joeyz0z
commented
1 year ago Thanks for your positive comment. We follow the dataset split in MSCap and MemCap to train a TextCNN classifier. Details of splits and code of TextCNN are as follows:
class textCNN(nn.Module):
def __init__(self, kernel_num, vocab_size, kernel_size, embed_dim, dropout, class_num):
super(textCNN, self).__init__()
ci = 1 # input chanel size
self.embed = nn.Embedding(vocab_size, embed_dim, padding_idx=1)
self.conv11 = nn.Conv2d(ci, kernel_num, (kernel_size[0], embed_dim))
self.conv12 = nn.Conv2d(ci, kernel_num, (kernel_size[1], embed_dim))
self.conv13 = nn.Conv2d(ci, kernel_num, (kernel_size[2], embed_dim))
self.dropout = nn.Dropout(dropout)
self.fc1 = nn.Linear(len(kernel_size) * kernel_num, class_num)
def init_embed(self, embed_matrix):
self.embed.weight = nn.Parameter(torch.Tensor(embed_matrix))
@staticmethod
def conv_and_pool(x, conv):
# x: (batch, 1, sentence_length, )
x = conv(x)
# x: (batch, kernel_num, H_out, 1)
x = F.relu(x.squeeze(3))
# x: (batch, kernel_num, H_out)
x = F.max_pool1d(x, x.size(2)).squeeze(2)
# (batch, kernel_num)
return x
def forward(self, x):
# x: (batch, sentence_length)
x = self.embed(x)
# x: (batch, sentence_length, embed_dim)
# TODO init embed matrix with pre-trained
x = x.unsqueeze(1)
# x: (batch, 1, sentence_length, embed_dim)
x1 = self.conv_and_pool(x, self.conv11) # (batch, kernel_num)
x2 = self.conv_and_pool(x, self.conv12) # (batch, kernel_num)
x3 = self.conv_and_pool(x, self.conv13) # (batch, kernel_num)
x = torch.cat((x1, x2, x3), 1) # (batch, 3 * kernel_num)
x = self.dropout(x)
logit = self.fc1(x)
return logit
def get_batch_captions_style_scores(self, captions, tokenizer, device):
input_ids = tokenizer.batch_encode_plus(captions, padding=True)['input_ids']
input_ids_ = torch.tensor(input_ids).to(device)
logits = self.forward(input_ids_)
probs = F.softmax(logits, dim=-1)
predicts = logits.argmax(-1)
return probs, predicts
def init_weight(self):
for m in self.modules():
if isinstance(m, nn.Conv2d):
n = m.kernel_size[0] * m.kernel_size[1] * m.out_channels
m.weight.data.normal_(0, math.sqrt(2. / n))
if m.bias is not None:
m.bias.data.zero_()
elif isinstance(m, nn.BatchNorm2d):
m.weight.data.fill_(1)
m.bias.data.zero_()
elif isinstance(m, nn.Linear):
m.weight.data.normal_(0, 0.01)
m.bias.data.zero_()
Rouchestand
Lxb-Code-Dev
Dear author, your paper is very creative and I am very interested in it. I am preparing to reproduce your experiment, but the code you provided does not seem to explain how to use the SentiCap dataset and FlickrStyle10k dataset. Can you give me some guidance? I would appreciate it if you could take the time to reply to me.