Nie możesz wybrać więcej, niż 25 tematów
Tematy muszą się zaczynać od litery lub cyfry, mogą zawierać myślniki ('-') i mogą mieć do 35 znaków.
97 wiersze
3.5 KiB
97 wiersze
3.5 KiB
from builtins import range
|
|
import numpy as np
|
|
from random import shuffle
|
|
from past.builtins import xrange
|
|
|
|
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计算
|
|
dW[:,y[i]] += -X[i] # dW计算
|
|
|
|
# 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 += reg * np.sum(W * W)
|
|
|
|
#############################################################################
|
|
# TODO：
|
|
# 计算损失函数的梯度并将其存储为dW。
|
|
# 与其先计算损失再计算梯度，还不如在计算损失的同时计算梯度更简单。
|
|
# 因此，您可能需要修改上面的一些代码来计算梯度。
|
|
#############################################################################
|
|
# *****START OF YOUR CODE (DO NOT DELETE/MODIFY THIS LINE)*****
|
|
|
|
pass
|
|
|
|
# *****END OF YOUR CODE (DO NOT DELETE/MODIFY THIS LINE)*****
|
|
|
|
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) # initialize the gradient as zero
|
|
|
|
#############################################################################
|
|
# TODO:
|
|
# 实现一个向量化SVM损失计算方法,并将结果存储到loss中
|
|
#############################################################################
|
|
|
|
# *****START OF YOUR CODE (DO NOT DELETE/MODIFY THIS LINE)*****
|
|
|
|
pass
|
|
|
|
# *****END OF YOUR CODE (DO NOT DELETE/MODIFY THIS LINE)*****
|
|
|
|
#############################################################################
|
|
# TODO:
|
|
# 实现一个向量化的梯度计算方法,并将结果存储到dW中
|
|
#
|
|
# 提示:与其从头计算梯度,不如利用一些计算loss时的中间变量
|
|
#############################################################################
|
|
# *****START OF YOUR CODE (DO NOT DELETE/MODIFY THIS LINE)*****
|
|
|
|
pass
|
|
|
|
# *****END OF YOUR CODE (DO NOT DELETE/MODIFY THIS LINE)*****
|
|
|
|
return loss, dW
|