深度学习实践指南（一）—— 卷积和池化

最新推荐文章于 2024-08-27 10:33:50 发布

五道口纳什

最新推荐文章于 2024-08-27 10:33:50 发布

阅读量1.3k

点赞数

分类专栏：深度学习

本文链接：https://blog.csdn.net/lanchunhui/article/details/51259007

版权

深度学习专栏收录该内容

61 篇文章 10 订阅

订阅专栏

详细信息请见 Convolutional Neural Networks (LeNet)

卷积：
```
from theano.tensor.nnet import conv2d
```

池化

from theano.tensor.signal.downsample import max_pool_2d

卷积

import numpy as np
import theano
import theano.tensor as T
from theano.tensor.nnet import conv2d

inpt = T.tensor4('inpt')

# 2: # feature maps
# 3: # color dim
# 9*9: # kernel size
W = theano.shared(np.asarray(np.random.randn(2, 3, 9, 9), dtype='float64'), name='W', borrow=True)
conv_out = conv2d(inpt, W)
f = theano.function([inpt], conv_out)

池化

import theano
import theano.tensor as T
from theano.tensor.signal import downsample

inpt = T.tensor4('inpt')
ds = (2, 2)
pool_out = downsample.max_pool_2d(inpt, ds, ignore_border=True)
f = theano.function([inpt], pool_out)

关于 max_pool_2d 的 ignore_border 参数：