|
|
import math |
|
|
|
|
|
import torch |
|
|
import torch.nn as nn |
|
|
import torch.nn.functional as F |
|
|
|
|
|
|
|
|
class PositionalEncoding(nn.Module): |
|
|
def __init__(self, d_model, dropout=0.1, max_len=600): |
|
|
super().__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) |
|
|
self.register_buffer('pe', pe) |
|
|
|
|
|
def forward(self, x): |
|
|
x = x + self.pe[:, x.shape[1], :] |
|
|
return self.dropout(x) |
|
|
|
|
|
|
|
|
def enc_dec_mask(T, S, frame_width=2, expansion=0, device='cuda'): |
|
|
mask = torch.ones(T, S) |
|
|
for i in range(T): |
|
|
mask[i, max(0, (i - expansion) * frame_width):(i + expansion + 1) * frame_width] = 0 |
|
|
return (mask == 1).to(device=device) |
|
|
|
