experiment in traffic.csv

[Gzlzero]

thanks for you code!I met any problems,when I train the traffic.csv on your model. How to deal with this.

D:\Anaconda3\envs\pytorch\python.exe F:\pythonProject\pathformer-main\run.py
Args in experiment:
Namespace(is_training=1, model='PathFormer', model_id='traffic.sh', data='custom', root_path='./dataset/traffic', data_path='traffic.csv', features='M', target='OT', freq='h', checkpoints='./checkpoints/', seq_len=96, pred_len=96, individual=False, d_model=16, d_ff=64, num_nodes=21, layer_nums=3, k=2, num_experts_list=[4, 4, 4], patch_size_list=[[16, 12, 8, 32], [12, 8, 6, 4], [8, 6, 4, 2]], do_predict=False, revin=1, drop=0.1, embed='timeF', residual_connection=0, metric='mae', num_workers=10, itr=1, train_epochs=20, batch_size=1, patience=5, learning_rate=0.001, lradj='TST', use_amp=False, pct_start=0.4, use_gpu=True, gpu=0, use_multi_gpu=False, devices='2', test_flop=False)
Use GPU: cuda:0

start training : traffic.sh_PathFormer_fttraffic_slM_pl96_96>>>>>>>>>>>>>>>>>>>>>>>>>>
train 12089
val 1661
test 3413
Traceback (most recent call last):
File "F:\pythonProject\pathformer-main\run.py", line 108, in
exp.train(setting)
File "F:\pythonProject\pathformer-main\exp\exp_main.py", line 146, in train
outputs, balance_loss = self.model(batch_x)
^^^^^^^^^^^^^^^^^^^
File "D:\Anaconda3\envs\pytorch\Lib\site-packages\torch\nn\modules\module.py", line 1511, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\Anaconda3\envs\pytorch\Lib\site-packages\torch\nn\modules\module.py", line 1520, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "F:\pythonProject\pathformer-main\models\PathFormer.py", line 56, in forward
out, aux_loss = layer(out)
^^^^^^^^^^
File "D:\Anaconda3\envs\pytorch\Lib\site-packages\torch\nn\modules\module.py", line 1511, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\Anaconda3\envs\pytorch\Lib\site-packages\torch\nn\modules\module.py", line 1520, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "F:\pythonProject\pathformer-main\layers\AMS.py", line 104, in forward
gates, load = self.noisy_top_k_gating(new_x, self.training)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "F:\pythonProject\pathformer-main\layers\AMS.py", line 74, in noisy_top_k_gating
x = self.start_linear(x).squeeze(-1)
^^^^^^^^^^^^^^^^^^^^
File "D:\Anaconda3\envs\pytorch\Lib\site-packages\torch\nn\modules\module.py", line 1511, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\Anaconda3\envs\pytorch\Lib\site-packages\torch\nn\modules\module.py", line 1520, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\Anaconda3\envs\pytorch\Lib\site-packages\torch\nn\modules\linear.py", line 116, in forward
return F.linear(input, self.weight, self.bias)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
RuntimeError: mat1 and mat2 shapes cannot be multiplied (96x862 and 21x1)

[PengChen12]

You should set num_nodes to the number of traffic dataset variables 862