计算感受野

发表于 更新于 分类于
  • feature map的计算公式为outsize = (insize - fsize + 2*pad) / stride + 1
  • stride 的计算公式为totstride = totstride * stride，这两个公式都是从前往后算
  • receptive field RF = ((RF -1)* stride) + fsize，这个要从后往前算
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
#!/usr/bin/env python

net_struct = {'alexnet': {'net':[[11,4,0],[3,2,0],[5,1,2],[3,2,0],[3,1,1],[3,1,1],[3,1,1],[3,2,0]],
                   'name':['conv1','pool1','conv2','pool2','conv3','conv4','conv5','pool5']},
       'vgg16': {'net':[[3,1,1],[3,1,1],[2,2,0],[3,1,1],[3,1,1],[2,2,0],[3,1,1],[3,1,1],[3,1,1],
                        [2,2,0],[3,1,1],[3,1,1],[3,1,1],[2,2,0],[3,1,1],[3,1,1],[3,1,1],[2,2,0]],
                 'name':['conv1_1','conv1_2','pool1','conv2_1','conv2_2','pool2','conv3_1','conv3_2',
                         'conv3_3', 'pool3','conv4_1','conv4_2','conv4_3','pool4','conv5_1','conv5_2','conv5_3','pool5']},
       'zf-5':{'net': [[7,2,3],[3,2,1],[5,2,2],[3,2,1],[3,1,1],[3,1,1],[3,1,1]],
               'name': ['conv1','pool1','conv2','pool2','conv3','conv4','conv5']}}

#[3,1,1] stands for filter_size, stride, padding

imsize = 224

def outFromIn(isz, net, layernum):
    totstride = 1
    insize = isz
    for layer in range(layernum):
        fsize, stride, pad = net[layer]
        outsize = (insize - fsize + 2*pad) / stride + 1
        insize = outsize
        totstride = totstride * stride
    return outsize, totstride

def inFromOut(net, layernum):
    RF = 1
    for layer in reversed(range(layernum)):
        fsize, stride, pad = net[layer]
        RF = ((RF -1)* stride) + fsize
    return RF

if __name__ == '__main__':
    print "layer output sizes given image = %dx%d" % (imsize, imsize)
    for net in net_struct.keys():
        print '************net structrue name is %s**************'% net
        for i in range(len(net_struct[net]['net'])):
            p = outFromIn(imsize,net_struct[net]['net'], i+1)
            rf = inFromOut(net_struct[net]['net'], i+1)
            print "Layer Name = %s, Output size = %3d, Stride = % 3d, RF size = %3d" % (net_struct[net]['name'][i], p[0], p[1], rf)

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
layer output sizes given image = 224x224
************net structrue name is vgg16**************
Layer Name = conv1_1, Output size = 224, Stride =   1, RF size =   3
Layer Name = conv1_2, Output size = 224, Stride =   1, RF size =   5
Layer Name = pool1, Output size = 112, Stride =   2, RF size =   6
Layer Name = conv2_1, Output size = 112, Stride =   2, RF size =  10
Layer Name = conv2_2, Output size = 112, Stride =   2, RF size =  14
Layer Name = pool2, Output size =  56, Stride =   4, RF size =  16
Layer Name = conv3_1, Output size =  56, Stride =   4, RF size =  24
Layer Name = conv3_2, Output size =  56, Stride =   4, RF size =  32
Layer Name = conv3_3, Output size =  56, Stride =   4, RF size =  40
Layer Name = pool3, Output size =  28, Stride =   8, RF size =  44
Layer Name = conv4_1, Output size =  28, Stride =   8, RF size =  60
Layer Name = conv4_2, Output size =  28, Stride =   8, RF size =  76
Layer Name = conv4_3, Output size =  28, Stride =   8, RF size =  92
Layer Name = pool4, Output size =  14, Stride =  16, RF size = 100
Layer Name = conv5_1, Output size =  14, Stride =  16, RF size = 132
Layer Name = conv5_2, Output size =  14, Stride =  16, RF size = 164
Layer Name = conv5_3, Output size =  14, Stride =  16, RF size = 196
Layer Name = pool5, Output size =   7, Stride =  32, RF size = 212
************net structrue name is zf-5**************
Layer Name = conv1, Output size = 112, Stride =   2, RF size =   7
Layer Name = pool1, Output size =  56, Stride =   4, RF size =  11
Layer Name = conv2, Output size =  28, Stride =   8, RF size =  27
Layer Name = pool2, Output size =  14, Stride =  16, RF size =  43
Layer Name = conv3, Output size =  14, Stride =  16, RF size =  75
Layer Name = conv4, Output size =  14, Stride =  16, RF size = 107
Layer Name = conv5, Output size =  14, Stride =  16, RF size = 139
************net structrue name is alexnet**************
Layer Name = conv1, Output size =  54, Stride =   4, RF size =  11
Layer Name = pool1, Output size =  26, Stride =   8, RF size =  19
Layer Name = conv2, Output size =  26, Stride =   8, RF size =  51
Layer Name = pool2, Output size =  12, Stride =  16, RF size =  67
Layer Name = conv3, Output size =  12, Stride =  16, RF size =  99
Layer Name = conv4, Output size =  12, Stride =  16, RF size = 131
Layer Name = conv5, Output size =  12, Stride =  16, RF size = 163
Layer Name = pool5, Output size =   5, Stride =  32, RF size = 195