def surrogateF1_loss(target, output): # WiP
#https://arxiv.org/pdf/1608.04802.pdf
y_true = K.flatten(target * 2 - 1)
y_pred = K.flatten(output * 2 - 1)
Yp = K.flatten(target)
Yn = 1. - Yp
tpl = K.sum(1. - categorical_hinge(y_true * Yp, y_pred * Yp))
fpu = K.sum(categorical_hinge(y_true * Yn, y_pred * Yn))
# 2 tpl / |Y+| + tpl + fpu
return 2 * tpl / (K.sum(Yp) + tpl + fpu)
def test_categorical_hinge():
y_pred = K.variable(np.array([[0.3, 0.2, 0.1],
[0.1, 0.2, 0.7]]))
y_true = K.variable(np.array([[0, 1, 0],
[1, 0, 0]]))
expected_loss = ((0.3 - 0.2 + 1) + (0.7 - 0.1 + 1)) / 2.0
loss = K.eval(losses.categorical_hinge(y_true, y_pred))
assert np.isclose(expected_loss, np.mean(loss))
def test_categorical_hinge():
y_pred = K.variable(np.array([[0.3, 0.2, 0.1],
[0.1, 0.2, 0.7]]))
y_true = K.variable(np.array([[0, 1, 0],
[1, 0, 0]]))
expected_loss = ((0.3 - 0.2 + 1) + (0.7 - 0.1 + 1)) / 2.0
loss = K.eval(losses.categorical_hinge(y_true, y_pred))
assert np.isclose(expected_loss, np.mean(loss))
def call(self, inputs):
y_pred, y_true = inputs
y_true = K.reshape(y_true, (-1, 8, 80))
y_true = K.max(y_true, axis=1)
return categorical_hinge(y_pred, y_true)
print("PREPAIRING")
ytrain_inds = y_train.argmax(axis=1)
X_batch = X_train[indices]
true_class = ytrain_inds[indices]
grads, scores, weights = weights_grad(X_batch, model)
gstack = np.zeros((num_weights, num_classes * batch_size))
for nn in range(batch_size):
for class_ind in range(num_classes):
gstack[:, [nn * num_classes + class_ind]] = np.vstack([
param.reshape(-1, 1) for param in (grads[3 * nn + class_ind])
])
#print(gstack.shape)
y = scores
keras_l = np.sum(k.eval(categorical_hinge(y_train[indices, :], y)))
#print(y)
#print(y.reshape((-1,1)))
wk = np.vstack([param.reshape(-1, 1) for param in weights])
print("SETTING UP CONVEX PROBLEM")
w = cp.Variable((num_weights, 1))
#yhat = cp.Variable((batch_size,num_classes))
#const = [yhat == y + cp.reshape((gstack.T@(w - wk)),(batch_size,num_classes))]
const = []
yhat = y + cp.reshape((gstack.T @ (w - wk)), (batch_size, num_classes))
#f = cp.sum(-yhat[np.arange(batch_size),true_class] + cp.log_sum_exp(yhat, axis=1)) + cp.norm(w,2)
f = cp.sum(
cp.pos(yhat - yhat[np.arange(batch_size), [true_class]].T @ np.ones(
(1, 3)) + 1)) + 10 * cp.norm(w - wk, 2)
objective = cp.Minimize(f)
