关于VGG-16模型的内存和参数的计算过程如下。

INPUT: [224x224x3] memory: 224*224*3=150K weights: 0

CONV3-64: [224x224x64] memory: 224*224*64=3.2M weights: (3*3*3)*64 = 1,728

CONV3-64: [224x224x64] memory: 224*224*64=3.2M weights: (3*3*64)*64 = 36,864

POOL2: [112x112x64] memory: 112*112*64=800K weights: 0

CONV3-128: [112x112x128] memory: 112*112*128=1.6M weights: (3*3*64)*128 = 73,728

CONV3-128: [112x112x128] memory: 112*112*128=1.6M weights: (3*3*128)*128 = 147,456

POOL2: [56x56x128] memory: 56*56*128=400K weights: 0

CONV3-256: [56x56x256] memory: 56*56*256=800K weights: (3*3*128)*256 = 294,912

CONV3-256: [56x56x256] memory: 56*56*256=800K weights: (3*3*256)*256 = 589,824

CONV3-256: [56x56x256] memory: 56*56*256=800K weights: (3*3*256)*256 = 589,824

POOL2: [28x28x256] memory: 28*28*256=200K weights: 0

CONV3-512: [28x28x512] memory: 28*28*512=400K weights: (3*3*256)*512 = 1,179,648

CONV3-512: [28x28x512] memory: 28*28*512=400K weights: (3*3*512)*512 = 2,359,296

CONV3-512: [28x28x512] memory: 28*28*512=400K weights: (3*3*512)*512 = 2,359,296

POOL2: [14x14x512] memory: 14*14*512=100K weights: 0

CONV3-512: [14x14x512] memory: 14*14*512=100K weights: (3*3*512)*512 = 2,359,296

CONV3-512: [14x14x512] memory: 14*14*512=100K weights: (3*3*512)*512 = 2,359,296

CONV3-512: [14x14x512] memory: 14*14*512=100K weights: (3*3*512)*512 = 2,359,296

POOL2: [7x7x512] memory: 7*7*512=25K weights: 0

FC: [1x1x4096] memory: 4096 weights: 7*7*512*4096 = 102,760,448

FC: [1x1x4096] memory: 4096 weights: 4096*4096 = 16,777,216

FC: [1x1x1000] memory: 1000 weights: 4096*1000 = 4,096,000

TOTAL memory: 24M * 4 bytes ~= 93MB / image (only forward! ~*2 for bwd)

TOTAL params: 138M parameters

如果动手算一下memory的和，如下。

0.15M+3.2M+3.2M+0.8M+1.6M+1.6M+0.4M+0.8M3+0.2M+0.4M3+0.1M*4+0.025M+0.004M+0.004M+0.001M = 15.184M

问题来了，计算得到的总内存为15.184*4 bytes ~=60MB / image，而教程中给的为93MB。并且教程中的数据(24M)被许多博客和文章所引用，导致经常看到的就是24M这个数据。起始该答案早在github上有针对教程中的疑问，并给出了如上手动计算的结果。所以，15M的memory才是正确的答案。    另外上述针对参数(weight)的计算中并没有加入bias的数量。

延伸1：模型的组成

参数的数量约为138M(不包含bias)，此时占用的内存大小为：138M*4 bytes ~=526M，该大小约等于保存后模型占用磁盘的大小，而实际利用ImageNet训练出来的VGG-16的模型大小超过552M。那么差的20多M内存哪去了，此处不局限于该模型的探讨，而是想更一般化的探讨模型中的成分。

由上可知，模型中主要是权重和偏移单元，如vgg-16加上偏移向量后的参数计算结果如下。然后是优化器和其他特殊层中的参数，如LeakyReLU，BN，和Dropout等的参数，如keras中的model。

conv3-64 x 2 : 38,720

conv3-128 x 2 : 221,440

conv3-256 x 3 : 1,475,328

conv3-512 x 3 : 5,899,776

conv3-512 x 3 : 7,079,424

fc1 : 102,764,544

fc2 : 16,781,312

fc3 : 4,097,000

TOTAL : 138,357,544

其中全连接的计算为：

fc1 (x): (512x7x7)x4,096 (weights) + 4,096 (biases)

fc2 : 4,096x4,096 (weights) + 4,096 (biases)

fc3 : 4,096x1,000 (weights) + 1,000 (biases)

延伸2：训练和测试时的内存组理解全连接层采用1×1的卷积核全卷积神经网络(FCN)深度学习中的批标准化(batch normalization)