mirror of
https://github.com/wassname/Castor.git
synced 2026-10-05 12:20:28 +08:00
Ashutosh-Adhikari
dc086e895f
* Add ReutersTrainer, ReutersEvaluator options in Factory classes * Add Reuters to Kim-CNN command line arguments * Fix SST dataset path according to changes in Kim-CNN args The dataset path in args.py was made to point at the dataset folder rather than dataset/SST folder. Hence SST folder was added to paths in the SST dataset class * Add Reuters dataset class, and support in __main__ * Add Reuters dataset trainers and evaluators * Remove debug print statement in reuters_evaluator * Fix rounding bug in reuters_trainer and reuters_evaluator * Add LSTM for baseline text classification measurements * Add eval metrics for lstm_baseline * Set batch_first param in lstm_baseline * Remove onnx args from lstm_baseline * Pack padded sequences in LSTM_baseline * Add TensorBoardX support for Reuters trainer * Add Arxiv Academic Paper Dataset (AAPD) * Add Hidden Bottleneck Layer to BiLSTM * Fix packing of padded tensors in Reuters * Add cmdline args for Hidden Bottleneck Layer for BiLSTM * Include pre-padding lengths in AAPD dataset * Remove duplication of preprocessing code in AAPD * Remove batch_size condition in ReutersTrainer * Add ignore_lengths option to ReutersTrainer and ReutersEvaluator * Add AAPDCharQuantized and ReutersCharQuantized * Rename Reuters_hierarchical to ReutersHierarchical * Add CharacterCNN for document classification * Update README.md for CharacterCNN * Fix table in README.md for CharacterCNN * Add AAPDHierarchical for HAN * Update HAN for changes in Reuters dataset endpoints * Fix bug in CharCNN when running on CPU * Add AAPD dataset support for KimCNN * Fix dataset paths for SST-1 * Fix dimensions of FC1 in CharCNN * Add model checkpointing for Reuters based on F1 * Refactor LSTM baseline __main__ * Add precision, recall and F1 to Reuters evaluator * Checkpoint only at the end of an epoch for ReutersTrainer Add detailed log printing for dev evaluations * Fix log_template and dev_log_template in ReutersTrainer * Add IMDB dataset * Fix duplicate printing of header in ReutersTrainer * Add support for single_label datasets in ReutersTrainer * Add support for IMDB dataset in lstm_baseline and lstm_reg * Fix evaluator call in main method of HAN * Add IMDB for HAN * Fix for single_label * Fix evaluate_dataset method for single_label datasets * Reduce default patience to 5 epochs before early stopping * Revert change to save_state rather than the entire model * Add Yelp 2018 dataset * Integrate Yelp2018 with LSTM baseline * Replace Yelp2018 with Yelp2014 dataset * Add Yelp2014 to LSTM Baseline * Integrate Yelp14 into LSTM Regularization * Remove dropout in HBL for LSTM Baseline and Reg * Add Yelp for HAN * Fix the saving issue for HAN * Fix loading for HAN * Fix typo in ReutersEvaluator * Print to STDOUT rather than logger * Print XML-CNN eval to STDOUT rather than logger * Update max_length for IMDB dataset * Add single_label support for char_cnn * Fix evaluation method for char_cnn * Remove unwanted parameters from ReutersTrainer and ReutersEval * Fix code formatting in lstm_reg/args * Add support for IMDB and Yelp in KimCNN * Fix single_label incorporation * Remove unnecessary conditions * Fix num_classes in Yelp2014 * Add single_label support for XML-CNN * Fix call to evaluator in XML-CNN * Address PEP8 issues * Address PEP8 issues * Address PEP8 issues * Address PEP8 issues
61 lines
2.2 KiB
Python
61 lines
2.2 KiB
Python
from .evaluators.sick_evaluator import SICKEvaluator
|
|
from .evaluators.msrvid_evaluator import MSRVIDEvaluator
|
|
from .evaluators.sst_evaluator import SSTEvaluator
|
|
from .evaluators.trecqa_evaluator import TRECQAEvaluator
|
|
from .evaluators.wikiqa_evaluator import WikiQAEvaluator
|
|
from .evaluators.pit2015_evaluator import PIT2015Evaluator
|
|
from .evaluators.reuters_evaluator import ReutersEvaluator
|
|
from .evaluators.snli_evaluator import SNLIEvaluator
|
|
from .evaluators.sts2014_evaluator import STS2014Evaluator
|
|
from .evaluators.quora_evaluator import QuoraEvaluator
|
|
from nce.nce_pairwise_mp.evaluators.trecqa_evaluator import TRECQAEvaluatorNCE
|
|
from nce.nce_pairwise_mp.evaluators.wikiqa_evaluator import WikiQAEvaluatorNCE
|
|
|
|
|
|
class EvaluatorFactory(object):
|
|
"""
|
|
Get the corresponding Evaluator class for a particular dataset.
|
|
"""
|
|
evaluator_map = {
|
|
'sick': SICKEvaluator,
|
|
'msrvid': MSRVIDEvaluator,
|
|
'SST-1': SSTEvaluator,
|
|
'SST-2': SSTEvaluator,
|
|
'trecqa': TRECQAEvaluator,
|
|
'wikiqa': WikiQAEvaluator,
|
|
'pit2015': PIT2015Evaluator,
|
|
'twitterurl': PIT2015Evaluator,
|
|
'Reuters': ReutersEvaluator,
|
|
'AAPD': ReutersEvaluator,
|
|
'IMDB': ReutersEvaluator,
|
|
'Yelp2014': ReutersEvaluator,
|
|
'SNLI': SNLIEvaluator,
|
|
'sts2014': STS2014Evaluator,
|
|
'Quora': QuoraEvaluator
|
|
}
|
|
|
|
evaluator_map_nce = {
|
|
'trecqa': TRECQAEvaluatorNCE,
|
|
'wikiqa': WikiQAEvaluatorNCE
|
|
}
|
|
|
|
@staticmethod
|
|
def get_evaluator(dataset_cls, model, embedding, data_loader, batch_size, device, nce=False, keep_results=False):
|
|
if data_loader is None:
|
|
return None
|
|
|
|
if nce:
|
|
evaluator_map = EvaluatorFactory.evaluator_map_nce
|
|
else:
|
|
evaluator_map = EvaluatorFactory.evaluator_map
|
|
|
|
if not hasattr(dataset_cls, 'NAME'):
|
|
raise ValueError('Invalid dataset. Dataset should have NAME attribute.')
|
|
|
|
if dataset_cls.NAME not in evaluator_map:
|
|
raise ValueError('{} is not implemented.'.format(dataset_cls))
|
|
|
|
return evaluator_map[dataset_cls.NAME](
|
|
dataset_cls, model, embedding, data_loader, batch_size, device, keep_results
|
|
)
|