主程序
Step1:环境参数设置
导入工具库并设置在notebook中显示图像的默认参数。
# Run some setup code for this notebook.
from __future__ import print_function
import random
import numpy as np
from cs231n.data_utils import load_CIFAR10
import matplotlib.pyplot as plt
# This is a bit of magic to make matplotlib figures appear inline in the
# notebook rather than in a new window.
%matplotlib inline
plt.rcParams['figure.figsize'] = (10.0, 8.0) # set default size of plots
plt.rcParams['image.interpolation'] = 'nearest'
plt.rcParams['image.cmap'] = 'gray'
# Some more magic so that the notebook will reload external python modules;
# see http://stackoverflow.com/questions/1907993/autoreload-of-modules-in-ipython
%load_ext autoreload
%autoreload 2
plt.rcParams是配置参数的方法,这里inline方式实现在notebook内显示图像,接下来设置显示的默认参数:
通过给figsize参数赋值,设置显示图像的最大范围
通过给interpolation赋值,设置差值方式
通过给cmap参数赋值'gray',设置图像在灰度空间内。
Step2:数据的获取和处理
# Load the raw CIFAR-10 data.
cifar10_dir = 'cs231n/datasets/cifar-10-batches-py'
# Cleaning up variables to prevent loading data multiple times (which may cause memory issue)
try:
del X_train, y_train
del X_test, y_test
print('Clear previously loaded data.')
except:
pass
X_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.
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)
这里为了避免重复加载训练数据、测试数据集,用一个try-except方法处理异常。
可视化部分样本,显示部分训练数据样本的图像
# Visualize some examples from the dataset.
# We show a few examples of training images from each class.
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 + 1
plt.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()
结果为:
子采样
# 把数据集分为训练集、验证集和测试集.
#此外还设置了一个dev set,它是训练集的一个子集
#我们可以将它(dev set)用于测试我们编写的代码,速度更快
num_training = 49000 #训练集大小
num_validation = 1000 #验证集大小
num_test = 1000 #测试集大小
num_dev = 500 #开发集大小
#验证集中的样本是原始训练集中的num_validation(1000)个样本
mask = range(num_training, num_training + num_validation)
X_val = X_train[mask]
y_val = y_train[mask]
#训练集是原始训练集中的前num_training(49000)个样本
mask = range(num_training)
X_train = X_train[mask]
y_train = y_train[mask]
#我们还设置了开发集 它是训练集中的一个小子集 从49000个训练样本中随机不放回取500个
mask = np.random.choice(num_training, num_dev, replace=False)
X_dev = X_train[mask]
y_dev = y_train[mask]
#测试集是原始测试集中的前num_test(1000)个样本
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)
输出:
Train data shape: (49000, 32, 32, 3)
Train labels shape: (49000,)
Validation data shape: (1000, 32, 32, 3)
Validation labels shape: (1000,)
Test data shape: (1000, 32, 32, 3)
Test labels shape: (1000,)
预处理
# 预处理 将每张图像(32,32,3)拉伸为一维数组(3072,)
#各个数据集从四维数组(m,32,32,3) 转型为2维数组(m,3072)
X_train = X_train.reshape((X_train.shape[0],-1))
X_val = X_val.reshape((X_val.shape[0],-1))
X_test = X_test.reshape((X_test.shape[0],-1))
X_dev = X_dev.reshape((X_dev.shape[0],-1))
'''
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))
'''
# 各个数据集转型后的大小
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)
输出:
Training data shape: (49000, 3072)
Validation data shape: (1000, 3072)
Test data shape: (1000, 3072)
dev data shape: (500, 3072)
#预处理 0均值化 减去图像每个像素/特征上的平均值
#基于训练数据 计算图像每个像素/特征上的平均值
mean_image = np.mean(X_train,axis=0) #(3072,)
print(mean_image[:10]) #查看前10个元素
plt.figure(figsize=(4,4))
plt.imshow(mean_image.reshape((32,32,3)).astype('uint8')) #可视化平均图像
[130.64189796 135.98173469 132.47391837 130.05569388 135.34804082
131.75402041 130.96055102 136.14328571 132.47636735 131.48467347]
#各个数据集减去基于训练集计算的各个像素/特征的平均值
#(m,3072) - (3072,) 广播运算
X_train -= mean_image
X_val -= mean_image
X_test -= mean_image
X_dev -= mean_image
#为各个数据集的特征矩阵加一列1 方便矩阵运算
#将偏置参数加到权重参数中 只需要优化一个权重矩阵W即可
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)
Step 3:分类
初始化KNN分类器
# 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
W = np.random.randn(3073, 10) * 0.0001
loss, grad = svm_loss_naive(W, X_dev, y_dev, 0.000005)
print('loss: %f' % (loss, ))
# 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.
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)
距离可视化
# 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.
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)
结果为:
numerical: -0.011401 analytic: -0.011401, relative error: 1.474249e-08
numerical: -23.651887 analytic: -23.651887, relative error: 7.907349e-12
numerical: 24.897402 analytic: 24.897402, relative error: 1.137686e-11
numerical: 19.950000 analytic: 19.950000, relative error: 2.425640e-11
numerical: -16.183868 analytic: -16.109304, relative error: 2.308959e-03
numerical: -6.893658 analytic: -6.893658, relative error: 3.255044e-11
numerical: -5.874221 analytic: -5.874221, relative error: 6.363300e-12
numerical: 0.311321 analytic: 0.311321, relative error: 4.335093e-11
numerical: -33.334133 analytic: -33.334133, relative error: 2.093848e-12
numerical: -25.731248 analytic: -25.731248, relative error: 1.321516e-11
numerical: 26.213996 analytic: 26.213996, relative error: 1.418260e-11
numerical: 5.730217 analytic: 5.730217, relative error: 1.917440e-11
numerical: -3.279934 analytic: -3.279934, relative error: 4.253709e-11
numerical: -4.634049 analytic: -4.634049, relative error: 7.355779e-11
numerical: -28.767326 analytic: -28.767326, relative error: 4.594319e-12
numerical: -4.643358 analytic: -4.643358, relative error: 4.011835e-11
numerical: 18.096989 analytic: 18.096989, relative error: 1.574772e-11
numerical: 4.332012 analytic: 4.332012, relative error: 2.406922e-11
numerical: -14.976196 analytic: -14.976196, relative error: 4.356412e-11
numerical: 15.522554 analytic: 15.522554, relative error: 1.036904e-11
Step 4: 预测
计算损失
# Next implement the function svm_loss_vectorized; for now only compute the loss;
# we will implement the gradient in a moment.
tic = time.time()
loss_naive, grad_naive = svm_loss_naive(W, X_dev, y_dev, 0.000005)
toc = time.time()
print('Naive loss: %e computed in %fs' % (loss_naive, toc - tic))
from cs231n.classifiers.linear_svm import svm_loss_vectorized
tic = time.time()
loss_vectorized, _ = svm_loss_vectorized(W, X_dev, y_dev, 0.000005)
toc = time.time()
print('Vectorized loss: %e computed in %fs' % (loss_vectorized, toc - tic))
# The losses should match but your vectorized implementation should be much faster.
print('difference: %f' % (loss_naive - loss_vectorized))
结果:
Naive loss: 9.140558e+00 computed in 0.336161s
Vectorized loss: 9.140558e+00 computed in 0.077880s
difference: 0.000000
# 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)
结果:
Naive loss and gradient: computed in 0.429454s
Vectorized loss and gradient: computed in 0.007643s
difference: 0.000000
梯度下降
# In the file linear_classifier.py, implement SGD in the function
# LinearClassifier.train() and then run it with the code below.
from cs231n.classifiers import LinearSVM
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))
# A useful debugging strategy is to plot the loss as a function of
# iteration number:
plt.plot(loss_hist)
plt.xlabel('Iteration number')
plt.ylabel('Loss value')
plt.show()
# Write the LinearSVM.predict function and evaluate the performance on both the
# training and validation set
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), ))
# 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 0.4 on the validation set.
learning_rates = [1e-7, 5e-5]
regularization_strengths = [2.5e4, 5e4]
# 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. #
################################################################################
#当前共有3*8=24种组合
for lr in learning_rates:
for reg in regularization_strengths:
svm = LinearSVM() #实例化类对象
#调用train方法
loss_hist = svm.train(X_train, y_train, learning_rate=lr, reg=reg,
num_iters=1500, verbose=True)
y_train_pred = svm.predict(X_train)
train_accuracy = np.mean(y_train == y_train_pred)
y_val_pred = svm.predict(X_val)
val_accuracy = np.mean(y_val == y_val_pred)
if val_accuracy > best_val:
best_val = val_accuracy
best_svm = svm
results[(lr,reg)] = (train_accuracy,val_accuracy)
################################################################################
# END OF YOUR CODE #
################################################################################
# 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)
# Visualize the cross-validation results
import math
x_scatter = [math.log10(x[0]) for x in results]
y_scatter = [math.log10(x[1]) for x in results]
# plot training accuracy
marker_size = 100
colors = [results[x][0] for x in results]
plt.subplot(2, 1, 1)
plt.scatter(x_scatter, y_scatter, marker_size, c=colors)
plt.colorbar()
plt.xlabel('log learning rate')
plt.ylabel('log regularization strength')
plt.title('CIFAR-10 training accuracy')
# plot validation accuracy
colors = [results[x][1] for x in results] # default size of markers is 20
plt.subplot(2, 1, 2)
plt.scatter(x_scatter, y_scatter, marker_size, c=colors)
plt.colorbar()
plt.xlabel('log learning rate')
plt.ylabel('log regularization strength')
plt.title('CIFAR-10 validation accuracy')
plt.show()
# 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)
linear SVM on raw pixels final test set accuracy: 0.103000
# Visualize the learned weights for each class.
# Depending on your choice of learning rate and regularization strength, these may
# or may not be nice to look at.
w = best_svm.W[:-1,:] # strip out the bias
w = w.reshape(32, 32, 3, 10)
w_min, w_max = np.min(w), np.max(w)
classes = ['plane', 'car', 'bird', 'cat', 'deer', 'dog', 'frog', 'horse', 'ship', 'truck']
for i in range(10):
plt.subplot(2, 5, i + 1)
# Rescale the weights to be between 0 and 255
wimg = 255.0 * (w[:, :, :, i].squeeze() - w_min) / (w_max - w_min)
plt.imshow(wimg.astype('uint8'))
plt.axis('off')
plt.title(classes[i])
结果:
需要引入的子程序
from __future__ import print_function
import numpy as np
from cs231n.classifiers.linear_svm import *
from cs231n.classifiers.softmax import *
class LinearClassifier(object):
def __init__(self):
self.W = None
def 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 N
training samples each of dimension D.
