cs231n assignment1——SVM

整体思路

  1. 加载CIFAR-10数据集并展示部分数据
  2. 数据图像归一化,减去均值(也可以再除以方差)
  3. svm_loss_naive和svm_loss_vectorized计算hinge损失,用拉格朗日法列hinge损失函数
  4. 利用随机梯度下降法优化SVM
  5. 在训练集和验证集计算准确率,保存最好的模型在测试集进行预测计算准确率

加载展示划分数据集

加载CIFAR-10数据集

# Load the raw CIFAR-10 data.
#加载CIFAR-10数据集
cifar10_dir = 'cs231n/datasets/cifar-10-batches-py'# Cleaning up variables to prevent loading data multiple times (which may cause memory issue)
#清理变量以防止多次加载数据
try:del X_train, y_traindel X_test, y_testprint('Clear previously loaded data.')
except:passX_train, y_train, X_test, y_test = load_CIFAR10(cifar10_dir)# As a sanity check, we print out the size of the training and test data.
#打印出训练和测试数据的大小。
print('Training data shape: ', X_train.shape)
print('Training labels shape: ', y_train.shape)
print('Test data shape: ', X_test.shape)
print('Test labels shape: ', y_test.shape)
# Visualize some examples from the dataset.
#可视化部分数据
# We show a few examples of training images from each class.
#从每个类别中展示一些训练图片
classes = ['plane', 'car', 'bird', 'cat', 'deer', 'dog', 'frog', 'horse', 'ship', 'truck']
num_classes = len(classes)
samples_per_class = 7
for y, cls in enumerate(classes):idxs = np.flatnonzero(y_train == y)idxs = np.random.choice(idxs, samples_per_class, replace=False)for i, idx in enumerate(idxs):plt_idx = i * num_classes + y + 1plt.subplot(samples_per_class, num_classes, plt_idx)plt.imshow(X_train[idx].astype('uint8'))plt.axis('off')if i == 0:plt.title(cls)
plt.show()

划分数据集

# Split the data into train, val, and test sets. In addition we will
# create a small development set as a subset of the training data;
# we can use this for development so our code runs faster.
#将数据集划分为训练集49000张,测试集1000张和验证集1000张
#创建小样本数据加速训练
num_training = 49000
num_validation = 1000
num_test = 1000
num_dev = 500# Our validation set will be num_validation points from the original
# training set.
#验证集取自原始训练集
mask = range(num_training, num_training + num_validation)
X_val = X_train[mask]
y_val = y_train[mask]# Our training set will be the first num_train points from the original
# training set.
#训练集也取自原始训练集
mask = range(num_training)
X_train = X_train[mask]
y_train = y_train[mask]# We will also make a development set, which is a small subset of
# the training set.
mask = np.random.choice(num_training, num_dev, replace=False)
X_dev = X_train[mask]
y_dev = y_train[mask]# We use the first num_test points of the original test set as our
# test set.
mask = range(num_test)
X_test = X_test[mask]
y_test = y_test[mask]print('Train data shape: ', X_train.shape)
print('Train labels shape: ', y_train.shape)
print('Validation data shape: ', X_val.shape)
print('Validation labels shape: ', y_val.shape)
print('Test data shape: ', X_test.shape)
print('Test labels shape: ', y_test.shape)

数据集格式转换

# Preprocessing: reshape the image data into rows
#将图像数据转化为行
X_train = np.reshape(X_train, (X_train.shape[0], -1))
X_val = np.reshape(X_val, (X_val.shape[0], -1))
X_test = np.reshape(X_test, (X_test.shape[0], -1))
X_dev = np.reshape(X_dev, (X_dev.shape[0], -1))# As a sanity check, print out the shapes of the data
#输出数据集形状
print('Training data shape: ', X_train.shape)
print('Validation data shape: ', X_val.shape)
print('Test data shape: ', X_test.shape)
print('dev data shape: ', X_dev.shape)

