Run autoregressive code

[kstudy123]

Hello, I would like to ask how to run the code in autoregressive form. I tried to run it with "--non_autoregressive" removed, and the code does show autoregressive form：
python training/transformer_model_fn.py \ --model_prefix=${POTR_OUT} \ --batch_size=16 \ --data_path=${H36M} \ --learning_rate=0.0001 \ --max_epochs=500 \ --steps_per_epoch=200 \ --loss_fn=l1 \ --model_dim=128 \ --num_encoder_layers=4 \ --num_decoder_layers=4 \ --num_heads=4 \ --dim_ffn=2048 \ --dropout=0.3 \ --lr_step_size=400 \ --learning_rate_fn=step \ --warmup_epochs=100 \ --pose_format=rotmat \ --pose_embedding_type=gcn_enc \ --dataset=h36m_v2 \ --pre_normalization \ --pad_decoder_inputs \ --pos_enc_alpha=10 \ --pos_enc_beta=500 \ --predict_activity \ --action=all

but the following error appears: What should I do please?

Traceback (most recent call last): File "../potr_main/training/transformer_model_fn.py", line 231, in <module> model_fn.train() File "../potr_main/training/../training/seq2seq_model_fn.py", line 308, in train eval_loss = self.evaluate_fn(e, _time)#eval() 这是画表吧 File "/opt/conda/lib/python3.8/site-packages/torch/autograd/grad_mode.py", line 26, in decorate_context return func(*args, **kwargs) File "../potr_main/training/../training/seq2seq_model_fn.py", line 524, in evaluate_h36m decoder_pred = self._model( File "/opt/conda/lib/python3.8/site-packages/torch/nn/modules/module.py", line 727, in _call_impl result = self.forward(*input, **kwargs) File "../potr_main/data/../models/PoseTransformer.py", line 203, in forward return self.forward_autoregressive( File "../potr_main/data/../models/PoseTransformer.py", line 421, in forward_autoregressive pose_code = self._pose_embedding(pred_pose) File "/opt/conda/lib/python3.8/site-packages/torch/nn/modules/module.py", line 727, in _call_impl result = self.forward(*input, **kwargs) File "../potr_main/data/../models/PoseGCN.py", line 350, in forward B, S, D = x.size() ValueError: not enough values to unpack (expected 3, got 2)

[siyu-lii]

I have the same problem as you, can you tell me how you solved it? Thank you very much.