- y: A numpy array of shape (N,) containing training labels; y[i] = c
means 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.shape
num_classes = np.max(y) + 1 # assume y takes values 0...K-1 where K is number of classes
if self.W is None:
# lazily initialize W
self.W = 0.001 * np.random.randn(dim, num_classes)
# Run stochastic gradient descent to optimize W
loss_history = []
for it in range(num_iters):
X_batch = None
y_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 (dim, batch_size) #
# 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. #
#########################################################################
random_Index = np.random.choice(len(X),batch_size,replace=True)
X_batch = X[random_Index]
y_batch = y[random_Index]
#########################################################################
# END OF YOUR CODE #
#########################################################################
# evaluate loss and gradient
loss, 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. #
#########################################################################
self.W += (-learning_rate*grad)
#########################################################################
# END OF YOUR CODE #
#########################################################################
if verbose and it % 100 == 0:
print('iteration %d / %d: loss %f' % (it, num_iters, loss))
return loss_history
def predict(self, X):
"""
Use the trained weights of this linear classifier to predict labels for
data points.
Inputs:
- X: A numpy array of shape (N, D) containing training data; there are N
training samples each of dimension D.
Returns:
- y_pred: Predicted labels for the data in X. y_pred is a 1-dimensional
array of length N, and each element is an integer giving the predicted
class.
"""
y_pred = np.zeros(X.shape[0])
###########################################################################
# TODO: #
# Implement this method. Store the predicted labels in y_pred. #
###########################################################################
pass
###########################################################################
# END OF YOUR CODE #
###########################################################################
return y_pred
def 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 N
data 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
"""
pass
class 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)
import numpy as np
from random import shuffle
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 minibatches
of 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 means
that X[i] has label c, where 0 <= c < C.
- reg: (float) regularization strength
Returns a tuple of:
- loss as single float
- gradient with respect to weights W; an array of same shape as W
"""
dW = np.zeros(W.shape) # initialize the gradient as zero
# compute the loss and the gradient
num_classes = W.shape[1]
num_train = X.shape[0]
loss = 0.0
for i in range(num_train):
scores = X[i].dot(W)
correct_class_score = scores[y[i]]
for j in range(num_classes):
if j == y[i]:
continue
margin = scores[j] - correct_class_score + 1 # note delta = 1
if margin > 0:
loss += margin
dW[:,j] += X[i]
dW[:,y[i]] += (-X[i])
# 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.
loss /= num_train
# Add regularization to the loss.
loss += 0.5*reg * np.sum(W * W) #使用L2惩罚 前面乘以0.5,可以约掉对平方求导时产生的2(笔记中没有加)
#############################################################################
# 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. #
#############################################################################
#注意我们一般只惩罚权重参数 之前我们把偏置参数加到了权重参数中 所以统一当作权重处理
#在神经网络中 我们会把他们分开
#可以把W中的权重参数单独拿出来进行惩罚 当然我们统一对W权重+偏置参数进行惩罚也是可以的 对最终结果几乎没有影响
#每个训练样本都会产生一个梯度 求平均梯度
dW /= num_train
dW += reg*W #加上正则化项产生的梯度
return loss, dW
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 = 0.0
dW = np.zeros(W.shape) # 初始化W的梯度
num_classes = W.shape[1] #类别数
num_train = X.shape[0] #训练样本数
scores = X.dot(W) #(N,C) 每行对应一个训练样本的得分向量
correct_class_scores = scores[np.arange(num_train),y].reshape((num_train,1)) #得到每个训练样本正确类别的得分 (N,1)
margins = scores - correct_class_scores + 1 #delta=1 广播 (N,C)
margins[np.arange(num_train),y] = 0
loss = np.sum(margins[margins>0])/num_train #数据损失 各训练样本损失的均值
loss += 0.5*reg*np.sum(W*W) #加上正则化损失
margins[margins>0] = 1 #不满足正确类别得分比不正确>delta 为1
margins[margins<=0] = 0 #满足为0
row_sum = np.sum(margins,axis=1) #计算对于每个样本来说不满足的数量 每行代表一个样本
margins[np.arange(num_train),y] = -row_sum
dW += np.dot(X.T,margins) #(D,C)
#每个训练样本都会产生一个梯度 求平均梯度
dW /= num_train
dW += reg*W #加上正则化项产生的梯度
return loss, dW