mirror of
https://github.com/saymrwulf/onnxruntime.git
synced 2026-05-16 21:00:14 +00:00
63 lines
2.4 KiB
Python
63 lines
2.4 KiB
Python
import math
|
|
import torch
|
|
import torch.nn as nn
|
|
import torch.nn.functional as F
|
|
|
|
|
|
class TransformerModel(nn.Module):
|
|
|
|
def __init__(self, ntoken, ninp, nhead, nhid, nlayers, dropout=0.5):
|
|
super(TransformerModel, self).__init__()
|
|
from torch.nn import TransformerEncoder, TransformerEncoderLayer
|
|
self.model_type = 'Transformer'
|
|
self.input1_mask = None
|
|
self.pos_encoder = PositionalEncoding(ninp, dropout)
|
|
encoder_layers = TransformerEncoderLayer(ninp, nhead, nhid, dropout)
|
|
self.transformer_encoder = TransformerEncoder(encoder_layers, nlayers)
|
|
self.encoder = nn.Embedding(ntoken, ninp)
|
|
self.ninp = ninp
|
|
self.decoder = nn.Linear(ninp, ntoken)
|
|
|
|
self.init_weights()
|
|
|
|
def _generate_square_subsequent_mask(self, sz):
|
|
mask = (torch.triu(torch.ones(sz, sz)) == 1).transpose(0, 1)
|
|
mask = mask.float().masked_fill(mask == 0, float('-inf')).masked_fill(mask == 1, float(0.0))
|
|
return mask
|
|
|
|
def init_weights(self):
|
|
initrange = 0.1
|
|
self.encoder.weight.data.uniform_(-initrange, initrange)
|
|
self.decoder.bias.data.zero_()
|
|
self.decoder.weight.data.uniform_(-initrange, initrange)
|
|
|
|
def forward(self, input1):
|
|
if self.input1_mask is None or self.input1_mask.size(0) != input1.size(0):
|
|
device = input1.device
|
|
mask = self._generate_square_subsequent_mask(input1.size(0)).to(device)
|
|
self.input1_mask = mask
|
|
|
|
input1 = self.encoder(input1) * math.sqrt(self.ninp)
|
|
input1 = self.pos_encoder(input1)
|
|
output = self.transformer_encoder(input1, self.input1_mask)
|
|
output = self.decoder(output)
|
|
return output
|
|
|
|
|
|
class PositionalEncoding(nn.Module):
|
|
|
|
def __init__(self, d_model, dropout=0.1, max_len=5000):
|
|
super(PositionalEncoding, self).__init__()
|
|
self.dropout = nn.Dropout(p=dropout)
|
|
|
|
pe = torch.zeros(max_len, d_model)
|
|
position = torch.arange(0, max_len, dtype=torch.float).unsqueeze(1)
|
|
div_term = torch.exp(torch.arange(0, d_model, 2).float() * (-math.log(10000.0) / d_model))
|
|
pe[:, 0::2] = torch.sin(position * div_term)
|
|
pe[:, 1::2] = torch.cos(position * div_term)
|
|
pe = pe.unsqueeze(0).transpose(0, 1)
|
|
self.register_buffer('pe', pe)
|
|
|
|
def forward(self, x):
|
|
x = x + self.pe[:x.size(0), :]
|
|
return self.dropout(x)
|