libcity.model.trajectory_loc_prediction.ATSTLSTM

class libcity.model.trajectory_loc_prediction.ATSTLSTM.ATSTLSTM(config, data_feature)

基类：libcity.model.abstract_model.AbstractModel

ATST_LSTM 轨迹下一跳预测模型.

calculate_loss(batch)

计算模型损失（不包含正则项） :param batch: 输入 :type batch: libcity.data.batch

返回

shape () 损失

返回类型

(torch.tensor.Tensor)

forward(batch)

Defines the computation performed at every call.

Should be overridden by all subclasses.

注解

Although the recipe for forward pass needs to be defined within this function, one should call the Module instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.

predict(batch)

参数

batch (Batch) – a batch of input

返回

predict result of this batch

返回类型

torch.tensor

training: bool

class libcity.model.trajectory_loc_prediction.ATSTLSTM.Attn(hidden_size)

基类：torch.nn.modules.module.Module

Attention 注意力机制模块, 对 LSTM 中间层输出做加权平均.

forward(x)

前向传播. :param x: shape (batch, seq_len, hidden_size) 中间层输出序列 :type x: torch.tensor.Tensor

返回

shape (batch, size)

返回类型

(torch.tensor.Tensor)

training: bool