卷积神经网络的内存大小是多少？

Question

我在看http://cs231n.github.io/convolutional-networks/

我不明白为什么第2层（CONV3-64：[224x224x64]）的内存大小为224x224x 64

1. 我知道有64个大小为3x3的过滤器，但为什么输入大小乘以64？
2. 为什么图层中的权重数（CONV3-128）是（3x3x64）x128而不是 （3x3x64x64）x128？ （前一层的权重乘以新的128个过滤器）

由于

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

Answer 1

您的第一个问题是指正向传递存储的内存。

1. 属于CONV3-64图层的224x224x64中的64，因为当您通过单个224x224x3图像时，它会通过64个3x3x3滤镜，因此必须将64个新图像存储在内存中以传播这些效果64通过正向传递进入网络。

您的第二个是指网络中的权重参数。

1. 在CONV3-128层中，输入为112x112x64，这意味着如果要应用单个3x3过滤器，实际上是对64个输入通道中的每一个应用不同的过滤器。您可以将输入视为由64个不同的3x3滤镜过滤的112x112x64音量，这可以被认为是3x3x64体积滤波器，它将输出单个112x112图像。此层的输出设置为128个通道，因此您必须执行此操作128次，因此此层中的128 * 64 * 3 * 3权重。