def test_curricularface_inference_mode():
_check_layer(CurricularFace(5, 10, s=1.31, m=0.5))
def test_curricularface_with_cross_entropy_loss():
emb_size = 4
n_classes = 3
s = 3.0
m = 0.1
# fmt: off
features = np.array(
[
[1, 2, 3, 4],
[5, 6, 7, 8],
],
dtype="f",
)
target = np.array([0, 2], dtype="l")
mask = np.array([[1, 0, 0], [0, 0, 1]], dtype="l") # one_hot(target)
weight = np.array(
[
[0.1, 0.2, 0.3, 0.4],
[1.1, 3.2, 5.3, 0.4],
[0.1, 0.2, 6.3, 0.4],
],
dtype="f",
)
# fmt: on
layer = CurricularFace(emb_size, n_classes, s, m)
layer.weight.data = torch.from_numpy(weight.T)
loss_fn = nn.CrossEntropyLoss(reduction="none")
normalized_features = normalize(features) # 2x4
normalized_projection = normalize(weight) # 3x4
cosine = normalized_features @ normalized_projection.T # 2x4 * 4x3 = 2x3
logit = cosine[mask.astype(np.bool)].reshape(-1, 1)
sine = np.sqrt(1.0 - np.power(logit, 2))
cos_theta_m = logit * np.cos(m) - sine * np.sin(m)
final_logit = np.where(logit > np.cos(np.pi - m), cos_theta_m,
logit - np.sin(np.pi - m) * m)
cos_mask = cosine > cos_theta_m
hard = cosine[cos_mask]
t = np.mean(logit) * 0.01 - (1 - 0.01) * 0
cosine[cos_mask] = hard * (t + hard) # 2x3
for r, c in enumerate(target):
cosine[r, c] = final_logit[r, 0]
cosine = cosine * s # 2x3
expected_loss = cross_entropy(cosine, mask, 1)
actual = (loss_fn(
layer(torch.from_numpy(features), torch.LongTensor(target)),
torch.LongTensor(target),
).detach().numpy())
assert np.allclose(expected_loss, actual, atol=EPS)
# reinitialize layer (t is changed)
layer = CurricularFace(emb_size, n_classes, s, m)
layer.weight.data = torch.from_numpy(weight.T)
loss_fn = nn.CrossEntropyLoss(reduction="mean")
expected_loss = cross_entropy(cosine, mask, 1)
actual = (loss_fn(
layer(torch.from_numpy(features), torch.LongTensor(target)),
torch.LongTensor(target),
).detach().numpy())
assert np.isclose(expected_loss.mean(), actual, atol=EPS)
# reinitialize layer (t is changed)
layer = CurricularFace(emb_size, n_classes, s, m)
layer.weight.data = torch.from_numpy(weight.T)
loss_fn = nn.CrossEntropyLoss(reduction="sum")
expected_loss = cross_entropy(cosine, mask, 1)
actual = (loss_fn(
layer(torch.from_numpy(features), torch.LongTensor(target)),
torch.LongTensor(target),
).detach().numpy())
assert np.isclose(expected_loss.sum(), actual, atol=EPS)