libcity.executor.traj_loc_pred_executor¶

class libcity.executor.traj_loc_pred_executor.TrajLocPredExecutor(config, model, data_feature)[source]¶

Bases: libcity.executor.abstract_executor.AbstractExecutor

_build_optimizer()[source]¶: 根据全局参数`learner`选择optimizer

_build_scheduler()[source]¶: 目前就固定的 scheduler 吧

evaluate(test_dataloader)[source]¶

use model to test data

Parameters: test_dataloader (torch.Dataloader) – Dataloader

load_model(cache_name)[source]¶

加载对应模型的 cache

Parameters: cache_name (str) – 保存的文件名

run(data_loader, model, lr, clip)[source]¶

save_model(cache_name)[source]¶

将当前的模型保存到文件

Parameters: cache_name (str) – 保存的文件名

train(train_dataloader, eval_dataloader)[source]¶

use data to train model with config

Parameters

train_dataloader (torch.Dataloader) – Dataloader
eval_dataloader (torch.Dataloader) – Dataloader