技术标签： cs231n
fc_net.py
from builtins import range
from builtins import object
import numpy as np
from cs231n.layers import *
from cs231n.layer_utils import *
class TwoLayerNet(object):
"""
A two-layer fully-connected neural network with ReLU nonlinearity and
softmax loss that uses a modular layer design. We assume an input dimension
of D, a hidden dimension of H, and perform classification over C classes.
The architecure should be affine - relu - affine - softmax.
Note that this class does not implement gradient descent; instead, it
will interact with a separate Solver object that is responsible for running
optimization.
The learnable parameters of the model are stored in the dictionary
self.params that maps parameter names to numpy arrays.
"""
def __init__(self, input_dim=3*32*32, hidden_dim=100, num_classes=10,
weight_scale=1e-3, reg=0.0):
"""
Initialize a new network.
Inputs:
- input_dim: An integer giving the size of the input
- hidden_dim: An integer giving the size of the hidden layer
- num_classes: An integer giving the number of classes to classify
- weight_scale: Scalar giving the standard deviation for random
initialization of the weights.
- reg: Scalar giving L2 regularization strength.
"""
self.params = {
}
self.reg = reg
############################################################################
# TODO: Initialize the weights and biases of the two-layer net. Weights #
# should be initialized from a Gaussian centered at 0.0 with #
# standard deviation equal to weight_scale, and biases should be #
# initialized to zero. All weights and biases should be stored in the #
# dictionary self.params, with first layer weights #
# and biases using the keys 'W1' and 'b1' and second layer #
# weights and biases using the keys 'W2' and 'b2'. #
############################################################################
#w高斯分布，b初始化0
mu = 0
sigma = weight_scale
self.params['W1'] = mu + sigma * np.random.randn(input_dim,hidden_dim)
self.params['b1'] = np.zeros(hidden_dim)
self.params['W2'] = mu + sigma * np.random.randn(hidden_dim,num_classes)
self.params['b2'] = np.zeros(num_classes)
pass
############################################################################
# END OF YOUR CODE #
############################################################################
def loss(self, X, y=None):
"""
Compute loss and gradient for a minibatch of data.
Inputs:
- X: Array of input data of shape (N, d_1, ..., d_k)
- y: Array of labels, of shape (N,). y[i] gives the label for X[i].
Returns:
If y is None, then run a test-time forward pass of the model and return:
- scores: Array of shape (N, C) giving classification scores, where
scores[i, c] is the classification score for X[i] and class c.
If y is not None, then run a training-time forward and backward pass and
return a tuple of:
- loss: Scalar value giving the loss
- grads: Dictionary with the same keys as self.params, mapping parameter
names to gradients of the loss with respect to those parameters.
"""
scores = None
############################################################################
# TODO: Implement the forward pass for the two-layer net, computing the #
# class scores for X and storing them in the scores variable. #
############################################################################
N = X.shape[0]
D = np.prod(X.shape[1:])
x_in = X
x_in = x_in.reshape(N, D)
fc1 = x_in.dot(self.params['W1']) + self.params['b1']
relu = np.maximum(0, fc1)
fc2 = relu.dot(self.params['W2']) + self.params['b2']
scores = fc2
pass
############################################################################
# END OF YOUR CODE #
############################################################################
# If y is None then we are in test mode so just return scores
if y is None:
return scores
loss, grads = 0, {
}
############################################################################
# TODO: Implement the backward pass for the two-layer net. Store the loss #
# in the loss variable and gradients in the grads dictionary. Compute data #
# loss using softmax, and make sure that grads[k] holds the gradients for #
# self.params[k]. Don't forget to add L2 regularization! #
# #
# NOTE: To ensure that your implementation matches ours and you pass the #
# automated tests, make sure that your L2 regularization includes a factor #
# of 0.5 to simplify the expression for the gradient. #
############################################################################
W1, b1 = self.params['W1'], self.params['b1']
W2, b2 = self.params['W2'], self.params['b2']
loss, dout2 = softmax_loss(scores, y)
loss += 0.5 * self.reg * (np.sum(W1*W1)+np.sum(W2*W2))
cache2 = relu, W2, b2
dx2,dw2,db2 = affine_backward(dout2, cache2)
grads['W2'] = dw2 + self.reg * self.params['W2'] #注意不要忘记 loss 中W1, W2 的贡献 和正则化参数
grads['b2'] = db2
cache1 = fc1
dout1 = dx2
dout = relu_backward(dout1, cache1)
cache = X, W1, b1
dx1,dw1,db1 = affine_backward(dout, cache)
grads['W1'] = dw1 + self.reg * self.params['W1']
grads['b1'] = db1
pass
############################################################################
# END OF YOUR CODE #
############################################################################
return loss, grads
class FullyConnectedNet(object):
"""
A fully-connected neural network with an arbitrary number of hidden layers,
ReLU nonlinearities, and a softmax loss function. This will also implement
dropout and batch/layer normalization as options. For a network with L layers,
the architecture will be
{affine - [batch/layer norm] - relu - [dropout]} x (L - 1) - affine - softmax
where batch/layer normalization and dropout are optional, and the {...} block is
repeated L - 1 times.
