n

import numpy as np

from cs231n.layers import *
from cs231n.fast_layers import *
from cs231n.layer_utils import * class ThreeLayerConvNet(object):
"""
A three-layer convolutional network with the following architecture: conv - relu - 2x2 max pool - affine - relu - affine - softmax The network operates on minibatches of data that have shape (N, C, H, W)
consisting of N images, each with height H and width W and with C input
channels.
""" def __init__(self, input_dim=(3, 32, 32), num_filters=32, filter_size=7,
hidden_dim=100, num_classes=10, weight_scale=1e-3, reg=0.0,
dtype=np.float32):
"""
Initialize a new network. Inputs:
- input_dim: Tuple (C, H, W) giving size of input data
- num_filters: Number of filters to use in the convolutional layer
- filter_size: Size of filters to use in the convolutional layer
- hidden_dim: Number of units to use in the fully-connected hidden layer
- num_classes: Number of scores to produce from the final affine layer.
- weight_scale: Scalar giving standard deviation for random initialization
of weights.
- reg: Scalar giving L2 regularization strength
- dtype: numpy datatype to use for computation.
"""
C,H,W=input_dim self.params = {}
self.reg = reg
self.dtype = dtype
self.params['W1']=np.random.randn(num_filters,C,filter_size,filter_size)*weight_scale
self.params['b1']=np.zeros(num_filters,)
self.params['W2']=np.random.randn(num_filters*H*W/4,hidden_dim)*weight_scale
self.params['b2']=np.zeros(hidden_dim,)
self.params['W3']=np.random.randn(hidden_dim,num_classes)*weight_scale
self.params['b3']=np.zeros(num_classes,)
# why randn needs int while seros needs tuple!!!!
for k, v in self.params.iteritems():
self.params[k] = v.astype(dtype) def loss(self, X, y=None):
"""
Evaluate loss and gradient for the three-layer convolutional network. Input / output: Same API as TwoLayerNet in fc_net.py.
"""
W1, b1 = self.params['W1'], self.params['b1']
W2, b2 = self.params['W2'], self.params['b2']
W3, b3 = self.params['W3'], self.params['b3'] # pass conv_param to the forward pass for the convolutional layer
filter_size = W1.shape[2]
conv_param = {'stride': 1, 'pad': (filter_size - 1) / 2} # pass pool_param to the forward pass for the max-pooling layer
pool_param = {'pool_height': 2, 'pool_width': 2, 'stride': 2} scores = None
out1,cache1=conv_relu_pool_forward(X,W1,b1,conv_param,pool_param) out=out1.reshape(out1.shape[0],-1) out,cache2=affine_relu_forward(out,W2,b2) scores,cache3=affine_forward(out,W3,b3) if y is None:
return scores loss, grads = 0, {}
loss,dout=softmax_loss(scores,y) loss+=self.reg*0.5*np.sum(W3**2)
loss+=self.reg*0.5*np.sum(W2**2)
loss+=self.reg*0.5*np.sum(W1**2) dout,grads['W3'],grads['b3']=affine_backward(dout,cache3)
grads['W3']+=W3*self.reg dout,grads['W2'],grads['b2']=affine_relu_backward(dout,cache2)
grads['W2']+=W2*self.reg dout=dout.reshape(*out1.shape)
dout,grads['W1'],grads['b1']=conv_relu_pool_backward(dout,cache1)
grads['W1']+=W1*self.reg ############################################################################
# END OF YOUR CODE #
############################################################################ return loss, grads pass

  

n

cnn.py cs231n的更多相关文章

  1. fc_net.py cs231n

    n如果有错误,欢迎指出,不胜感激 import numpy as np from cs231n.layers import * from cs231n.layer_utils import * cla ...

  2. layers.py cs231n

    如果有错误,欢迎指出,不胜感激. import numpy as np def affine_forward(x, w, b): 第一个最简单的 affine_forward简单的前向传递,返回 ou ...

  3. optim.py cs231n

    n如果有错误,欢迎指出,不胜感激 import numpy as np """ This file implements various first-order upda ...

