Question about amsoftmax.

[tfygg]

`class ArcMarginProduct(nn.Module):
def init(self, in_feature=128, out_feature=10575, s=32.0, m=0.50, easy_margin=False):
super(ArcMarginProduct, self).init()
self.in_feature = in_feature
self.out_feature = out_feature
self.s = s
self.m = m
self.weight = Parameter(torch.Tensor(out_feature, in_feature))
nn.init.xavier_uniform_(self.weight)

    self.easy_margin = easy_margin
    self.cos_m = math.cos(m)
    self.sin_m = math.sin(m)

    # make the function cos(theta+m) monotonic decreasing while theta in [0°,180°]
    self.th = math.cos(math.pi - m)
    self.mm = math.sin(math.pi - m) * m

def forward(self, x, label):
    # cos(theta)
    cosine = F.linear(F.normalize(x), F.normalize(self.weight))
    # cos(theta + m)
    sine = torch.sqrt(1.0 - torch.pow(cosine, 2))
    phi = cosine * self.cos_m - sine * self.sin_m

    if self.easy_margin:
        phi = torch.where(cosine > 0, phi, cosine)
    else:
        phi = torch.where((cosine - self.th) > 0, phi, cosine - self.mm)

    #one_hot = torch.zeros(cosine.size(), device='cuda' if torch.cuda.is_available() else 'cpu')
    one_hot = torch.zeros_like(cosine)
    one_hot.scatter_(1, label.view(-1, 1), 1)
    output = (one_hot * phi) + ((1.0 - one_hot) * cosine)
    output = output * self.s

    return output`

This is the implementation of amsoftmax, but in your code, cos_theta is equal to output without normalization.

[kprokofi]

This function takes cosine from the last layer of the model. See class AngleSimpleLinear.