78 lines
2.6 KiB
Python
78 lines
2.6 KiB
Python
import torch
|
|
import torch.nn as nn
|
|
import torch.nn.functional as F
|
|
import torch_receptive_field
|
|
|
|
from base.base_net import BaseNet
|
|
|
|
|
|
class SubTer_LeNet(BaseNet):
|
|
def __init__(self, rep_dim=1024):
|
|
super().__init__()
|
|
|
|
self.input_dim = (1, 32, 2048) # Input dimension for the network
|
|
self.rep_dim = rep_dim
|
|
self.pool = nn.MaxPool2d(2, 2)
|
|
|
|
self.conv1 = nn.Conv2d(1, 8, 5, bias=False, padding=2)
|
|
self.bn1 = nn.BatchNorm2d(8, eps=1e-04, affine=False)
|
|
self.conv2 = nn.Conv2d(8, 4, 5, bias=False, padding=2)
|
|
self.bn2 = nn.BatchNorm2d(4, eps=1e-04, affine=False)
|
|
self.fc1 = nn.Linear(4 * 512 * 8, self.rep_dim, bias=False)
|
|
|
|
def forward(self, x):
|
|
x = x.view(-1, 1, 32, 2048)
|
|
x = self.conv1(x)
|
|
x = self.pool(F.leaky_relu(self.bn1(x)))
|
|
x = self.conv2(x)
|
|
x = self.pool(F.leaky_relu(self.bn2(x)))
|
|
x = x.view(int(x.size(0)), -1)
|
|
x = self.fc1(x)
|
|
return x
|
|
|
|
def summary(self, receptive_field: bool = False):
|
|
# first run super method to log parameters and structure
|
|
super().summary(receptive_field=receptive_field)
|
|
self.logger.info("torch_receptive_field:")
|
|
torch_receptive_field.receptive_field(self, input_size=self.input_dim)
|
|
# torch_receptive_field.receptive_field_for_unit(rf, "2", (2,2))
|
|
|
|
|
|
class SubTer_LeNet_Decoder(BaseNet):
|
|
def __init__(self, rep_dim=1024):
|
|
super().__init__()
|
|
|
|
self.rep_dim = rep_dim
|
|
|
|
# Decoder network
|
|
self.fc3 = nn.Linear(self.rep_dim, 4 * 512 * 8, bias=False)
|
|
self.bn3 = nn.BatchNorm2d(4, eps=1e-04, affine=False)
|
|
self.deconv1 = nn.ConvTranspose2d(4, 8, 5, bias=False, padding=2)
|
|
self.bn4 = nn.BatchNorm2d(8, eps=1e-04, affine=False)
|
|
self.deconv2 = nn.ConvTranspose2d(8, 1, 5, bias=False, padding=2)
|
|
|
|
def forward(self, x):
|
|
x = self.fc3(x)
|
|
x = x.view(int(x.size(0)), 4, 8, 512)
|
|
x = F.interpolate(F.leaky_relu(self.bn3(x)), scale_factor=2)
|
|
x = self.deconv1(x)
|
|
x = F.interpolate(F.leaky_relu(self.bn4(x)), scale_factor=2)
|
|
x = self.deconv2(x)
|
|
x = torch.sigmoid(x)
|
|
return x
|
|
|
|
|
|
class SubTer_LeNet_Autoencoder(BaseNet):
|
|
def __init__(self, rep_dim=1024):
|
|
super().__init__()
|
|
|
|
self.input_dim = (1, 32, 2048) # Input dimension for the network
|
|
self.rep_dim = rep_dim
|
|
self.encoder = SubTer_LeNet(rep_dim=rep_dim)
|
|
self.decoder = SubTer_LeNet_Decoder(rep_dim=rep_dim)
|
|
|
|
def forward(self, x):
|
|
x = self.encoder(x)
|
|
x = self.decoder(x)
|
|
return x
|