def test_apply_once(self):
x = np.arange(3 * 4 * 5).reshape((3, 4, 5))
np.testing.assert_array_almost_equal(dd.apply_once(np.std, x, [0, -1]),
16.39105447 * np.ones((1, 4, 1)))
x = np.arange(2 * 3).reshape((2, 3))
np.testing.assert_array_equal(
dd.apply_once(np.sum, x, 1, keepdims=False), np.array([3, 12]))
def test_apply_once(self):
x = np.arange(3 * 4 * 5).reshape((3, 4, 5))
np.testing.assert_array_almost_equal(dd.apply_once(np.std, x, [0, -1]),
16.39105447 * np.ones((1, 4, 1)))
x = np.arange(2 * 3).reshape((2, 3))
np.testing.assert_array_equal(dd.apply_once(np.sum, x, 1, keepdims=False),
np.array([3, 12]))
def predict_proba(self, X):
X = X.reshape(-1, 3, 32, 32)
#X = X.transpose(0, 2, 3, 1)
prob = np.zeros((X.shape[0], self.n_classes_))
M = 2500
for k in range(int(np.ceil(X.shape[0] / M))):
y = self.net_.forward_all(data=X[k * M:(k + 1) *
M]).values()[0].squeeze(axis=(2,
3))
prob[k * M:(k + 1) * M] = y
T = 30.0
eps = 0.0001
#prob = prob.clip(eps, 1-eps)
log_prob = np.log(prob)
print('log_prob', log_prob.min(), log_prob.max())
#log_prob = log_prob.clip(min=-4, max=4)
new_prob = np.exp(log_prob / T)
new_prob /= dd.apply_once(np.sum, new_prob, [1])
return new_prob
def predict_proba(self, X):
X = X.reshape(-1, 3, 32, 32)
# X = X.transpose(0, 2, 3, 1)
prob = np.zeros((X.shape[0], self.n_classes_))
M = 2500
for k in range(int(np.ceil(X.shape[0] / M))):
y = self.net_.forward_all(data=X[k * M : (k + 1) * M]).values()[0].squeeze(axis=(2, 3))
prob[k * M : (k + 1) * M] = y
T = 30.0
eps = 0.0001
# prob = prob.clip(eps, 1-eps)
log_prob = np.log(prob)
print("log_prob", log_prob.min(), log_prob.max())
# log_prob = log_prob.clip(min=-4, max=4)
new_prob = np.exp(log_prob / T)
new_prob /= dd.apply_once(np.sum, new_prob, [1])
return new_prob
def temperature(y, T):
y = y**(1 / T)
return y / dd.apply_once(np.sum, y, [1])
def temperature(y, T):
y = y**(1 / T)
return y / dd.apply_once(np.sum, y, [1])