Similar to the TwoLayerNet above, learnable parameters are stored in the
self.params dictionary and will be learned using the Solver class.
"""
def __init__(self, hidden_dims, input_dim=3*32*32, num_classes=10,
dropout=1, normalization=None, reg=0.0,
weight_scale=1e-2, dtype=np.float32, seed=None):
"""
Initialize a new FullyConnectedNet.
Inputs:
- hidden_dims: A list of integers giving the size of each hidden layer.
- input_dim: An integer giving the size of the input.
- num_classes: An integer giving the number of classes to classify.
- dropout: Scalar between 0 and 1 giving dropout strength. If dropout=1 then
the network should not use dropout at all.
- normalization: What type of normalization the network should use. Valid values
are "batchnorm", "layernorm", or None for no normalization (the default).
- reg: Scalar giving L2 regularization strength.
- weight_scale: Scalar giving the standard deviation for random
initialization of the weights.
- dtype: A numpy datatype object; all computations will be performed using
this datatype. float32 is faster but less accurate, so you should use
float64 for numeric gradient checking.
- seed: If not None, then pass this random seed to the dropout layers. This
will make the dropout layers deteriminstic so we can gradient check the
model.
"""
self.normalization = normalization
self.use_dropout = dropout != 1
self.reg = reg
self.num_layers = 1 + len(hidden_dims)
self.dtype = dtype
self.params = {
}
############################################################################
# TODO: Initialize the parameters of the network, storing all values in #
# the self.params dictionary. Store weights and biases for the first layer #
# in W1 and b1; for the second layer use W2 and b2, etc. Weights should be #
# initialized from a normal distribution centered at 0 with standard #
# deviation equal to weight_scale. Biases should be initialized to zero. #
# #
# When using batch normalization, store scale and shift parameters for the #
# first layer in gamma1 and beta1; for the second layer use gamma2 and #
# beta2, etc. Scale parameters should be initialized to ones and shift #
# parameters should be initialized to zeros. #
############################################################################
parameters = [input_dim] + hidden_dims + [num_classes]
lx = len(parameters)
for i in range(1,lx):
idw = 'W' + str(i)
idb = 'b' + str(i)
self.params[idw] = np.random.randn(parameters[i-1], parameters[i]) * weight_scale
self.params[idb] = np.zeros(parameters[i])
if self.normalization=='batchnorm':
for i in range(1,lx-1):
idga = 'gamma' + str(i)
idbe = 'beta' + str(i)
self.params[idga] = np.ones(parameters[i])
self.params[idbe] = np.zeros(parameters[i])