图像数据归一化

外链图片转存失败,源站可能有防盗链机制,建议将图片保存下来直接上传

# Preprocessing: subtract the mean image
#减去均值
# first: compute the image mean based on the training data
#计算训练数据的均值
mean_image = np.mean(X_train, axis=0)
print(mean_image[:10]) # 输出部分元素
plt.figure(figsize=(4,4))
plt.imshow(mean_image.reshape((32,32,3)).astype('uint8')) # visualize the mean image
plt.show()# second: subtract the mean image from train and test data
#减去均值(更严谨的话可以继续除以方差)
X_train -= mean_image
X_val -= mean_image
X_test -= mean_image
X_dev -= mean_image# third: append the bias dimension of ones (i.e. bias trick) so that our SVM
# only has to worry about optimizing a single weight matrix W.
#数据维度转变简便计算优化权重矩阵W
X_train = np.hstack([X_train, np.ones((X_train.shape[0], 1))])
X_val = np.hstack([X_val, np.ones((X_val.shape[0], 1))])
X_test = np.hstack([X_test, np.ones((X_test.shape[0], 1))])
X_dev = np.hstack([X_dev, np.ones((X_dev.shape[0], 1))])print(X_train.shape, X_val.shape, X_test.shape, X_dev.shape)

评估多类 SVM 损失函数的函数

在这里插入图片描述

​ (图来自《从零开始:机器学习的数学原理和算法实践》)
在这里插入图片描述

所以我们在linear_svm.py中完善svm_loss_naive

def svm_loss_naive(W, X, y, reg):"""Structured SVM loss function, naive implementation (with loops).Inputs have dimension D, there are C classes, and we operate on minibatchesof N examples.Inputs:- W: A numpy array of shape (D, C) containing weights.- X: A numpy array of shape (N, D) containing a minibatch of data.- y: A numpy array of shape (N,) containing training labels; y[i] = c meansthat X[i] has label c, where 0 <= c < C.- reg: (float) regularization strengthReturns a tuple of:- loss as single float- gradient with respect to weights W; an array of same shape as W"""#梯度矩阵初始化dW = np.zeros(W.shape)  # initialize the gradient as zero# compute the loss and the gradient#计算损失和梯度num_classes = W.shape[1]num_train = X.shape[0]loss = 0.0for i in range(num_train):#W*Xiscore = X[i].dot(W)correct_score = score[y[i]]for j in range(num_classes):#预测正确if j == y[i]:continue#W*Xi-Wyi*Xi+1margin = score[j] - correct_score + 1  # 拉格朗日if margin > 0:loss += margin# Right now the loss is a sum over all training examples, but we want it# to be an average instead so we divide by num_train.#平均损失loss /= num_train#加上正则化λ||W||²# Add regularization to the loss.loss += reg * np.sum(W * W)############################################################################## TODO:                                                                     ## Compute the gradient of the loss function and store it dW.                ## Rather that first computing the loss and then computing the derivative,   ## it may be simpler to compute the derivative at the same time that the     ## loss is being computed. As a result you may need to modify some of the    ## code above to compute the gradient.                                       ############################################################################### *****START OF YOUR CODE (DO NOT DELETE/MODIFY THIS LINE)*****dW /= num_traindW += reg * W# *****END OF YOUR CODE (DO NOT DELETE/MODIFY THIS LINE)*****return loss, dW

评估svm_loss_naive函数

# Evaluate the naive implementation of the loss we provided for you:
from cs231n.classifiers.linear_svm import svm_loss_naive
import time# generate a random SVM weight matrix of small numbers
# 随机初始化权重矩阵
W = np.random.randn(3073, 10) * 0.0001 
#计算梯度和损失
loss, grad = svm_loss_naive(W, X_dev, y_dev, 0.000005)
print('loss: %f' % (loss, ))

在验证集计算梯度损失

数值估计损失函数的梯度,并将数值估计值与计算的梯度进行比较

# Once you've implemented the gradient, recompute it with the code below
# and gradient check it with the function we provided for you# Compute the loss and its gradient at W.
#计算损失和梯度
loss, grad = svm_loss_naive(W, X_dev, y_dev, 0.0)# Numerically compute the gradient along several randomly chosen dimensions, and
# compare them with your analytically computed gradient. The numbers should match
# almost exactly along all dimensions.
from cs231n.gradient_check import grad_check_sparse
f = lambda w: svm_loss_naive(w, X_dev, y_dev, 0.0)[0]
grad_numerical = grad_check_sparse(f, W, grad)# do the gradient check once again with regularization turned on
# you didn't forget the regularization gradient did you?
loss, grad = svm_loss_naive(W, X_dev, y_dev, 5e1)
f = lambda w: svm_loss_naive(w, X_dev, y_dev, 5e1)[0]
grad_numerical = grad_check_sparse(f, W, grad)

