Spaces:
Running
Running
File size: 2,229 Bytes
95d308c |
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 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 |
import torch
import torch.nn as nn
from src.audio2pose_models.networks import ResidualConv, Upsample
class ResUnet(nn.Module):
def __init__(self, channel=1, filters=[32, 64, 128, 256]):
super(ResUnet, self).__init__()
self.input_layer = nn.Sequential(
nn.Conv2d(channel, filters[0], kernel_size=3, padding=1),
nn.BatchNorm2d(filters[0]),
nn.ReLU(),
nn.Conv2d(filters[0], filters[0], kernel_size=3, padding=1),
)
self.input_skip = nn.Sequential(
nn.Conv2d(channel, filters[0], kernel_size=3, padding=1)
)
self.residual_conv_1 = ResidualConv(filters[0], filters[1], stride=(2,1), padding=1)
self.residual_conv_2 = ResidualConv(filters[1], filters[2], stride=(2,1), padding=1)
self.bridge = ResidualConv(filters[2], filters[3], stride=(2,1), padding=1)
self.upsample_1 = Upsample(filters[3], filters[3], kernel=(2,1), stride=(2,1))
self.up_residual_conv1 = ResidualConv(filters[3] + filters[2], filters[2], stride=1, padding=1)
self.upsample_2 = Upsample(filters[2], filters[2], kernel=(2,1), stride=(2,1))
self.up_residual_conv2 = ResidualConv(filters[2] + filters[1], filters[1], stride=1, padding=1)
self.upsample_3 = Upsample(filters[1], filters[1], kernel=(2,1), stride=(2,1))
self.up_residual_conv3 = ResidualConv(filters[1] + filters[0], filters[0], stride=1, padding=1)
self.output_layer = nn.Sequential(
nn.Conv2d(filters[0], 1, 1, 1),
nn.Sigmoid(),
)
def forward(self, x):
# Encode
x1 = self.input_layer(x) + self.input_skip(x)
x2 = self.residual_conv_1(x1)
x3 = self.residual_conv_2(x2)
# Bridge
x4 = self.bridge(x3)
# Decode
x4 = self.upsample_1(x4)
x5 = torch.cat([x4, x3], dim=1)
x6 = self.up_residual_conv1(x5)
x6 = self.upsample_2(x6)
x7 = torch.cat([x6, x2], dim=1)
x8 = self.up_residual_conv2(x7)
x8 = self.upsample_3(x8)
x9 = torch.cat([x8, x1], dim=1)
x10 = self.up_residual_conv3(x9)
output = self.output_layer(x10)
return output |