mirror of
https://github.com/wassname/Castor.git
synced 2026-10-05 12:20:28 +08:00
Achyudh Ram
f0a5c370bc
* 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
66 lines
3.0 KiB
Python
66 lines
3.0 KiB
Python
import torch
|
|
import torch.nn as nn
|
|
|
|
import torch.nn.functional as F
|
|
|
|
|
|
class KimCNN(nn.Module):
|
|
def __init__(self, config):
|
|
super(KimCNN, self).__init__()
|
|
dataset = config.dataset
|
|
output_channel = config.output_channel
|
|
target_class = config.target_class
|
|
words_num = config.words_num
|
|
words_dim = config.words_dim
|
|
self.mode = config.mode
|
|
Ks = 3 # There are three conv nets here
|
|
|
|
input_channel = 1
|
|
if config.mode == 'rand':
|
|
rand_embed_init = torch.Tensor(words_num, words_dim).uniform_(-0.25, 0.25)
|
|
self.embed = nn.Embedding.from_pretrained(rand_embed_init, freeze=False)
|
|
elif config.mode == 'static':
|
|
self.static_embed = nn.Embedding.from_pretrained(dataset.TEXT_FIELD.vocab.vectors, freeze=True)
|
|
elif config.mode == 'non-static':
|
|
self.non_static_embed = nn.Embedding.from_pretrained(dataset.TEXT_FIELD.vocab.vectors, freeze=False)
|
|
elif config.mode == 'multichannel':
|
|
self.static_embed = nn.Embedding.from_pretrained(dataset.TEXT_FIELD.vocab.vectors, freeze=True)
|
|
self.non_static_embed = nn.Embedding.from_pretrained(dataset.TEXT_FIELD.vocab.vectors, freeze=False)
|
|
input_channel = 2
|
|
else:
|
|
print("Unsupported Mode")
|
|
exit()
|
|
|
|
self.conv1 = nn.Conv2d(input_channel, output_channel, (3, words_dim), padding=(2,0))
|
|
self.conv2 = nn.Conv2d(input_channel, output_channel, (4, words_dim), padding=(3,0))
|
|
self.conv3 = nn.Conv2d(input_channel, output_channel, (5, words_dim), padding=(4,0))
|
|
|
|
self.dropout = nn.Dropout(config.dropout)
|
|
self.fc1 = nn.Linear(Ks * output_channel, target_class)
|
|
|
|
def forward(self, x, **kwargs):
|
|
if self.mode == 'rand':
|
|
word_input = self.embed(x) # (batch, sent_len, embed_dim)
|
|
x = word_input.unsqueeze(1) # (batch, channel_input, sent_len, embed_dim)
|
|
elif self.mode == 'static':
|
|
static_input = self.static_embed(x)
|
|
x = static_input.unsqueeze(1) # (batch, channel_input, sent_len, embed_dim)
|
|
elif self.mode == 'non-static':
|
|
non_static_input = self.non_static_embed(x)
|
|
x = non_static_input.unsqueeze(1) # (batch, channel_input, sent_len, embed_dim)
|
|
elif self.mode == 'multichannel':
|
|
non_static_input = self.non_static_embed(x)
|
|
static_input = self.static_embed(x)
|
|
x = torch.stack([non_static_input, static_input], dim=1) # (batch, channel_input=2, sent_len, embed_dim)
|
|
else:
|
|
print("Unsupported Mode")
|
|
exit()
|
|
x = [F.relu(self.conv1(x)).squeeze(3), F.relu(self.conv2(x)).squeeze(3), F.relu(self.conv3(x)).squeeze(3)]
|
|
# (batch, channel_output, ~=sent_len) * Ks
|
|
x = [F.max_pool1d(i, i.size(2)).squeeze(2) for i in x] # max-over-time pooling
|
|
# (batch, channel_output) * Ks
|
|
x = torch.cat(x, 1) # (batch, channel_output * Ks)
|
|
x = self.dropout(x)
|
|
logit = self.fc1(x) # (batch, target_size)
|
|
return logit
|