training/models.py [651:686]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        if self.action_input == True:
            if len(input_feats) == 0:
                input_feats = self.action_embed(actions_in)
            else:
                input_feats = torch.cat(
                    [input_feats, self.action_embed(actions_in)], 2)

        packed_input_feats = pack_padded_sequence(
            input_feats, action_lengths, batch_first=True)
        packed_output, hidden = self.rnn(packed_input_feats)
        rnn_output, _ = pad_packed_sequence(packed_output, batch_first=True)
        output = self.decoder(rnn_output.contiguous().view(
            rnn_output.size(0) * rnn_output.size(1), rnn_output.size(2)))

        if self.return_states == True:
            return rnn_output, output, hidden
        else:
            return output, hidden

    def step_forward(self, img_feats, question_feats, actions_in, hidden):
        input_feats = Variable()

        T = False
        if self.image_input == True:
            N, T, _ = img_feats.size()
            input_feats = img_feats

        if self.question_input == True:
            N, D = question_feats.size()
            question_feats = question_feats.view(N, 1, D)
            if T == False:
                T = actions_in.size(1)
            question_feats = question_feats.repeat(1, T, 1)
            if len(input_feats) == 0:
                input_feats = question_feats
            else:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



training/models.py [804:839]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        if self.action_input == True:
            if len(input_feats) == 0:
                input_feats = self.action_embed(actions_in)
            else:
                input_feats = torch.cat(
                    [input_feats, self.action_embed(actions_in)], 2)

        packed_input_feats = pack_padded_sequence(
            input_feats, action_lengths, batch_first=True)
        packed_output, hidden = self.rnn(packed_input_feats)
        rnn_output, _ = pad_packed_sequence(packed_output, batch_first=True)
        output = self.decoder(rnn_output.contiguous().view(
            rnn_output.size(0) * rnn_output.size(1), rnn_output.size(2)))

        if self.return_states == True:
            return rnn_output, output, hidden
        else:
            return output, hidden

    def step_forward(self, img_feats, question_feats, actions_in, hidden):
        input_feats = Variable()

        T = False
        if self.image_input == True:
            N, T, _ = img_feats.size()
            input_feats = img_feats

        if self.question_input == True:
            N, D = question_feats.size()
            question_feats = question_feats.view(N, 1, D)
            if T == False:
                T = actions_in.size(1)
            question_feats = question_feats.repeat(1, T, 1)
            if len(input_feats) == 0:
                input_feats = question_feats
            else:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -