我们从Python开源项目中，提取了以下7个代码示例，用于说明如何使用torch.renorm()。
def test_renorm(self): m1 = torch.randn(10,5) res1 = torch.Tensor() def renorm(matrix, value, dim, max_norm): m1 = matrix.transpose(dim, 0).contiguous() # collapse non-dim dimensions. m2 = m1.clone().resize_(m1.size(0), int(math.floor(m1.nelement() / m1.size(0)))) norms = m2.norm(value, 1) # clip new_norms = norms.clone() new_norms[torch.gt(norms, max_norm)] = max_norm new_norms.div_(norms.add_(1e-7)) # renormalize m1.mul_(new_norms.expand_as(m1)) return m1.transpose(dim, 0) # note that the axis fed to torch.renorm is different (2~=1) maxnorm = m1.norm(2, 1).mean() m2 = renorm(m1, 2, 1, maxnorm) m1.renorm_(2, 1, maxnorm) self.assertEqual(m1, m2, 1e-5) self.assertEqual(m1.norm(2, 0), m2.norm(2, 0), 1e-5) m1 = torch.randn(3, 4, 5) m2 = m1.transpose(1, 2).contiguous().clone().resize_(15, 4) maxnorm = m2.norm(2, 0).mean() m2 = renorm(m2, 2, 1, maxnorm) m1.renorm_(2, 1, maxnorm) m3 = m1.transpose(1, 2).contiguous().clone().resize_(15, 4) self.assertEqual(m3, m2) self.assertEqual(m3.norm(2, 0), m2.norm(2, 0))
def apply(self, model): last_weight = None for name, module in list(model.named_children()): if hasattr(module, 'weight') and ( not module.__class__.__name__.startswith('BatchNorm')): module.weight.data = th.renorm(module.weight.data,2,0,maxnorm=2) last_weight = module.weight if last_weight is not None: last_weight.data = th.renorm(last_weight.data,2,0,maxnorm=0.5)
def test_renorm(self): m1 = torch.randn(10, 5) res1 = torch.Tensor() def renorm(matrix, value, dim, max_norm): m1 = matrix.transpose(dim, 0).contiguous() # collapse non-dim dimensions. m2 = m1.clone().resize_(m1.size(0), int(math.floor(m1.nelement() / m1.size(0)))) norms = m2.norm(value, 1) # clip new_norms = norms.clone() new_norms[torch.gt(norms, max_norm)] = max_norm new_norms.div_(norms.add_(1e-7)) # renormalize m1.mul_(new_norms.expand_as(m1)) return m1.transpose(dim, 0) # note that the axis fed to torch.renorm is different (2~=1) maxnorm = m1.norm(2, 1).mean() m2 = renorm(m1, 2, 1, maxnorm) m1.renorm_(2, 1, maxnorm) self.assertEqual(m1, m2, 1e-5) self.assertEqual(m1.norm(2, 0), m2.norm(2, 0), 1e-5) m1 = torch.randn(3, 4, 5) m2 = m1.transpose(1, 2).contiguous().clone().resize_(15, 4) maxnorm = m2.norm(2, 0).mean() m2 = renorm(m2, 2, 1, maxnorm) m1.renorm_(2, 1, maxnorm) m3 = m1.transpose(1, 2).contiguous().clone().resize_(15, 4) self.assertEqual(m3, m2) self.assertEqual(m3.norm(2, 0), m2.norm(2, 0))
def test_renorm(self): m1 = torch.randn(10, 5) res1 = torch.Tensor() def renorm(matrix, value, dim, max_norm): m1 = matrix.transpose(dim, 0).contiguous() # collapse non-dim dimensions. m2 = m1.clone().resize_(m1.size(0), int(math.floor(m1.nelement() / m1.size(0)))) norms = m2.norm(value, 1, True) # clip new_norms = norms.clone() new_norms[torch.gt(norms, max_norm)] = max_norm new_norms.div_(norms.add_(1e-7)) # renormalize m1.mul_(new_norms.expand_as(m1)) return m1.transpose(dim, 0) # note that the axis fed to torch.renorm is different (2~=1) maxnorm = m1.norm(2, 1).mean() m2 = renorm(m1, 2, 1, maxnorm) m1.renorm_(2, 1, maxnorm) self.assertEqual(m1, m2, 1e-5) self.assertEqual(m1.norm(2, 0), m2.norm(2, 0), 1e-5) m1 = torch.randn(3, 4, 5) m2 = m1.transpose(1, 2).contiguous().clone().resize_(15, 4) maxnorm = m2.norm(2, 0).mean() m2 = renorm(m2, 2, 1, maxnorm) m1.renorm_(2, 1, maxnorm) m3 = m1.transpose(1, 2).contiguous().clone().resize_(15, 4) self.assertEqual(m3, m2) self.assertEqual(m3.norm(2, 0), m2.norm(2, 0))
def __call__(self, module): w = module.weight.data module.weight.data = th.renorm(w, 2, self.axis, self.value)
