File size: 1,099 Bytes
d60982d |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 |
import torch
import torch.nn as nn
import torch.nn.functional as F
import torchvision.models as models
class Encoder(nn.Module):
def __init__(self, out_dim=64):
super(Encoder, self).__init__()
self.conv1 = nn.Conv2d(3, 16, kernel_size=3, stride=1, padding=1)
self.conv2 = nn.Conv2d(16, 32, kernel_size=3, stride=1, padding=1)
self.conv3 = nn.Conv2d(32, 64, kernel_size=3, stride=1, padding=1)
self.conv4 = nn.Conv2d(64, 64, kernel_size=3, stride=1, padding=1)
self.pool = nn.MaxPool2d(2, 2)
# projection MLP
self.l1 = nn.Linear(64, 64)
self.l2 = nn.Linear(64, out_dim)
def forward(self, x):
x = self.conv1(x)
x = F.relu(x)
x = self.pool(x)
x = self.conv2(x)
x = F.relu(x)
x = self.pool(x)
x = self.conv3(x)
x = F.relu(x)
x = self.pool(x)
x = self.conv4(x)
x = F.relu(x)
x = self.pool(x)
h = torch.mean(x, dim=[2, 3])
x = self.l1(h)
x = F.relu(x)
x = self.l2(x)
return h, x
|