############################################################################
# END OF YOUR CODE #
############################################################################
# When using dropout we need to pass a dropout_param dictionary to each
# dropout layer so that the layer knows the dropout probability and the mode
# (train / test). You can pass the same dropout_param to each dropout layer.
self.dropout_param = {
}
if self.use_dropout:
self.dropout_param = {
'mode': 'train', 'p': dropout}
if seed is not None:
self.dropout_param['seed'] = seed
# With batch normalization we need to keep track of running means and
# variances, so we need to pass a special bn_param object to each batch
# normalization layer. You should pass self.bn_params[0] to the forward pass
# of the first batch normalization layer, self.bn_params[1] to the forward
# pass of the second batch normalization layer, etc.
self.bn_params = []
if self.normalization=='batchnorm':
self.bn_params = [{
'mode': 'train'} for i in range(self.num_layers - 1)]
if self.normalization=='layernorm':
self.bn_params = [{
} for i in range(self.num_layers - 1)]
# Cast all parameters to the correct datatype
for k, v in self.params.items():
self.params[k] = v.astype(dtype)
def loss(self, X, y=None):
"""
Compute loss and gradient for the fully-connected net.
Input / output: Same as TwoLayerNet above.
"""
X = X.astype(self.dtype)
mode = 'test' if y is None else 'train'
# Set train/test mode for batchnorm params and dropout param since they
# behave differently during training and testing.
if self.use_dropout:
self.dropout_param['mode'] = mode
if self.normalization=='batchnorm':
for bn_param in self.bn_params:
bn_param['mode'] = mode
scores = None
############################################################################
# TODO: Implement the forward pass for the fully-connected net, computing #
# the class scores for X and storing them in the scores variable. #
# #
# When using dropout, you'll need to pass self.dropout_param to each #
# dropout forward pass. #
# #
# When using batch normalization, you'll need to pass self.bn_params[0] to #
# the forward pass for the first batch normalization layer, pass #
# self.bn_params[1] to the forward pass for the second batch normalization #
# layer, etc. #
############################################################################
N, D = X.shape[0], np.prod(X.shape[1:])
scores = X.reshape(N,D)
list_x_in = {
}
list_x_in['x' + str(0)] = scores
for i in range(1,self.num_layers):
xa, wa, ba = scores, self.params['W' + str(i)], self.params['b' + str(i)]
if self.normalization == 'batchnorm' and self.use_dropout:
gamma, beta = self.params['gamma' + str(i)], self.params['beta' + str(i)]
scores, cache = affine_bn_relu_drop_forward(xa, wa, ba, gamma, beta, self.bn_params[i - 1],self.dropout_param)
elif self.normalization == 'batchnorm':
gamma, beta = self.params['gamma' + str(i)], self.params['beta' + str(i)]
scores, cache = affine_bn_relu_forward(xa, wa, ba, gamma, beta, self.bn_params[i-1])
elif self.use_dropout:
scores, cache = affine_relu_drop_forward(xa, wa, ba, self.dropout_param)
else:
scores, cache = affine_relu_forward(xa, wa, ba)
list_x_in['x'+str(i)] = cache
#注：最后一层没用relu
xa, wa, ba = scores, self.params['W' + str(self.num_layers)], self.params['b' + str(self.num_layers)]
scores, cache = affine_forward(xa, wa, ba)
list_x_in['x' + str(self.num_layers)] = cache
############################################################################
# END OF YOUR CODE #
############################################################################
# If test mode return early
if mode == 'test':
return scores
loss, grads = 0.0, {
}
############################################################################
# TODO: Implement the backward pass for the fully-connected net. Store the #
# loss in the loss variable and gradients in the grads dictionary. Compute #
# data loss using softmax, and make sure that grads[k] holds the gradients #
# for self.params[k]. Don't forget to add L2 regularization! #
# #
# When using batch/layer normalization, you don't need to regularize the scale #
# and shift parameters. #
# #
# NOTE: To ensure that your implementation matches ours and you pass the #
# automated tests, make sure that your L2 regularization includes a factor #
# of 0.5 to simplify the expression for the gradient. #
############################################################################