用向量形式计算损失函数

在这里插入图片描述

所以我们在linear_svm.py中完善svm_loss_vectorized

def svm_loss_vectorized(W, X, y, reg):"""Structured SVM loss function, vectorized implementation.Inputs and outputs are the same as svm_loss_naive."""loss = 0.0dW = np.zeros(W.shape)  # initialize the gradient as zero############################################################################## TODO:                                                                     ## Implement a vectorized version of the structured SVM loss, storing the    ## result in loss.                                                           ############################################################################### *****START OF YOUR CODE (DO NOT DELETE/MODIFY THIS LINE)*****num_train=X.shape[0]classes_num=X.shape[1]score = X.dot(W)#矩阵大小变化,大小不同的矩阵不可以加减correct_scores = score[range(num_train), list(y)].reshape(-1, 1) #[N, 1]margin = np.maximum(0, score - correct_scores + 1)margin[range(num_train), list(y)] = 0#正则化loss = np.sum(margin) / num_trainloss += 0.5 * reg * np.sum(W * W)# *****END OF YOUR CODE (DO NOT DELETE/MODIFY THIS LINE)*****############################################################################## TODO:                                                                     ## Implement a vectorized version of the gradient for the structured SVM     ## loss, storing the result in dW.                                           ##                                                                           ## Hint: Instead of computing the gradient from scratch, it may be easier    ## to reuse some of the intermediate values that you used to compute the     ## loss.                                                                     ############################################################################### *****START OF YOUR CODE (DO NOT DELETE/MODIFY THIS LINE)*****#大于0的置1,其余为0margin[margin>0] = 1margin[range(num_train),list(y)] = 0margin[range(num_train),y] -= np.sum(margin,1)dW=X.T.dot(margin)dW=dW/num_traindW=dW+reg*W# *****END OF YOUR CODE (DO NOT DELETE/MODIFY THIS LINE)*****return loss, dW

然后我们对比两种损失函数计算的时间差异

# Complete the implementation of svm_loss_vectorized, and compute the gradient
# of the loss function in a vectorized way.# The naive implementation and the vectorized implementation should match, but
# the vectorized version should still be much faster.
tic = time.time()
_, grad_naive = svm_loss_naive(W, X_dev, y_dev, 0.000005)
toc = time.time()
print('Naive loss and gradient: computed in %fs' % (toc - tic))tic = time.time()
_, grad_vectorized = svm_loss_vectorized(W, X_dev, y_dev, 0.000005)
toc = time.time()
print('Vectorized loss and gradient: computed in %fs' % (toc - tic))# The loss is a single number, so it is easy to compare the values computed
# by the two implementations. The gradient on the other hand is a matrix, so
# we use the Frobenius norm to compare them.
difference = np.linalg.norm(grad_naive - grad_vectorized, ord='fro')
print('difference: %f' % difference)

