def fun(x, y):
x_1, x_2 = split(x, y, labels)
max_1, _ = (x_1 + alpha).topk(k, dim=1)
max_1 = max_1.mean(1)
max_2, _ = x_1.topk(k - 1, dim=1)
max_2 = (max_2.sum(1) + x_2) / k
loss = torch.clamp(max_1 - max_2, min=0)
return loss
def fun(x, y):
x_1, x_2 = split(x, y, labels)
# all scores are divided by (k * tau)
x_1.div_(k * tau)
x_2.div_(k * tau)
# term 1: all terms that will *not* include the ground truth score
# term 2: all terms that will include the ground truth score
res = lsp(x_1)
term_1, term_2 = res[1], res[0]
term_1, term_2 = LogTensor(term_1), LogTensor(term_2)
X_2 = LogTensor(x_2)
cst = x_2.data.new(1).fill_(float(alpha) / tau)
One_by_tau = LogTensor(ag.Variable(cst, requires_grad=False))
Loss_ = term_2 * X_2
loss_pos = (term_1 * One_by_tau + Loss_).torch()
loss_neg = Loss_.torch()
loss = tau * (loss_pos - loss_neg)
return loss
print('Cuda: \t\t{}'.format(CUDA))
print('n_trials: \t\t{}'.format(n_trials))
print('-' * 70)
torch.manual_seed(1234)
scores = Variable(torch.randn(batch_size, n_classes))
target = torch.from_numpy(np.random.randint(n_classes, size=batch_size))
labels = torch.from_numpy(np.arange(n_classes))
if CUDA:
target = target.cuda()
labels = labels.cuda()
scores = scores.cuda()
x_1, x_2 = split(scores, Variable(target), labels)
x_1.div_(k * tau)
x_2.div_(k * tau)
def timing_fun(fun, x, k, verbosity, double=False, n_trials=50,
forward=1, use_buffer=False):
times = []
for _ in range(n_trials):
if double:
x = x.double()
x = Variable(x.data.clone(), requires_grad=not forward)
if use_buffer:
buffer = x.data.new(x.size(0), x.size(1), k + 1)
if CUDA:
torch.cuda.synchronize()