  4. [Keras] mnist with cnn

    典型的卷积神经网络. Keras傻瓜式读取数据:自动下载,自动解压,自动加载. # X_train: array([[[[ 0., 0., 0., ..., 0., 0., 0.], [ 0., 0. ...

  5. 卷积神经网络CNN(Convolutional Neural Networks)没有原理只有实现

    零.说明: 本文的所有代码均可在 DML 找到,欢迎点星星. 注.CNN的这份代码非常慢,基本上没有实际使用的可能,所以我只是发出来,代表我还是实践过而已 一.引入: CNN这个模型实在是有些年份了, ...

  6. 深度学习之卷积神经网络(CNN)详解与代码实现(一)

    卷积神经网络(CNN)详解与代码实现 本文系作者原创,转载请注明出处:https://www.cnblogs.com/further-further-further/p/10430073.html 目 ...

  7. python,tensorflow,CNN实现mnist数据集的训练与验证正确率

    1.工程目录 2.导入data和input_data.py 链接:https://pan.baidu.com/s/1EBNyNurBXWeJVyhNeVnmnA 提取码:4nnl 3.CNN.py i ...

  8. 基于MNIST数据的卷积神经网络CNN

    基于tensorflow使用CNN识别MNIST 参数数量:第一个卷积层5x5x1x32=800个参数,第二个卷积层5x5x32x64=51200个参数,第三个全连接层7x7x64x1024=3211 ...

  9. 【转载】 深度学习之卷积神经网络(CNN)详解与代码实现(一)

    原文地址: https://www.cnblogs.com/further-further-further/p/10430073.html ------------------------------ ...

随机推荐

  1. Lua程序设计之数值

    (摘自Lua程序设计) 数值常量 从Lua5.3版本开始Lua语言为数值格式提供了两种选择:被称为integer的64位整形和被称为float的双精度浮点类型(注意,"float" ...

  2. Odoo 新 API 概述

    __all__ = [ 'Environment', 'Meta', 'guess', 'noguess', 'model', 'multi', 'one', 'cr', 'cr_context', ...

  3. 19-10-15-W

    暴力终于不跪了$\text{QvQ}$ z总j结 考试开始看到几个大字:Day1 Happy-(××终于不用爆〇了哈哈哈哈!!) 开T1.一看,不是在线仙人球嵌套动态网络路径剖分优化的分支定界贪心剪枝 ...

  4. light oj 1219 树上贪心

    #include <iostream> #include <cstdlib> #include <cstring> #include <queue> # ...

  5. pyd打包补充

    网上说的将python代码,通过Cython打包成pyd的教程挺多,好处也多,主要有两个: 1.隐藏代码 2.加速运行速度 补充两点: 1.打包脚本配置 __build__.py from distu ...

  6. mysql 对数据库操作的常用sql语句

    1.查看创建某个数据库的 创建语句 show create database mysql 这个sql语句的意思是 展示创建名为mysql的数据库的 语句.执行之后如下图所示 仿造上面这个创建语句 创建 ...

  7. Nginx与PHP工作原理

    Nginx的工作原理 1.Nginx的模块与工作原理 Nginx由内核和模块组成,其中,内核的设计非常微小和简洁,完成的工作也非常简单,仅仅通过查找配置文件将客户端请求映射到一个location bl ...

  8. UVa-401 Palindromes回文词

    虽然是水题,但是容易错.参照了紫书的代码可以写的很简洁.主要还是注意常量数组的使用,能让代码变得简单许多 #include <iostream> #include <cstdio&g ...

  9. 威胁快报|首爆新型ibus蠕虫,利用热门漏洞疯狂挖矿牟利

    一.背景 近日阿里云安全团队发现了一起利用多个流行漏洞传播的蠕虫事件.黑客首先利用ThinkPHP远程命令执行等多个热门漏洞控制大量主机,并将其中一台“肉鸡”作为蠕虫脚本的下载源.其余受控主机下载并运 ...

  10. TZ_06_SpringMVC的入门程序

    SpringMVC的入门程序 1. 创建WEB工程,引入开发的jar包 1. 具体的坐标如下 2. 配置核心的控制器(配置DispatcherServlet) 1. 在web.xml配置文件中核心控制 ...