使用SGD优化

在这里插入图片描述

from __future__ import print_functionfrom builtins import range
from builtins import object
import numpy as np
from ..classifiers.linear_svm import *
from ..classifiers.softmax import *
from past.builtins import xrangeclass LinearClassifier(object):def __init__(self):self.W = Nonedef train(self,X,y,learning_rate=1e-3,reg=1e-5,num_iters=100,batch_size=200,verbose=False,):"""Train this linear classifier using stochastic gradient descent.Inputs:- X: A numpy array of shape (N, D) containing training data; there are Ntraining samples each of dimension D.- y: A numpy array of shape (N,) containing training labels; y[i] = cmeans that X[i] has label 0 <= c < C for C classes.- learning_rate: (float) learning rate for optimization.- reg: (float) regularization strength.- num_iters: (integer) number of steps to take when optimizing- batch_size: (integer) number of training examples to use at each step.- verbose: (boolean) If true, print progress during optimization.Outputs:A list containing the value of the loss function at each training iteration."""num_train, dim = X.shapenum_classes = (np.max(y) + 1)  # assume y takes values 0...K-1 where K is number of classesif self.W is None:# lazily initialize Wself.W = 0.001 * np.random.randn(dim, num_classes)# Run stochastic gradient descent to optimize Wloss_history = []for it in range(num_iters):X_batch = Noney_batch = None########################################################################## TODO:                                                                 ## Sample batch_size elements from the training data and their           ## corresponding labels to use in this round of gradient descent.        ## Store the data in X_batch and their corresponding labels in           ## y_batch; after sampling X_batch should have shape (batch_size, dim)   ## and y_batch should have shape (batch_size,)                           ##                                                                       ## Hint: Use np.random.choice to generate indices. Sampling with         ## replacement is faster than sampling without replacement.              ########################################################################### *****START OF YOUR CODE (DO NOT DELETE/MODIFY THIS LINE)*****hint=np.random.choice(num_train,batch_size,replace=True)X_batch = X[hint]y_batch = y[hint]# *****END OF YOUR CODE (DO NOT DELETE/MODIFY THIS LINE)*****# evaluate loss and gradientloss, grad = self.loss(X_batch, y_batch, reg)loss_history.append(loss)# perform parameter update########################################################################## TODO:                                                                 ## Update the weights using the gradient and the learning rate.          ########################################################################### *****START OF YOUR CODE (DO NOT DELETE/MODIFY THIS LINE)*****self.W = self.W - learning_rate * grad# *****END OF YOUR CODE (DO NOT DELETE/MODIFY THIS LINE)*****if verbose and it % 100 == 0:print("iteration %d / %d: loss %f" % (it, num_iters, loss))return loss_historydef predict(self, X):"""Use the trained weights of this linear classifier to predict labels fordata points.Inputs:- X: A numpy array of shape (N, D) containing training data; there are Ntraining samples each of dimension D.Returns:- y_pred: Predicted labels for the data in X. y_pred is a 1-dimensionalarray of length N, and each element is an integer giving the predictedclass."""y_pred = np.zeros(X.shape[0])############################################################################ TODO:                                                                   ## Implement this method. Store the predicted labels in y_pred.            ############################################################################# *****START OF YOUR CODE (DO NOT DELETE/MODIFY THIS LINE)*****scores = X.dot(self.W)y_pred = y_pred+np.argmax(scores,1)# *****END OF YOUR CODE (DO NOT DELETE/MODIFY THIS LINE)*****return y_preddef loss(self, X_batch, y_batch, reg):"""Compute the loss function and its derivative.Subclasses will override this.Inputs:- X_batch: A numpy array of shape (N, D) containing a minibatch of Ndata points; each point has dimension D.- y_batch: A numpy array of shape (N,) containing labels for the minibatch.- reg: (float) regularization strength.Returns: A tuple containing:- loss as a single float- gradient with respect to self.W; an array of the same shape as W"""passclass LinearSVM(LinearClassifier):""" A subclass that uses the Multiclass SVM loss function """def loss(self, X_batch, y_batch, reg):return svm_loss_vectorized(self.W, X_batch, y_batch, reg)class Softmax(LinearClassifier):""" A subclass that uses the Softmax + Cross-entropy loss function """def loss(self, X_batch, y_batch, reg):return softmax_loss_vectorized(self.W, X_batch, y_batch, reg)

利用SGD迭代减少损失

from cs231n.classifiers import LinearSVM
#加载SVM
svm = LinearSVM()
tic = time.time()
loss_hist = svm.train(X_train, y_train, learning_rate=1e-7, reg=2.5e4,num_iters=1500, verbose=True)
toc = time.time()
print('That took %fs' % (toc - tic))

在训练集和验证集计算准确率

#在训练集和验证集进行预测结果,计算准确率
y_train_pred = svm.predict(X_train)
print('training accuracy: %f' % (np.mean(y_train == y_train_pred), ))
y_val_pred = svm.predict(X_val)
print('validation accuracy: %f' % (np.mean(y_val == y_val_pred), ))

