迁移学习——使用Tensorflow和VGG16预训模型进行预测

使用Tensorflow和VGG16预训模型进行预测

from：https://zhuanlan.zhihu.com/p/28997549

fast.ai的入门教程中使用了kaggle: dogs vs cats作为例子来让大家入门Computer Vision。不过并未应用到最近很火的Tensorflow。Keras虽然可以调用Tensorflow作为backend，不过既然可以少走一层直接走Tensorflow，那秉着学习的想法，就直接用Tensorflow来一下把。

听说工程上普遍的做法并不是从头开始训练模型，而是直接用已经训练完的模型稍加改动（这个过程叫finetune）来达到目的。那么这里就需要用Tensorflow还原出VGG16的模型。这里借鉴了frossard的python代码和他转化的权重。架构具体如下：（cs231n有更详细的介绍）

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

具体实现移步VGG16。这里要注意的一点就是最后的输出是不需要经过Relu的。

预测猫和狗不能照搬这个架构，因为VGG16是用来预测ImageNet上1000个不同种类的。用来预测猫和狗两种类别，需要在这个架构的基础上再加一层FC把1000转化成2个。（也可以把最后一层替换掉，直接输出成2个）。我还在VGG16之后多加了一层BN，原来VGG16的时候并不存在BN。我也并没有在每个CONV后面加，因为不想算...