lonicera-yx / mgt Goto Github PK

您好，您的代码很优秀，处理数据的想法真的很妙，请问上海地铁刷卡train.pkl是如何处理得到的呢？如果您能回答感激不尽！

代码运行到“HZMetro.py”的146行的“ rest_ind = self.restday.loc[dates].to_numpy().flatten().astype(np.int64) # 0: workday, 1: restday”报错

报错详情如下：
---------- Training ----------
num_samples: 1188, num_batches: 594
0%| | 0/594 [00:00<?, ?it/s]Traceback (most recent call last):
File "F:/orginalCode/MGT-main/main.py", line 236, in
train(args, logger)
File "F:/orginalCode/MGT-main/main.py", line 156, in train
criterion, optimizer, scheduler, args)
File "F:/orginalCode/MGT-main/main.py", line 86, in train_epoch
for batch in tqdm(train_loader):
File "D:\programfiles\Anaconda3\lib\site-packages\tqdm\std.py", line 1107, in iter
for obj in iterable:
File "D:\programfiles\Anaconda3\lib\site-packages\torch\utils\data\dataloader.py", line 435, in next
data = self._next_data()
File "D:\programfiles\Anaconda3\lib\site-packages\torch\utils\data\dataloader.py", line 1085, in _next_data
return self._process_data(data)
File "D:\programfiles\Anaconda3\lib\site-packages\torch\utils\data\dataloader.py", line 1111, in _process_data
data.reraise()
File "D:\programfiles\Anaconda3\lib\site-packages\torch_utils.py", line 428, in reraise
raise self.exc_type(msg)
KeyError: Caught KeyError in DataLoader worker process 0.
Original Traceback (most recent call last):
File "D:\programfiles\Anaconda3\lib\site-packages\torch\utils\data_utils\worker.py", line 198, in _worker_loop
data = fetcher.fetch(index)
File "D:\programfiles\Anaconda3\lib\site-packages\torch\utils\data_utils\fetch.py", line 44, in fetch
data = [self.dataset[idx] for idx in possibly_batched_index]
File "D:\programfiles\Anaconda3\lib\site-packages\torch\utils\data_utils\fetch.py", line 44, in
data = [self.dataset[idx] for idx in possibly_batched_index]
File "F:\orginalCode\MGT-main\datasets\HZMetro.py", line 62, in getitem
inputs_rest = self.rest_transform(self.data['xtime'][item])
File "F:\orginalCode\MGT-main\datasets\HZMetro.py", line 146, in rest_transform
rest_ind = self.restday.loc[dates].to_numpy().flatten().astype(np.int64) # 0: workday, 1: restday
File "D:\programfiles\Anaconda3\lib\site-packages\pandas\core\indexing.py", line 1767, in getitem
return self._getitem_axis(maybe_callable, axis=axis)
File "D:\programfiles\Anaconda3\lib\site-packages\pandas\core\indexing.py", line 1953, in _getitem_axis
return self._getitem_iterable(key, axis=axis)
File "D:\programfiles\Anaconda3\lib\site-packages\pandas\core\indexing.py", line 1594, in _getitem_iterable
keyarr, indexer = self._get_listlike_indexer(key, axis, raise_missing=False)
File "D:\programfiles\Anaconda3\lib\site-packages\pandas\core\indexing.py", line 1552, in _get_listlike_indexer
keyarr, indexer, o._get_axis_number(axis), raise_missing=raise_missing
File "D:\programfiles\Anaconda3\lib\site-packages\pandas\core\indexing.py", line 1639, in _validate_read_indexer
raise KeyError(f"None of [{key}] are in the [{axis_name}]")
KeyError: "None of [Index(['2019-01-02', '2019-01-02', '2019-01-02', '2019-01-02'], dtype='object', name='time')] are in the [index]"

0%| | 0/594 [00:12<?, ?it/s]

Process finished with exit code 1

File "F:/orginalCode/MGT-main/main.py", line 236, in
train(args, logger)
File "F:/orginalCode/MGT-main/main.py", line 132, in train
(train_set, train_loader), (val_set, val_loader) = gen_train_val_data(args)
File "F:/orginalCode/MGT-main/main.py", line 43, in gen_train_val_data
train_set = eval(args.dataset)(args.dataset_model_args['dataset'], split='train')
TypeError: string indices must be integers

请问yaml文件中的num_embeddings变量的取值是什么含义？想替换数据集，但是第一个元素一直调得不对。

MGT.py文件里的第87,88行“inputs_extras_embedding = torch.cat([self.embedding_modulesi
for i in range(len(self.num_embeddings))] + [inputs_pe], dim=-1)”
代码报错，报错详情如下：

---------- Training ----------
num_samples: 1188, num_batches: 594
0%| | 0/594 [00:00<?, ?it/s]Traceback (most recent call last):
File "F:/orginalCode/MGT-main/main.py", line 236, in
train(args, logger)
File "F:/orginalCode/MGT-main/main.py", line 156, in train
criterion, optimizer, scheduler, args)
File "F:/orginalCode/MGT-main/main.py", line 91, in train_epoch
outputs = model(inputs, targets, *extras, **statics)
File "D:\programfiles\Anaconda3\lib\site-packages\torch\nn\modules\module.py", line 727, in _call_impl
result = self.forward(*input, **kwargs)
File "F:\orginalCode\MGT-main\models\MGT.py", line 503, in forward
z_inputs, z_targets = self.temporal_embedding(extras) # (B, P, d_model), (B, Q, d_model)
File "D:\programfiles\Anaconda3\lib\site-packages\torch\nn\modules\module.py", line 727, in _call_impl
result = self.forward(*input, **kwargs)
File "F:\orginalCode\MGT-main\models\MGT.py", line 88, in forward
for i in range(len(self.num_embeddings))] + [inputs_pe], dim=-1)
File "F:\orginalCode\MGT-main\models\MGT.py", line 88, in
for i in range(len(self.num_embeddings))] + [inputs_pe], dim=-1)
File "D:\programfiles\Anaconda3\lib\site-packages\torch\nn\modules\module.py", line 727, in _call_impl
result = self.forward(*input, **kwargs)
File "D:\programfiles\Anaconda3\lib\site-packages\torch\nn\modules\sparse.py", line 126, in forward
self.norm_type, self.scale_grad_by_freq, self.sparse)
File "D:\programfiles\Anaconda3\lib\site-packages\torch\nn\functional.py", line 1852, in embedding
return torch.embedding(weight, input, padding_idx, scale_grad_by_freq, sparse)
TypeError: embedding(): argument 'indices' (position 2) must be Tensor, not list
0%| | 0/594 [00:13<?, ?it/s]

Process finished with exit code 1

怎么才能复现你论文里面的高峰时段预测的代码