mirror of
https://github.com/wassname/Castor.git
synced 2026-08-20 12:00:37 +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
40 lines
2.4 KiB
Python
40 lines
2.4 KiB
Python
import os
|
|
|
|
from argparse import ArgumentParser
|
|
|
|
|
|
def get_args():
|
|
parser = ArgumentParser(description="Kim CNN")
|
|
parser.add_argument('--no_cuda', action='store_false', help='do not use cuda', dest='cuda')
|
|
parser.add_argument('--gpu', type=int, default=0) # Use -1 for CPU
|
|
parser.add_argument('--epochs', type=int, default=30)
|
|
parser.add_argument('--batch_size', type=int, default=1024)
|
|
parser.add_argument('--mode', type=str, default='multichannel', choices=['rand', 'static', 'non-static', 'multichannel'])
|
|
parser.add_argument('--lr', type=float, default=1.0)
|
|
parser.add_argument('--seed', type=int, default=3435)
|
|
parser.add_argument('--dataset', type=str, default='SST-1', choices=['SST-1', 'SST-2', 'Reuters', 'AAPD', 'IMDB', 'Yelp2014'])
|
|
parser.add_argument('--resume_snapshot', type=str, default=None)
|
|
parser.add_argument('--single_label', action='store_true')
|
|
parser.add_argument('--dev_every', type=int, default=30)
|
|
parser.add_argument('--log_every', type=int, default=10)
|
|
parser.add_argument('--patience', type=int, default=50)
|
|
parser.add_argument('--save_path', type=str, default='kim_cnn/saves')
|
|
parser.add_argument('--output_channel', type=int, default=100)
|
|
parser.add_argument('--words_dim', type=int, default=300)
|
|
parser.add_argument('--embed_dim', type=int, default=300)
|
|
parser.add_argument('--dropout', type=float, default=0.5)
|
|
parser.add_argument('--epoch_decay', type=int, default=15)
|
|
parser.add_argument('--data_dir', help='word vectors directory',
|
|
default=os.path.join(os.pardir, 'Castor-data', 'datasets'))
|
|
parser.add_argument('--word_vectors_dir', help='word vectors directory',
|
|
default=os.path.join(os.pardir, 'Castor-data', 'embeddings', 'word2vec'))
|
|
parser.add_argument('--word_vectors_file', help='word vectors filename', default='GoogleNews-vectors-negative300.txt')
|
|
parser.add_argument('--trained_model', type=str, default="")
|
|
parser.add_argument('--weight_decay', type=float, default=0)
|
|
parser.add_argument('--onnx', action='store_true', default=False, help='Export model in ONNX format')
|
|
parser.add_argument('--onnx_batch_size', type=int, default=1024, help='Batch size for ONNX export')
|
|
parser.add_argument('--onnx_sent_len', type=int, default=32, help='Sentence length for ONNX export')
|
|
|
|
args = parser.parse_args()
|
|
return args
|