def test_svm():
traindataloc, testdataloc = "../data/train.txt", "../data/test.txt"
train_data, train_label = load_features(traindataloc)
test_data, test_label = load_features(testdataloc)
svm_with_diff_c(train_label.tolist(), train_data.tolist(),
test_label.tolist(), test_data.tolist())
'''svm_with_diff_kernel(train_label.tolist(), train_data.tolist(),
def train(self, X, Y):
# Use ten 20 feature classifiers
F, D, n, i = [
1,
], [
1,
], [
5,
], 0
features = load_features(self.feature_type)
X_train, Y_train, X_dev, Y_dev = self.split(X, Y)
PX, PY, NX, NY = self.get_positive_negative_set(X_train, Y_train)
# Integrate PX and NX
PX, NX = IntegralImage(PX), IntegralImage(NX)
X_dev = IntegralImage(X_dev)
c_list = []
y_pred = [
1,
]
while F[i] > self.F_thresh and sum(y_pred) != 0:
i += 1
n.append(n[i - 1])
D.append(0)
F.append(F[i - 1])
inc = 10
while F[i] > self.f * F[i - 1] and F[i] > self.F_thresh:
n[i] += inc
# Use P and N to train classifier
print("Training on", PX.ii.shape[0], "positive examples and",
NX.ii.shape[0], "negative examples.")
X_train = IntegralImage.from_array(
np.concatenate((PX.ii, NX.ii)))
Y_train = np.concatenate((PY, NY))
weak_classifiers, alphas = self.boosting_algorithm.boost(
X_train,
Y_train,
self.select_features(features, stage=i, num=n[i]),
iter=self.T)
threshold = sum(alphas) / 2.0
step = threshold / 100.0
D[i] = 0
# Evaluate current cascaded classifier on validation set to determine Fi and Di.
# Loop until Di < d * D[i-1]. Decrease threshold by 1 everytime until detection rate is greater
while D[i] < self.d * D[i - 1]:
c = StrongClassifier(weak_classifiers, alphas, threshold)
TP, FP, TN, FN = self.evaluate(c_list + [
c,
], X_dev, Y_dev)
F[i] = FP / float(FP + TN)
D[i] = TP / float(FN + TP)
if self.verbose:
print("F", F[i], "D", D[i])
if D[i] < self.d * D[i - 1]:
# Decrement threshold by one step
threshold -= step
inc += 2
y_pred = c.predict(NX)
NX.ii = NX.ii[y_pred == 1]
NY = NY[y_pred == 1]
c_list.append(c)
# Print results
if self.verbose:
print("Detection Rates:", D)
print("False Positive Rates:", F)
print("Number of Features per Cascade", n[1:5])
self.classifiers = c_list