import torch
import torch.nn as nn
from torch import optim
from models import Model
from datasets import data_loader, text_CLS
from configs import Config
cfg = Config()
data_path = 'sources/weibo_senti_100k.csv'
data_stop_path = 'sources/hit_stopword'
dict_path = 'sources/dict'
dataset = text_CLS(dict_path, data_path, data_stop_path)
train_dataloader = data_loader(dataset, cfg)
cfg.pad_size = dataset.max_len_seq
model_text_cls = Model(config=cfg)
model_text_cls.to(cfg.device)
loss_func = nn.CrossEntropyLoss()
optimizer = optim.Adam(model_text_cls.parameters(), lr=cfg.learn_rate)
for epoch in range(cfg.num_epochs):
for i, batch in enumerate(train_dataloader):
label, data = batch
data = torch.tensor(data, dtype=torch.int64).to(cfg.device)
label = torch.tensor(label, dtype=torch.int64).to(cfg.device)
optimizer.zero_grad()
pred = model_text_cls.forward(data)
loss_val = loss_func(pred, label)
bidirectional=True,
batch_first=True,
dropout=config.dropout)
self.maxpool = nn.MaxPool1d(config.pad_size)
self.fc = nn.Linear(config.hidden_size * 2 + config.embed_size,
config.num_classes)
self.softmax = nn.Softmax(dim=1)
def forward(self, x):
embed = self.embeding(x)
out, _ = self.lstm(embed)
out = torch.cat((embed, out), 2)
out = F.relu(out)
out = out.permute(0, 2, 1)
out = self.maxpool(out).reshape(out.size()[0], -1)
# print(out.size())
out = self.fc(out)
out = self.softmax(out)
return out
if __name__ == '__main__':
from configs import Config
cfg = Config()
cfg.pad_size = 640
model_textcls = Model(config=cfg)
input_tensor = torch.tensor([i for i in range(640)]).reshape([1, 640])
out_tensor = model_textcls.forward(input_tensor)
print(out_tensor.size())
print(out_tensor)
