return W1, b1, W2, b2
def calc_class(X):
y = fcann2_classify(X, W1, b1, W2, b2)
return np.argmax(y, axis=1) * np.max(y, axis=1)
if __name__ == "__main__":
np.random.seed(100)
# get the training dataset
X, Y_ = data.sample_gmm_2d(6, 2, 10)
# train the model
W1, b1, W2, b2 = fcann2_train(X, data.class_to_onehot(Y_), 6)
# evaluate the model on the training dataset
probs = fcann2_classify(X, W1, b1, W2, b2)
Y = np.argmax(probs, axis=1)
# report performance
accuracy, recall, precision = data.eval_perf_multi(Y, Y_)
AP = data.eval_AP(Y_)
print(accuracy, recall, precision, AP)
# graph the decision surface
rect = (np.min(X, axis=0), np.max(X, axis=0))
data.graph_surface(calc_class, rect, offset=0.5)
# graph the data points
data.graph_data(X, Y_, Y, special=[])
return self.session.run(self.probs, feed_dict={self.X: X})
def calc_class(X):
y = tflr.eval(X)
return np.argmax(y, axis=1) * np.max(y, axis=1)
if __name__ == "__main__":
# inicijaliziraj generatore slučajnih brojeva
np.random.seed(100)
tf.set_random_seed(100)
# instanciraj podatke X i labele Yoh_
X, Y_ = data.sample_gmm_2d(6, 2, 10)
Yoh_ = data.class_to_onehot(Y_)
# izgradi graf:
tflr = TFLogreg(X.shape[1], Yoh_.shape[1], 0.06, 1)
# nauči parametre:
tflr.train(X, Yoh_, 1000)
# dohvati vjerojatnosti na skupu za učenje
probs = tflr.eval(X)
Y = np.argmax(probs, axis=1)
# ispiši performansu (preciznost i odziv po razredima)
accuracy, recall, precision = data.eval_perf_multi(Y, Y_)
AP = data.eval_AP(Y_)
print(accuracy, recall, precision, AP)
(2 * np.linalg.norm(w))) * 2 * w # D x 1
grad_b = (1 / N) * np.sum(dL_dscores) # 1 x 1
# poboljšani parametri
w += -param_delta * grad_w
b += -param_delta * grad_b
return w, b
if __name__ == "__main__":
np.random.seed(100)
# get the training dataset
X, Y_ = data.sample_gauss(2, 100)
# train the model
w, b = binlogreg_train(X, data.class_to_onehot(Y_))
# evaluate the model on the training dataset
probs = binlogreg_classify(X, w, b)
Y = probs > 0.5
# report performance
accuracy, recall, precision = data.eval_perf_binary(Y[:, -1], Y_)
AP = data.eval_AP(Y_)
print(accuracy, recall, precision, AP)
# graph the decision surface
rect = (np.min(X, axis=0), np.max(X, axis=0))
data.graph_surface(lambda x: binlogreg_classify(x, w, b), rect, offset=0.5)
# graph the data points
data.graph_data(X, Y_, Y[:, -1], special=[])