计算预测数据准确率

# Use the validation set to tune hyperparameters (regularization strength and
# learning rate). You should experiment with different ranges for the learning
# rates and regularization strengths; if you are careful you should be able to
# get a classification accuracy of about 0.39 (> 0.385) on the validation set.# Note: you may see runtime/overflow warnings during hyper-parameter search.
# This may be caused by extreme values, and is not a bug.# results is dictionary mapping tuples of the form
# (learning_rate, regularization_strength) to tuples of the form
# (training_accuracy, validation_accuracy). The accuracy is simply the fraction
# of data points that are correctly classified.
results = {}
best_val = -1   # The highest validation accuracy that we have seen so far.
best_svm = None # The LinearSVM object that achieved the highest validation rate.################################################################################
# TODO:                                                                        #
# Write code that chooses the best hyperparameters by tuning on the validation #
# set. For each combination of hyperparameters, train a linear SVM on the      #
# training set, compute its accuracy on the training and validation sets, and  #
# store these numbers in the results dictionary. In addition, store the best   #
# validation accuracy in best_val and the LinearSVM object that achieves this  #
# accuracy in best_svm.                                                        #
#                                                                              #
# Hint: You should use a small value for num_iters as you develop your         #
# validation code so that the SVMs don't take much time to train; once you are #
# confident that your validation code works, you should rerun the validation   #
# code with a larger value for num_iters.                                      #
################################################################################# Provided as a reference. You may or may not want to change these hyperparameters
#学习率
learning_rates = [1e-7, 5e-5]
#reg
regularization_strengths = [2.5e4, 5e4]# *****START OF YOUR CODE (DO NOT DELETE/MODIFY THIS LINE)*****for learning_rate in learning_rates:for regularization_strength in regularization_strengths:svm = LinearSVM()#svm训练loss_hist = svm.train(X_train, y_train, learning_rate=learning_rate, reg=regularization_strength, num_iters=1500, verbose=True)#在训练集预测,计算平均准确率y_train_pred2 = svm.predict(X_train)training_accuracy = np.mean(y_train == svm.predict(X_train))print('training accuracy: %f' % (np.mean(y_train == y_train_pred2)))#在验证集预测,计算平均准确率y_val_pred2 = svm.predict(X_val)val_accuracy = np.mean(y_val== svm.predict(X_val))print('validation accuracy: %f' % (np.mean(y_val == y_val_pred2)))#在训练集和验证集计算的准确率保存在resultsresults[(learning_rate,regularization_strength)] = (training_accuracy,val_accuracy)print(results)#取最大的准确率保存在best_valif best_val < val_accuracy:best_val = val_accuracybest_svm = svm# *****END OF YOUR CODE (DO NOT DELETE/MODIFY THIS LINE)*****# Print out results.
for lr, reg in sorted(results):train_accuracy, val_accuracy = results[(lr, reg)]print('lr %e reg %e train accuracy: %f val accuracy: %f' % (lr, reg, train_accuracy, val_accuracy))print('best validation accuracy achieved during cross-validation: %f' % best_val)

将最好的模型保存在best_svm中,在测试集计算准确率

# Evaluate the best svm on test set
y_test_pred = best_svm.predict(X_test)
test_accuracy = np.mean(y_test == y_test_pred)
print('linear SVM on raw pixels final test set accuracy: %f' % test_accuracy)

主要解决问题:

  • 损失函数和梯度的推导

  • 为什么SGD越迭代可能产生loss变大的情况:

    因为SGD在每一步放弃了对梯度准确性的追求,每步仅仅随机采样少量样本来计算梯度,计算速度快,内存开销小,但是由于每步接受的信息量有限,对梯度的估计出现偏差也在所难免,造成目标函数曲线收敛轨迹显得很不稳定,伴有剧烈波动,甚至有时出现不收敛的情况。(这很正常!)

一个冷笑话(这能看出来是啥就有鬼了,果然用词很严谨

%f’ % (
lr, reg, train_accuracy, val_accuracy))

print(‘best validation accuracy achieved during cross-validation: %f’ % best_val)

将最好的模型保存在best_svm中,在测试集计算准确率```python
# Evaluate the best svm on test set
y_test_pred = best_svm.predict(X_test)
test_accuracy = np.mean(y_test == y_test_pred)
print('linear SVM on raw pixels final test set accuracy: %f' % test_accuracy)

主要解决问题:

  • 损失函数和梯度的推导

  • 为什么SGD越迭代可能产生loss变大的情况:

    因为SGD在每一步放弃了对梯度准确性的追求,每步仅仅随机采样少量样本来计算梯度,计算速度快,内存开销小,但是由于每步接受的信息量有限,对梯度的估计出现偏差也在所难免,造成目标函数曲线收敛轨迹显得很不稳定,伴有剧烈波动,甚至有时出现不收敛的情况。(这很正常!)

