def disambiguate_samples(data, distance):
n_before = data.shape[0]
# it would be better if centroids were calculated without the duplicates
centroids = utils.get_centroids(data[:, :-1], data[:, -1])
to_remove = set()
to_add = []
for i in range(n_before):
if i in to_remove:
continue
ambiguity = False
for j in range(i + 1, n_before):
if sum(abs(data[i, :-1] - data[j, :-1]) > 0) == 0:
ambiguity = True
to_remove.add(i)
to_remove.add(j)
if ambiguity:
dist = np.array([[distance(data[i, :-1], centroids[c]), c]
for c in centroids.keys()])
data[i, -1] = dist[np.argmin(dist[:, 0]), 1]
to_add.append(data[i, :])
data = np.delete(data, list(to_remove), axis=0)
data = np.vstack([data, np.array(to_add)])
if n_before - data.shape[0] > 0:
print('\tRemoved {} ambiguous samples.'.format(n_before -
data.shape[0]))
return data
def forward(self, embeddings):
torch.clamp(self.w, 1e-6)
centroids = get_centroids(embeddings)
cossim = get_cossim(embeddings, centroids)
sim_matrix = self.w * cossim.to(self.device) + self.b
loss, _ = calc_loss(sim_matrix)
return loss
def forward(self, embeddings, y=None):
#pdb.set_trace()
torch.clamp(self.w, 1e-6)
centroids = get_centroids(embeddings)
cossim = get_cossim(embeddings, centroids)
sim_matrix = self.w*cossim + self.b
loss, _ = calc_loss(sim_matrix)
return loss
def forward(self, embeddings):
torch.clamp(self.w, hp.re_num)
centroids = utils.get_centroids(embeddings)
cossim = utils.get_cossim(embeddings, centroids)
sim_matrix = self.w * cossim + self.b
loss, _ = utils.cal_loss(sim_matrix)
return loss
def forward(self, embeddings, embedder_net, lamb):
torch.clamp(self.w, 1e-6)
centroids = get_centroids(embeddings)
cossim = get_cossim(embeddings, centroids)
sim_matrix = self.w * cossim.to(self.device) + self.b
per_loss, _ = calc_loss(sim_matrix)
weights = embedder_net.LSTM_stack.all_weights
norm_loss = lamb * torch.sum(
torch.Tensor([
torch.norm(weights[i][j].data.to(self.device), 2)
for i in range(hp.model.num_layer) for j in range(4)
]))
loss = per_loss + norm_loss
return loss, per_loss, norm_loss
