observerspy / cs231n Goto Github PK

View Code? Open in Web Editor NEW

160.0 6.0 54.0 28.33 MB

homework for CS231n 2017

Jupyter Notebook 98.99% Shell 0.02% Python 1.00%

cs231n's Introduction

CS231n

homework for CS231n

cs231n's People

Contributors

Stargazers

Watchers

Forkers

kvnzhao nicehuster123 slidelucask do-oo hw313 xiaomaohoujiao2 fightingforyang siyue0211 jweiiii pythonkerry stevewsw 106378051 happyconan playezio perry7799 havj121 harvestgolem littlecat80 harry771 benyuereal npeight kelly-yt-liao sutluo hotview chenhuang20 alexjjyy kirayuta wangyuzhen1996 ustbxyls xinrouli miaomiao17 chengzhuo1992 guolaoban fantasyjxf yelianjin fw339wj zj1224 njuhaozhang lemonray liulangxing qusongzhixiasha tym2103 silyfox vectorcsw demodante patricwu albertsebastain jiajunlong shirley-cv fzu-lw azzgavin aaaaaaaaaaaly onlyourmiracle

cs231n's Issues

why use different stack function?

Hello,
About assignment1: knn.ipynb
X_tr = np.vstack(X_train_folds[0:j] + X_train_folds[j+1:])
y_tr = np.hstack(y_train_folds[0:j] + y_train_folds[j+1:])

why use differnt stack function?

Thank you.

assignment1/svm_classification

in class LinearClassifier: you define the default shape of X(D, N), and the shape of y_pred will be (N)

it is right.
def predict(self, X):
"""
Use the trained weights of this linear classifier to predict labels for
data points.

Inputs:
- X: D x N array of training data. Each column is a D-dimensional point.

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[1])

but in your assignment1/svm.ipynb:

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), ))

this time the shape of X_train is (N, D), therefor y_pred will be (D, )?

FURTHERMORE:
the next step you do :
y_pred = np.argmax(X.dot(self.W), axis=1)
totally changed the shape of y_pred to (N,)

SO , WHY you add the line:
y_pred = np.zeros(X.shape[1])

thanks a lot ! you code and annotation really illuminated me !

observerspy / cs231n Goto Github PK

cs231n's Introduction

CS231n

cs231n's People

Contributors

Stargazers

Watchers

Forkers

cs231n's Issues

why use different stack function?

assignment1/svm_classification

in class LinearClassifier: you define the default shape of X(D, N), and the shape of y_pred will be (N)

Recommend Projects

React

Vue.js

Typescript

TensorFlow

Django

Laravel

D3

Recommend Topics

javascript

web

server

Machine learning

Visualization

Game

Recommend Org

Facebook

Microsoft

Google

Alibaba

D3

Tencent