mirror of
https://github.com/wassname/Castor.git
synced 2026-09-09 11:13:20 +08:00
Achyudh Ram
6daa5a128f
* 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
39 lines
2.2 KiB
Python
39 lines
2.2 KiB
Python
import os
|
|
|
|
from argparse import ArgumentParser
|
|
|
|
|
|
def get_args():
|
|
parser = ArgumentParser(description="Baseline LSTM for text classification")
|
|
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=50)
|
|
parser.add_argument('--batch_size', type=int, default=1024)
|
|
parser.add_argument('--bidirectional', action='store_true'),
|
|
parser.add_argument('--bottleneck_layer', action='store_true'),
|
|
parser.add_argument('--num_layers', type=int, default=2)
|
|
parser.add_argument('--hidden_dim', type=int, default=256)
|
|
parser.add_argument('--mode', type=str, default='static', choices=['rand', 'static', 'non-static'])
|
|
parser.add_argument('--lr', type=float, default=0.001)
|
|
parser.add_argument('--seed', type=int, default=3435)
|
|
parser.add_argument('--dataset', type=str, default='Reuters', choices=['SST-1', 'SST-2', 'Reuters', 'AAPD'])
|
|
parser.add_argument('--resume_snapshot', type=str, default=None)
|
|
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='lstm_baseline/saves')
|
|
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)
|
|
|
|
args = parser.parse_args()
|
|
return args
|