
flatten_1 (Flatten)          (None, 192)               0         
_________________________________________________________________
dense_1 (Dense)              (None, 128)               24704     
_________________________________________________________________
dropout_2 (Dropout)          (None, 128)               0         
_________________________________________________________________
dense_2 (Dense)              (None, 4)                 516       
=================================================================
Total params: 37,506
Trainable params: 37,506
Non-trainable params: 0
_________________________________________________________________

阿列克谢·乌姆诺夫

第一层的输出形状为 B*4738*3538*32（B 是批量大小），大约需要 1GB * B 内存。梯度和其他激活也可能会占用一些内存。也许增加第一层的步幅会有所帮助。

本文收集自互联网，转载请注明来源。

如有侵权，请联系[email protected] 删除。