【cs231n】Lecture 2 : Image Classification pipeline 图像分类管道

Assignment 1

• K - Nearest Neighbor (k - 最近邻分类器)
• Linear classifiers (线性分类器) ：SVM，Softmax
• Two - layer neural network (两层神经网络)
• Image Features (图像特征)

Ⅰ. Image Classification : A core task in Computer Vision

• The problem : Semantic Gap (语义鸿沟)
• Challenges : Viewpoint variation (视角变化)
• Challenges : Occlusion (包藏)
• Challenges: Background Clutter (背景混乱)

Ⅱ. Data-driven Approach (数据驱动方法)

1. Collect a dataset of images and labels
2. Use Machine Learning to train a classifier
3. Evaluate the classifier on new images

def train(images, labels):
	# Machine Learning!
	return model;

def predict(images, labels):
	# Use model to predict labels
	return test_labels;

First classifier : Nearest Neighbor (近邻分类器)

The function is usually used to memorize all data and labels

def train(images, labels):
	# Machine Learning!
	return model;

The function is usually used to predict the label of the most similar training image

def predict(images, labels):
	# Use model to predict labels
	return test_labels;

Example Dateset : CIFAR10

• 10 classes
• 50,000 training images
• 10,000 testing images

Distance Metric to compare images

$$L1distance:d1(I1,I2)=\sum _P\left|I_1^P-I_2^P\right|$$

Nearest Neighbor Classifier

import numpy as np

class NearestNeighbor:
	def __init__(self):
		pass

	def train(self, X, Y):
	""" X is N * D where each row is an example. Y is 1-dimension of size N """
	# the nearest neighbor classifier simply remembers all the training data
	self.Xtr = X
	self.ytr = y

	def predict(self, X):
	""" X is N * D where each row is an example we wish to predict label for """
	num_test = X.shape[0]
	# lets make sure that the output type matches the input type
	Y_pred = np.zeros(num_test, dtype = self.ytr.dtype)

	# loop over all test rows
	for i in xrange(num_test):
		# find the nearest training image to the i'th test image
		# using the L1 distance (sum of absolute value differences)
		distances = np.sum(np.abs(self.Xtr - X[i,:]), axis = 1)
		# get the index with smallest distance
		min_index = np.argmin(distances)
		# predict the label of the nearest example
		Ypred[i] = self.ytr[min_index]
		
	return Ypred

Q & A :
Q: How fast are training and prediction?
A: Train O(1) Predict O(N)
This is bad. Because we want to classifier that are fast at prediction; and slow for training is ok

K-Nearest Neighbor Classifier

K-Nearest Neighbors ：Distance Metric (距离度量标准)

Hyperparameters

Setting Hyperpararmeters

Summary