torch.zeros(M, S, M), ), ), ('embedding', torch.tensor([[1, 2, 4, 5], [4, 3, 2, 5]]), (torch.rand(6, 3), ), '', (True, )), ( 'embedding_bag', torch.tensor([1, 2, 4, 2]), ( torch.rand(5, 3), torch.tensor([0, 4]), ), ), ('batch_norm', (S, S), ( non_differentiable(torch.randn(S)), non_differentiable(torch.ones(S)), ), '', (False, 'aten::_batch_norm_impl_index')), ( 'instance_norm', (S, S, S), (non_differentiable(torch.zeros(S)), non_differentiable(torch.ones(S))), ), ('layer_norm', (S, S, S, S), ([5], ), '', (False, ['aten::contiguous', 'aten::_batch_norm_impl_index'])), ('layer_norm', (S, S, S, S), ( [5], non_differentiable(torch.rand(S)), ), 'with_only_weight', (False, ['aten::contiguous', 'aten::_batch_norm_impl_index'])),
('hardshrink', (S, S, S), (0.4,),), ('tanhshrink', (S, S, S), (),), ('softsign', (S, S, S), (),), ('softplus', (S, S, S), (),), ('softmin', (S, S, S), (0,),), ('softmax', (S, S, S), (0,), '', (True,)), ('softmax', (S, S, S), (0, 3, torch.double), 'with_all_args', (True,)), ('tanh', (S, S, S), (), '', (True,)), ('sigmoid', (S, S, S), (), '', (True,)), ('log_softmax', (S, S, S), (0,), '', (True,)), ('linear', (S, S), ((M, S),), '', (True, ['aten::t', 'aten::matmul'])), ('linear', (S, S), ((M, S), (M,)), 'addmm', (True, ['aten::add', 'aten::mm'])), ('bilinear', (S, S, S), ((S, S, M), torch.zeros(M, S, M),),), ('embedding', torch.tensor([[1, 2, 4, 5], [4, 3, 2, 5]]), (torch.rand(6, 3), ), '', (True,)), ('embedding_bag', torch.tensor([1, 2, 4, 2]), (torch.rand(5, 3), torch.tensor([0, 4]),),), ('batch_norm', (S, S), (non_differentiable(torch.randn(S)), non_differentiable(torch.ones(S)), ), '', (False, 'aten::_batch_norm_impl_index')), ('instance_norm', (S, S, S), (non_differentiable(torch.zeros(S)), non_differentiable(torch.ones(S))),), ('layer_norm', (S, S, S, S), ([5],), '', (False, ['aten::contiguous', 'aten::_batch_norm_impl_index'])), ('layer_norm', (S, S, S, S), ([5], non_differentiable(torch.rand(S)),), 'with_only_weight', (False, ['aten::contiguous', 'aten::_batch_norm_impl_index'])), ('layer_norm', (S, S, S, S), ([5], None, non_differentiable(torch.rand(S)),), 'with_only_bias', (False, ['aten::contiguous', 'aten::_batch_norm_impl_index'])), ('layer_norm', (S, S, S, S), ([5], non_differentiable(torch.rand(S)), non_differentiable(torch.rand(S))), 'with_weight_and_bias', (False, ['aten::contiguous', 'aten::_batch_norm_impl_index', 'aten::addcmul'])), ('group_norm', (S, S, S), (1, torch.rand(5),),), ('local_response_norm', (S, S, S), (2, ),), ('nll_loss', F.log_softmax(torch.randn(3, 5), dim=0), (torch.tensor([1, 0, 4]),), '', (True, 'aten::nll_loss_forward')), ('poisson_nll_loss', torch.rand(S, 2), (torch.rand(S, 2),),),