一个冷笑话(这能看出来是啥就有鬼了,果然用词很严谨

在这里插入图片描述

本文来自互联网用户投稿,该文观点仅代表作者本人,不代表本站立场。本站仅提供信息存储空间服务,不拥有所有权,不承担相关法律责任。如若转载,请注明出处:http://www.mzph.cn/news/636376.shtml

如若内容造成侵权/违法违规/事实不符,请联系多彩编程网进行投诉反馈email:809451989@qq.com,一经查实,立即删除!

相关文章

产品经理 | 原型设计必须遵循的视觉设计规范(1)— 设计原则

前言&#xff1a;Hello大家好&#xff0c;我是小哥谈。本系列原型设计规范教程&#xff0c;主要用于规范系统的原型界面设计&#xff0c;使之具有良好的设计风格&#xff0c;帮助塑造品牌形象。通过定义原型的字体、图标、布局、颜色等信息&#xff0c;提供多样化的交互设计方案…

无法找到mfc100.dll的解决方法分享,如何快速修复mfc100.dll文件

在日常使用电脑时&#xff0c;我们可能会碰到一些系统错误提示&#xff0c;比如“无法找到mfc100.dll”的信息。这种错误通常会阻碍代码的执行或某些应用程序的启动。为了帮助您解决这一问题&#xff0c;本文将深入探讨其成因&#xff0c;并提供几种不同的mfc100.dll解决方案。…

1360. 卒的遍历-深度优先搜索-DFS

代码&#xff1a; #include<bits/stdc.h> using namespace std; int n,m; int r[25][3]; int fx[3]{0,1,0}; int fy[3]{0,0,1}; int a; void print(int k){a;cout<<a<<":";for(int i1;i<k;i){cout<<r[i][1]<<","<<…

[C#]winform部署yolov8图像分类的openvino格式的模型

【官方框架地址】 https://github.com/ultralytics/ultralytics 【openvino介绍】 OpenVINO是一个针对Intel硬件优化的开源工具包&#xff0c;用于优化和部署深度学习模型。以下是OpenVINO部署模型的主要优点&#xff1a; 高性能&#xff1a;OpenVINO提供了一系列性能优化工…

Flask 3.x log全域配置(包含pytest)

最近使用到flask3.x&#xff0c;配置了全域的log&#xff0c;这边记录下 首先需要创建logging的配置文件&#xff0c;我是放在项目根目录的&#xff0c; Logging 配置 logging.json {"version": 1, # 配置文件版本号"formatters": {"default&qu…

HTTP 协议和 TCP/IP 协议之间有什么区别?

HTTP&#xff08;超文本传输协议&#xff09;和TCP/IP&#xff08;传输控制协议/互联网协议&#xff09;是两种在互联网通信中广泛使用的协议&#xff0c;它们之间的区别和联系对许多人来说可能还不是很清晰&#xff0c;今天我们就带大家来一起了解一下HTTP和TCP/IP协议这2者之…

java数据结构与算法刷题-----LeetCode566. 重塑矩阵

java数据结构与算法刷题目录&#xff08;剑指Offer、LeetCode、ACM&#xff09;-----主目录-----持续更新(进不去说明我没写完)&#xff1a;https://blog.csdn.net/grd_java/article/details/123063846 文章目录 1. 法一&#xff0c;下标填充2. 法二&#xff1a;数学除法和取余…

MFC 序列化机制

目录 文件操作相关类 序列化机制相关类 序列化机制使用 序列化机制执行过程 序列化类对象 文件操作相关类 CFile&#xff1a;文件操作类&#xff0c;封装了关于文件读写等操作&#xff0c;常见的方法&#xff1a; CFile::Open&#xff1a;打开或者创建文件CFile::Write/…

Mongo集群入门

一、前言 MongoDB 有三种集群架构模式&#xff0c;分别为主从复制&#xff08;Master-Slaver&#xff09;、副本集&#xff08;Replica Set&#xff09;和分片&#xff08;Sharding&#xff09;模式。 Master-Slaver 是一种主从复制的模式&#xff0c;目前已经不推荐使用。 Re…

大模型:我也会自监督学习~

前言 当下大模型的能力已经很强了&#xff0c;但是将来我们想要的是能力更强的大模型&#xff0c;其最好能够处理各种复杂问题也即强对齐模型。 之前大模型训练的监督信号主要来源于人类反馈&#xff0c;但是如果想要训练一个强对齐模型必然就需要一个对应的强监督信号&#…

