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
29 lines
1.1 KiB
Python
Executable File
29 lines
1.1 KiB
Python
Executable File
import torch
|
|
import torch.nn as nn
|
|
from torch.autograd import Variable
|
|
#from utils import
|
|
import torch.nn.functional as F
|
|
from han.sent_level_rnn import SentLevelRNN
|
|
from han.word_level_rnn import WordLevelRNN
|
|
|
|
|
|
class HAN(nn.Module):
|
|
def __init__(self, config):
|
|
super(HAN, self).__init__()
|
|
dataset = config.dataset
|
|
self.mode = config.mode
|
|
self.word_attention_rnn = WordLevelRNN(config)
|
|
self.sentence_attention_rnn = SentLevelRNN(config)
|
|
def forward(self, x, **kwargs):
|
|
x = x.permute(1,2,0) ## Expected : #sentences, #words, batch size
|
|
num_sentences = x.size()[0]
|
|
word_attentions = None
|
|
for i in range(num_sentences):
|
|
_word_attention = self.word_attention_rnn(x[i,:,:])
|
|
if word_attentions is None:
|
|
word_attentions = _word_attention
|
|
else:
|
|
word_attentions = torch.cat((word_attentions, _word_attention),0)
|
|
return self.sentence_attention_rnn(word_attentions)
|
|
|