loss, dout = softmax_loss(scores, y)
for i in range(self.num_layers):
loss = loss + 0.5*self.reg*np.sum(np.square(self.params['W'+str(i+1)]))
cache = list_x_in['x' + str(self.num_layers)]
dout, dw, db = affine_backward(dout, cache)
grads['W' + str(self.num_layers)], grads['b' + str(self.num_layers)] = dw + self.reg * self.params['W' + str(self.num_layers)], db
for id in range(self.num_layers-1,0,-1):
cache = list_x_in['x'+str(id)]
if self.normalization == 'batchnorm' and self.use_dropout:
dout, dw, db, dgamma, dbeta = affine_bn_relu_drop_backward(dout, cache)
grads['gamma' + str(id)], grads['beta' + str(id)] = dgamma, dbeta
elif self.normalization == 'batchnorm':
dout, dw, db, dgamma, dbeta = affine_bn_relu_backward(dout, cache)
grads['gamma' + str(id)], grads['beta' + str(id)] = dgamma, dbeta
elif self.use_dropout:
# print("dout", dout.shape)
dout, dw, db = affine_relu_drop_backward(dout, cache)
# print("dout",dout.shape)
else:
dout, dw, db = affine_relu_backward(dout, cache)
grads['W'+str(id)], grads['b'+str(id)] = dw+self.reg * self.params['W'+str(id)], db
############################################################################
# END OF YOUR CODE #
############################################################################
return loss, grads
optic.py
import numpy as np
"""
This file implements various first-order update rules that are commonly used
for training neural networks. Each update rule accepts current weights and the
gradient of the loss with respect to those weights and produces the next set of
weights. Each update rule has the same interface:
def update(w, dw, config=None):
Inputs:
- w: A numpy array giving the current weights.
- dw: A numpy array of the same shape as w giving the gradient of the
loss with respect to w.
- config: A dictionary containing hyperparameter values such as learning
rate, momentum, etc. If the update rule requires caching values over many
iterations, then config will also hold these cached values.
Returns:
- next_w: The next point after the update.
- config: The config dictionary to be passed to the next iteration of the
update rule.
NOTE: For most update rules, the default learning rate will probably not
perform well; however the default values of the other hyperparameters should
work well for a variety of different problems.
For efficiency, update rules may perform in-place updates, mutating w and
setting next_w equal to w.
"""
def sgd(w, dw, config=None):
"""
Performs vanilla stochastic gradient descent.
config format:
- learning_rate: Scalar learning rate.
"""
if config is None: config = {
}
config.setdefault('learning_rate', 1e-2)
w -= config['learning_rate'] * dw
return w, config
def sgd_momentum(w, dw, config=None):
"""
Performs stochastic gradient descent with momentum.
config format:
- learning_rate: Scalar learning rate.
- momentum: Scalar between 0 and 1 giving the momentum value.
Setting momentum = 0 reduces to sgd.
- velocity: A numpy array of the same shape as w and dw used to store a
moving average of the gradients.
"""
if config is None: config = {
}
config.setdefault('learning_rate', 1e-2)
config.setdefault('momentum', 0.9)
v = config.get('velocity', np.zeros_like(w))
next_w = None
###########################################################################
# TODO: Implement the momentum update formula. Store the updated value in #
# the next_w variable. You should also use and update the velocity v. #
###########################################################################
v = config['momentum'] * v - config['learning_rate']*dw
next_w = w + v
pass
###########################################################################
# END OF YOUR CODE #
###########################################################################
config['velocity'] = v
return next_w, config
def rmsprop(w, dw, config=None):
"""
Uses the RMSProp update rule, which uses a moving average of squared
gradient values to set adaptive per-parameter learning rates.
config format:
- learning_rate: Scalar learning rate.
- decay_rate: Scalar between 0 and 1 giving the decay rate for the squared
gradient cache.
- epsilon: Small scalar used for smoothing to avoid dividing by zero.
- cache: Moving average of second moments of gradients.
