test model and get error about temporal-adaptive-module HOT 2 CLOSED

Thanks for your attention. The code and pretrained models are only tested on PyTorch1.1. Thus it may encounter some errors when running with pytorch of higher version due to the incompatibility. As your problem, I advise you to use MMAction2 ^_^.

from temporal-adaptive-module.

Hi I think here the error is that for higher pytorch version, you need to decorate the forward and backward function of the torch.autograd.Function as @staticmethod.
But my question, why do we need a torch.autograd.Function as the SegmentConsensus function here? can't we just simply implment this as a normal torch.nn.Module as in the following?

class ConsensusModule(torch.nn.Module):  # contains no parameters 

    def __init__(self, consensus_type, dim=1):
        super(ConsensusModule, self).__init__()
        self.consensus_type = consensus_type if consensus_type != 'rnn' else 'identity'
        self.dim = dim
        # assert self.dim == 1
    def forward(self, input): #  input_tensor (bz, T, n_class)
        if self.consensus_type == 'avg':
            return input.mean(dim=self.dim, keepdim=True)
        elif self.consensus_type == 'identity':
            return input

from temporal-adaptive-module.