Skip to content

Navigation Menu

Sign in
Appearance settings

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly
Sign up
Appearance settings
This repository was archived by the owner on May 13, 2023. It is now read-only.

Commit 00958f1

Browse files
first commit
0 parents commit 00958f1

18 files changed

+1206
-0
lines changed

‎Assignment2.ipynb

Lines changed: 908 additions & 0 deletions
Large diffs are not rendered by default.

‎__init__.py

Lines changed: 3 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,3 @@
1+
from svm_loss import svm_loss
2+
from svm_gradient import svm_gradient
3+
from svm_solver import svm_solver

‎__pycache__/__init__.cpython-36.pyc

319 Bytes
Binary file not shown.

‎__pycache__/svm_gradient.cpython-36.pyc

1.32 KB
Binary file not shown.

‎__pycache__/svm_loss.cpython-36.pyc

1.15 KB
Binary file not shown.

‎__pycache__/svm_solver.cpython-36.pyc

1.32 KB
Binary file not shown.

‎assignment2/.DS_Store

6 KB
Binary file not shown.

‎assignment2/__init__.py

Lines changed: 3 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,3 @@
1+
from svm_loss import svm_loss
2+
from svm_gradient import svm_gradient
3+
from svm_solver import svm_solver
319 Bytes
Binary file not shown.

‎assignment2/svm_gradient.py

Lines changed: 36 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,36 @@
1+
import numpy as np
2+
3+
4+
def svm_gradient(w, b, x, y, C):
5+
"""
6+
Compute gradient for SVM w.r.t. to the parameters w and b on a mini-batch (x, y)
7+
8+
Args:
9+
w: Parameters of shape [num_features]
10+
b: Bias (a scalar)
11+
x: A mini-batch of training example [k, num_features]
12+
y: Labels corresponding to x of size [k]
13+
14+
Returns:
15+
grad_w: The gradient of the SVM objective w.r.t. w of shape [k, num_features]
16+
grad_v: The gradient of the SVM objective w.r.t. b of shape [k, 1]
17+
18+
"""
19+
20+
grad_w = 0
21+
grad_b = 0
22+
23+
24+
#######################################################################
25+
# TODO: #
26+
# Compute the gradient for a particular choice of w and b. #
27+
# Compute the partial derivatives and set grad_w and grad_b to the #
28+
# partial derivatives of the cost w.r.t. both parameters #
29+
# #
30+
#######################################################################
31+
32+
33+
#######################################################################
34+
# END OF YOUR CODE #
35+
#######################################################################
36+
return grad_w, grad_b

0 commit comments

Comments
(0)

AltStyle によって変換されたページ (->オリジナル) /