WebDriverWait太强大

selenium webdriver及wait 1 implicitly包打天下2 Linkedin无法登录返回值很乱&#xff0c;怎么破&#xff1f; 1 implicitly包打天下 有了implicitly之后&#xff0c;基本上不再关注网速之类的影响。 self.driver.implicitly_wait(511)2 Linkedin无法登录返回值很乱&#xf…

探索图像检索:从理论到实战的应用

目录 一、引言二、图像检索技术概述图像检索的基本概念图像检索与文本检索的区别特征提取技术相似度计算索引技术 三、图像检索技术代码示例图像特征提取示例相似度计算索引技术 四、图像搜索流程架构数据采集与预处理特征提取相似度计算与排名结果呈现与优化 五、实际应用图像…

【征服redis11】花了一天,我终于懂了redis的底层数据结构

现在我们可以开始讨论一个硬核问题了—Redis的数据结构。在redis里常见的数据类型有String、Hash、Set、List、Zset五种常用结构&#xff0c;另外还有Hyperloglog、Geo、Streams等结构。这些结构的特征和应用场景我们在前面都介绍过&#xff0c;这里我们来研究一下其内部结构是…

【分布式技术】ELK大型日志收集分析系统

目录 步骤一&#xff1a;完成JAVA环境部署 步骤二&#xff1a;部署ES节点&#xff08;三台主机&#xff09; 步骤三&#xff1a;内核参数修改 步骤四&#xff1a;web端查看验证 步骤五&#xff1a;yum安装nginx 步骤六&#xff1a;完成logstash部署 步骤七&#xff1a;部…

荣誉艾尔迪亚人的题解

目录 原题描述&#xff1a; 题目背景 题目描述 输入格式 输出格式 样例 Input 1 Output 1 Input 2 Output 2 数据范围&#xff1a; 样例解释 主要思路&#xff1a; 代码code&#xff1a; 原题描述&#xff1a; 时间限制: 1000ms 空间限制: 65536kb 题目背景 ​…

Python爬虫时被封IP,该怎么解决?四大动态IP平台测评

在使用 Python 进行爬虫时&#xff0c;很有可能因为一些异常行为被封 IP&#xff0c;这主要是因为一些爬虫时产生的异常行为导致的。 在曾经的一次数据爬取的时候&#xff0c;我尝试去爬取Google地图上面的商家联系方式和地址信息做营销&#xff0c;可是很不幸&#xff0c;还只…

从规则到神经网络:机器翻译技术的演化之路

文章目录 从规则到神经网络&#xff1a;机器翻译技术的演化之路一、概述1. 机器翻译的历史与发展2. 神经机器翻译的兴起3. 技术对现代社会的影响 二、机器翻译的核心技术1. 规则基础的机器翻译&#xff08;Rule-Based Machine Translation, RBMT&#xff09;2. 统计机器翻译&am…

【内存管理】flink内存管理(一):内存管理概述:flink主动管理内存原理、flink内存模型

文章目录 一.flink为什么自己管理内存1. 处理大数据时JVM内存管理的问题2. flink主动管理内存逻辑2.1. Flink内存管理方面2.2. 序列化、反序列化说明 3. Flink主动管理内存的好处 二. Flink内存模型1. 堆内存2. 非堆内存2.1. 托管内存2.2.直接内存2.3. JVM特定内存 本节从整体使…

Nginx重写功能location与rewrite

1. location 从功能看 rewrite 和 location 似乎有点像&#xff0c;都能实现跳转&#xff0c;主要区别在于 rewrite 是在同一域名内更改获取资源的路径&#xff0c;而 location 是对一类路径做控制访问或反向代理&#xff0c;还可以proxy_pass 到其他机器。 rewrite 对访问的…

书生·浦语大模型实战营-学习笔记4

XTuner 大模型单卡低成本微调实战 Finetune简介 常见的两种微调策略&#xff1a;增量预训练、指令跟随 指令跟随微调 数据是一问一答的形式 对话模板构建 每个开源模型使用的对话模板都不相同 指令微调原理&#xff1a; 由于只有答案部分是我们期望模型来进行回答的内容…