"""
if config is None: config = {
}
config.setdefault('learning_rate', 1e-2)
config.setdefault('decay_rate', 0.99)
config.setdefault('epsilon', 1e-8)
config.setdefault('cache', np.zeros_like(w))
next_w = None
###########################################################################
# TODO: Implement the RMSprop update formula, storing the next value of w #
# in the next_w variable. Don't forget to update cache value stored in #
# config['cache']. #
###########################################################################
cache = config['decay_rate']*config['cache']+(1-config['decay_rate'])*np.square(dw)
next_w = w - config['learning_rate'] * dw / np.sqrt(cache+config['epsilon'])
config['cache'] = cache
pass
###########################################################################
# END OF YOUR CODE #
###########################################################################
return next_w, config
def adam(w, dw, config=None):
"""
Uses the Adam update rule, which incorporates moving averages of both the
gradient and its square and a bias correction term.
config format:
- learning_rate: Scalar learning rate.
- beta1: Decay rate for moving average of first moment of gradient.
- beta2: Decay rate for moving average of second moment of gradient.
- epsilon: Small scalar used for smoothing to avoid dividing by zero.
- m: Moving average of gradient.
- v: Moving average of squared gradient.
- t: Iteration number.
"""
if config is None: config = {
}
config.setdefault('learning_rate', 1e-3)
config.setdefault('beta1', 0.9)
config.setdefault('beta2', 0.999)
config.setdefault('epsilon', 1e-8)
config.setdefault('m', np.zeros_like(w))
config.setdefault('v', np.zeros_like(w))
config.setdefault('t', 0)
next_w = None
###########################################################################
# TODO: Implement the Adam update formula, storing the next value of w in #
# the next_w variable. Don't forget to update the m, v, and t variables #
# stored in config. #
# #
# NOTE: In order to match the reference output, please modify t _before_ #
# using it in any calculations. #
###########################################################################
config['t'] = config['t'] + 1
first_moment = config['beta1']*config['m'] + (1-config['beta1'])*dw
second_moment = config['beta2']*config['v'] + (1-config['beta2'])*dw*dw
first_moment_bias = first_moment / (1 - config['beta1']**config['t'])
second_moment_bias = second_moment / (1 - config['beta2']**config['t'])
next_w = w - config['learning_rate'] * first_moment_bias / (np.sqrt(second_moment_bias)+config['epsilon'])
config['m'] = first_moment
config['v'] = second_moment
pass
###########################################################################
# END OF YOUR CODE #
###########################################################################
