静态变量的使用

[IgnoranceSmile]

有人使用静态变量并成功运行过么 我的代码如下： import pandas as pd from paddlets import TSDataset

x = np.linspace(-np.pi, np.pi, 200) sinx = np.sin(x) * 4 + np.random.randn(200)

df = pd.DataFrame( { 'time_col': pd.date_range('2022-01-01', periods=200, freq='1h'), 'value': sinx, 'known_cov_1': sinx + 4, 'known_cov_2': sinx + 5, 'observed_cov': sinx + 8, 'static_cov': [1 for i in range(200)], } ) target_cov_dataset = TSDataset.load_from_dataframe( df, time_col='time_col', target_cols='value', known_cov_cols=['known_cov_1', 'known_cov_2'], observed_cov_cols='observed_cov', static_cov_cols='static_cov', freq='1h' )

temporal_fusion_transformer = TFTModel( in_chunk_len = in_chunk_len, out_chunk_len = out_chunk_len, max_epochs=800, patience=100 )

temporal_fusion_transformer.fit(target_cov_dataset) 报错：

ValueError Traceback (most recent call last) /tmp/ipykernel_43360/875506061.py in 32 ) 33 ---> 34 temporal_fusion_transformer.fit(target_cov_dataset)

/usr/local/lib/python3.7/dist-packages/paddlets/models/forecasting/dl/paddle_base_impl.py in fit(self, train_tsdataset, valid_tsdataset) 344 self._check_multi_tsdataset(valid_tsdataset) 345 train_dataloader, valid_dataloaders = self._init_fit_dataloaders(train_tsdataset, valid_tsdataset) --> 346 self._fit(train_dataloader, valid_dataloaders) 347 348 def _fit(

/usr/local/lib/python3.7/dist-packages/paddlets/models/forecasting/dl/paddle_base_impl.py in _fit(self, train_dataloader, valid_dataloaders) 370 # Call the on_epoch_begin method of each callback before the epoch starts. 371 self._callback_container.on_epoch_begin(epoch_idx) --> 372 self._train_epoch(train_dataloader) 373 374 # Predict for each eval set.

/usr/local/lib/python3.7/dist-packages/paddlets/models/forecasting/dl/paddle_base_impl.py in _train_epoch(self, train_loader) 438 self._callback_container.on_batch_begin(batch_idx) 439 X, y = self._prepare_X_y(data) --> 440 batch_logs = self._train_batch(X, y) ... 208 helper = LayerHelper('embedding', **locals())

ValueError: (InvalidArgument) Variable value (input) of OP(fluid.layers.embedding) expected >= 0 and < 1, but got 1. Please check input value. [Hint: Expected ids[i] < row_number, but received ids[i]:1 >= row_number:1.] (at /paddle/paddle/phi/kernels/cpu/embedding_kernel.cc:63) [operator < lookup_table_v2 > error]

[Sunting78]

您好，麻烦提供下具体环境，我们复现跟进。

[IgnoranceSmile]

使用官方最新的Docker运行的 语言名称及版本：Python 3.7.13 依赖库及其版本：paddlepaddle 2.3.2 paddlets 1.1.0

测试后发现静态协变量不能为int类型，修改为float类型后可以正常运行

[Sunting78]

是的，已解决，问题关闭。