convlab2.policy.mle.crosswoz package¶

Submodules¶

convlab2.policy.mle.crosswoz.evaluate module¶

convlab2.policy.mle.crosswoz.evaluate.calculateF1(predict_golden)¶

convlab2.policy.mle.crosswoz.evaluate.da_evaluate_simulation(policy)¶

convlab2.policy.mle.crosswoz.evaluate.end2end_evaluate_simulation(policy)¶

convlab2.policy.mle.crosswoz.evaluate.evaluate_corpus_f1(policy, data, goal_type=None)¶

convlab2.policy.mle.crosswoz.evaluate.read_zipped_json(filepath, filename)¶

convlab2.policy.mle.crosswoz.loader module¶

class convlab2.policy.mle.crosswoz.loader.Dataset(s_s, a_s)¶: Bases: torch.utils.data.dataset.Dataset

class convlab2.policy.mle.crosswoz.loader.PolicyDataLoaderCrossWoz¶

Bases: object

create_dataset(part, batchsz)¶

convlab2.policy.mle.crosswoz.mle module¶

class convlab2.policy.mle.crosswoz.mle.MLE(archive_file='/home/travis/build/thu-coai/ConvLab-2/convlab2/policy/mle/crosswoz/models/mle_policy_crosswoz.zip', model_file='https://convlab.blob.core.windows.net/convlab-2/mle_policy_crosswoz.zip')¶: Bases: convlab2.policy.mle.mle.MLEAbstract

convlab2.policy.mle.crosswoz.train module¶

class convlab2.policy.mle.crosswoz.train.MLE_Trainer(manager, cfg)¶

Bases: object

imit_test(epoch, best)¶: provide an unbiased evaluation of the policy fit on the training dataset

imitating(epoch)¶: pretrain the policy by simple imitation learning (behavioral cloning)

load(filename='save/best')¶

policy_loop(data)¶

save(directory, epoch)¶

test()¶

Module contents¶