linear_svm.py:
```python
import numpy as np
class LinearSVM:
def __init__(self, lr=0.01, reg=0.01, num_iters=1000, batch_size=32):
self.lr = lr
self.reg = reg
self.num_iters = num_iters
self.batch_size = batch_size
self.W = None
self.b = None
def train(self, X, y):
num_train, dim = X.shape
num_classes = np.max(y) + 1
if self.W is None:
self.W = 0.001 * np.random.randn(dim, num_classes)
self.b = np.zeros((1, num_classes))
loss_history = []
for i in range(self.num_iters):
batch_idx = np.random.choice(num_train, self.batch_size)
X_batch = X[batch_idx]
y_batch = y[batch_idx]
loss, grad_W, grad_b = self.loss(X_batch, y_batch)
loss_history.append(loss)
self.W -= self.lr * grad_W
self.b -= self.lr * grad_b
return loss_history
def predict(self, X):
scores = X.dot(self.W) + self.b
y_pred = np.argmax(scores, axis=1)
return y_pred
def loss(self, X_batch, y_batch):
num_train = X_batch.shape[0]
scores = X_batch.dot(self.W) + self.b
correct_scores = scores[range(num_train), y_batch]
margins = np.maximum(0, scores - correct_scores[:, np.newaxis] + 1)
margins[range(num_train), y_batch] = 0
loss = np.sum(margins) / num_train + 0.5 * self.reg * np.sum(self.W * self.W)
num_pos = np.sum(margins > 0, axis=1)
dscores = np.zeros_like(scores)
dscores[margins > 0] = 1
dscores[range(num_train), y_batch] -= num_pos
dscores /= num_train
grad_W = np.dot(X_batch.T, dscores) + self.reg * self.W
grad_b = np.sum(dscores, axis=0, keepdims=True)
return loss, grad_W, grad_b
```
linear_classifier.py:
```python
import numpy as np
class LinearClassifier:
def __init__(self, lr=0.01, reg=0.01, num_iters=1000, batch_size=32):
self.lr = lr
self.reg = reg
self.num_iters = num_iters
self.batch_size = batch_size
self.W = None
self.b = None
def train(self, X, y):
num_train, dim = X.shape
num_classes = np.max(y) + 1
if self.W is None:
self.W = 0.001 * np.random.randn(dim, num_classes)
self.b = np.zeros((1, num_classes))
loss_history = []
for i in range(self.num_iters):
batch_idx = np.random.choice(num_train, self.batch_size)
X_batch = X[batch_idx]
y_batch = y[batch_idx]
loss, grad_W, grad_b = self.loss(X_batch, y_batch)
loss_history.append(loss)
self.W -= self.lr * grad_W
self.b -= self.lr * grad_b
return loss_history
def predict(self, X):
scores = X.dot(self.W) + self.b
y_pred = np.argmax(scores, axis=1)
return y_pred
def loss(self, X_batch, y_batch):
num_train = X_batch.shape[0]
scores = X_batch.dot(self.W) + self.b
correct_scores = scores[range(num_train), y_batch]
margins = np.maximum(0, scores - correct_scores[:, np.newaxis] + 1)
margins[range(num_train), y_batch] = 0
loss = np.sum(margins) / num_train + 0.5 * self.reg * np.sum(self.W * self.W)
num_pos = np.sum(margins > 0, axis=1)
dscores = np.zeros_like(scores)
dscores[margins > 0] = 1
dscores[range(num_train), y_batch] -= num_pos
dscores /= num_train
grad_W = np.dot(X_batch.T, dscores) + self.reg * self.W
grad_b = np.sum(dscores, axis=0, keepdims=True)
return loss, grad_W, grad_b
```
svm.ipynb:
```python
import numpy as np
import matplotlib.pyplot as plt
from sklearn.datasets import make_blobs, make_moons
from sklearn.model_selection import train_test_split
from linear_classifier import LinearClassifier
def plot_data(X, y, title):
plt.scatter(X[:, 0], X[:, 1], c=y, cmap=plt.cm.RdBu)
plt.title(title)
plt.xlabel('Feature 1')
plt.ylabel('Feature 2')
plt.show()
def plot_decision_boundary(clf, X, y, title):
plt.scatter(X[:, 0], X[:, 1], c=y, cmap=plt.cm.RdBu)
ax = plt.gca()
xlim = ax.get_xlim()
ylim = ax.get_ylim()
xx = np.linspace(xlim[0], xlim[1], 100)
yy = np.linspace(ylim[0], ylim[1], 100)
XX, YY = np.meshgrid(xx, yy)
xy = np.vstack([XX.ravel(), YY.ravel()]).T
Z = clf.predict(xy).reshape(XX.shape)
plt.contour(XX, YY, Z, levels=[0], colors='k', linestyles='-')
plt.title(title)
plt.xlabel('Feature 1')
plt.ylabel('Feature 2')
plt.show()
def main():
X, y = make_blobs(n_samples=200, centers=2, random_state=42)
plot_data(X, y, 'Linearly Separable Data')
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
clf = LinearClassifier()
loss_history = clf.train(X_train, y_train)
train_acc = np.mean(clf.predict(X_train) == y_train)
test_acc = np.mean(clf.predict(X_test) == y_test)
print('Train accuracy: {:.3f}, Test accuracy: {:.3f}'.format(train_acc, test_acc))
plot_decision_boundary(clf, X, y, 'Linear SVM')
if __name__ == '__main__':
main()
```
以上的代码实现了一个简单的线性 SVM，可以用于二分类问题。在 `svm.ipynb` 文件中，我们使用 `make_blobs` 生成了一个线性可分的数据集，然后将其拆分为训练集和测试集。接着，我们使用 `LinearClassifier` 对训练集进行训练，并在测试集上评估模型性能。最后，我们绘制了模型的决策边界。
扫一扫
294
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
