报错场景：
运行torch1.8.0
报错内容：
Args in experiment:
Namespace(activation='gelu', attn='prob', batch_size=32, c_out=1, checkpoints='./checkpoints/', cols=None, d_ff=2048, d_layers=1, d_model=512, data='chicken', data_path='月均价.csv', dec_in=1, des='test', detail_freq='m', devices='0,1,2,3', distil=True, do_predict=True, dropout=0.1, e_layers=2, embed='timeF', enc_in=1, factor=5, features='S', freq='m', gpu=0, inverse=True, itr=100, label_len=6, learning_rate=0.0001, loss='mse', lradj='type1', mix=True, model='informer', n_heads=8, num_workers=0, output='./output', output_attention=False, padding=0, patience=5, pred_len=1, random_choos=True, root_path='./data/chicken/', s_layers=[3, 2, 1], seed=12345, seq_len=12, target='price', train_epochs=100, use_amp=False, use_gpu=True, use_multi_gpu=False)
提示：由于未来还没有发生，在真实值数据中没有这个月份数据，故而无法画出未来预测值~未来值的对比图!
Program to continue！>>>
Use GPU: cuda:0
>>>>>>>start training : informer_chicken_ftS_sl12_ll6_pl1_dm512_nh8_el2_dl1_df2048_atprob_fc5_ebtimeF_dtTrue_mxTrue_test_0 >>>>>>>>>>>>>>>>>>>>>>>>>>
train 104
val 18
test 33
Traceback (most recent call last):
File "main_informer.py", line 289, in <module>
model,info_dict,all_epoch_train_loss,all_epoch_vali_loss,all_epoch_test_loss,epoch_count = exp.train(setting,info_dict,run_name_dir_ckp,run_ex_dir)
File "/home/mw/project/exp/exp_informer.py", line 240, in train
pred, true = self._process_one_batch(train_data, batch_x, batch_y, batch_x_mark, batch_y_mark)
File "/home/mw/project/exp/exp_informer.py", line 498, in _process_one_batch
outputs = self.model(batch_x, batch_x_mark, dec_inp, batch_y_mark)
File "/opt/conda/lib/python3.8/site-packages/torch/nn/modules/module.py", line 889, in _call_impl
result = self.forward(*input, **kwargs)
File "/home/mw/project/models/model.py", line 69, in forward
enc_out = self.enc_embedding(x_enc, x_mark_enc)
File "/opt/conda/lib/python3.8/site-packages/torch/nn/modules/module.py", line 889, in _call_impl
result = self.forward(*input, **kwargs)
File "/home/mw/project/models/embed.py", line 107, in forward
x = self.value_embedding(x) + self.position_embedding(x) + self.temporal_embedding(x_mark)
File "/opt/conda/lib/python3.8/site-packages/torch/nn/modules/module.py", line 889, in _call_impl
result = self.forward(*input, **kwargs)
File "/home/mw/project/models/embed.py", line 37, in forward
x = self.tokenConv(x.permute(0, 2, 1)).transpose(1,2)
File "/opt/conda/lib/python3.8/site-packages/torch/nn/modules/module.py", line 889, in _call_impl
result = self.forward(*input, **kwargs)
File "/opt/conda/lib/python3.8/site-packages/torch/nn/modules/conv.py", line 263, in forward
return self._conv_forward(input, self.weight, self.bias)
File "/opt/conda/lib/python3.8/site-packages/torch/nn/modules/conv.py", line 256, in _conv_forward
return F.conv1d(F.pad(input, self._reversed_padding_repeated_twice, mode=self.padding_mode),
RuntimeError: cuDNN error: CUDNN_STATUS_NOT_INITIALIZED