return next_w, config
文章浏览阅读3.5k次，点赞2次，收藏13次。为了从FTP服务器下载文件，需要要实现一个简单的FTP客户端。FTP（文件传输协议） 是 TCP/IP 协议组中的应用层协议。FTP协议使用字符串格式命令字，每条命令都是一行字符串，以“\r\n”结尾。客户端发送格式是：命令+空格+参数+"\r\n"的格式服务器返回格式是以：状态码+空格+提示字符串+"\r\n"的格式，代码只要解析状态码就可以了。读写文件需要登陆服务器，特殊用..._ftp 登录返回230
文章浏览阅读648次。前提：systemctl stop firewalld 关闭防火墙关闭selinux查看getenforce临时关闭setenforce 0永久关闭sed-i'/SELINUX/s/enforcing/disabled/'/etc/selinux/configselinux的三种模式enforcing：强制模式，SELinux 运作中，且已经正确的开始限制..._centos7 安装rabbitmq3.6.5
文章浏览阅读5.8k次。满意答案s55f2avsx2017.09.05采纳率：46%等级：12已帮助：5646人新版Android Studio/IntelliJ IDEA可以直接导入eclipse项目,不再推荐使用eclipse导出gradle的方式2启动Android Studio/IntelliJ IDEA，选择 import project3选择eclipse 项目4选择 create project f..._android studio 项目导入idea 看不懂安卓项目
文章浏览阅读860次，点赞2次，收藏6次。AI大模型技术已经在自然语言处理、计算机视觉、多模态交互等领域取得了显著的进展和成果，同时也引发了一系列新的挑战和问题，如数据质量、计算效率、知识可解释性、安全可靠性等。城市运维涉及到多个方面，如交通管理、环境监测、公共安全、社会治理等，它们需要处理和分析大量的多模态数据，如图像、视频、语音、文本等，并根据不同的场景和需求，提供合适的决策和响应。知识搜索有多种形式，如语义搜索、对话搜索、图像搜索、视频搜索等，它们可以根据用户的输入和意图，从海量的数据源中检索出最相关的信息，并以友好的方式呈现给用户。_ai大模型应用开发
文章浏览阅读8.2k次，点赞12次，收藏121次。为什么要测量阻抗呢？阻抗能代表什么？阻抗测量的注意事项... ...很多人可能会带着一系列的问题来阅读本文。不管是数字电路工程师还是射频工程师，都在关注各类器件的阻抗，本文非常值得一读。全文13000多字，认真读完大概需要2小时。一、阻抗测试基本概念阻抗定义：阻抗是元器件或电路对周期的交流信号的总的反作用。AC 交流测试信号 (幅度和频率)。包括实部和虚部。图1 阻抗的定义阻抗是评测电路、元件以及制作元件材料的重要参数。那么什么是阻抗呢？让我们先来看一下阻抗的定义。首先阻抗是一个矢量。通常，阻抗是_阻抗实部和虚部
文章浏览阅读955次。前面章节分享试用了pyzero,pygame但随着想增加更丰富的游戏内容，好多还要进行自己编写类，从今天开始解绍一个新的python游戏库arcade模块。通过此次的《连连看》游戏实现，让我对swing的相关知识有了进一步的了解，对java这门语言也有了比以前更深刻的认识。java的一些基本语法，比如数据类型、运算符、程序流程控制和数组等，理解更加透彻。java最核心的核心就是面向对象思想，对于这一个概念，终于悟到了一些。_arcade语言 like
文章浏览阅读1.1k次。源码简介与安装说明：2021增强版短视频去水印源码 去水印微信小程序源码网站 去水印软件源码安装环境（需要材料）：备案域名–服务器安装宝塔-安装 Nginx 或者 Apachephp5.6 以上-安装 sg11 插件小程序已自带解析接口，支持全网主流短视频平台，搭建好了就能用注：接口是公益的，那么多人用解析慢是肯定的，前段和后端源码已经打包，上传服务器之后在配置文件修改数据库密码。然后输入自己的域名，进入后台，创建小程序，输入自己的小程序配置即可安装说明：上传源码，修改data/_去水印机要增强版
文章浏览阅读557次。1. 触发器是FPGA存储数据的基本单元2. 触发器作为时序逻辑的基本元件，官方提供了丰富的配置方式，以适应各种可能的应用场景。_fdre #(.init(1'b0) // initial value of register (1'b0 or 1'b1) ) fdce_osc (
文章浏览阅读560次。本该是不同编译器结果不同，但是尝试了g++ msvc都是先计算c，再计算b，最后得到a+b+c是经过赋值以后的b和c参与计算而不是6。由上表可知，将q复制到p数组可以表示为：*p++=*q++，*优先级高，先取到对应q数组的值，然后两个++都是在后面，该行运算完后执行++。在电脑端编译完后会分为text data bss三种，其中text为可执行程序，data为初始化过的ro+rw变量，bss为未初始化或初始化为0变量。_嵌入式面试笔试c语言知识点
文章浏览阅读2.3k次。57 Things I've Learned Founding 3 Tech CompaniesJason Goldberg, Betashop | Oct. 29, 2010, 1:29 PMI’ve been founding andhelping run techn_mature
文章浏览阅读1.9k次。问题：先讲下需求，有若干个文本文件（txt或者csv文件等），每行代表一条数据，现在希望能合并成 1 个文本文件，且需要去除重复行。分析：一向奉行简单原则，如无必要，绝不复杂。如果数据量不大，那么如下两条命令就可以搞定合并：cat a.txt >> new.txtcat b.txt >> new.txt……去重：cat new...._python 超大文本合并
文章浏览阅读489次。这个过渡页是第一次打开小程序展示的，点击某个小程序前把手机的开发者->network link conditioner->enable & very bad network 就会在停在此页。比如《支付宝运动》这个小程序先看这个类的.h可以看到它继承于DTViewController点击左上角返回的方法- (void)back;#import "DTViewController.h"#import "APBaseLoadingV..._类似支付宝页面过度加载页