| """RRDBNet architecture (Real-ESRGAN / ESRGAN generator). |
| |
| Self-contained re-implementation of `basicsr.archs.rrdbnet_arch.RRDBNet` so that |
| the OpenVINO export does not require the whole BasicSR package to be installed. |
| |
| The module layout (parameter names) is identical to the original |
| `RealESRGAN_x4plus` checkpoint, so `load_state_dict(..., strict=True)` works. |
| """ |
|
|
| import torch |
| from torch import nn as nn |
| from torch.nn import functional as F |
|
|
|
|
| class ResidualDenseBlock(nn.Module): |
| """Residual dense block used inside every RRDB.""" |
|
|
| def __init__(self, num_feat=64, num_grow_ch=32): |
| super().__init__() |
| self.conv1 = nn.Conv2d(num_feat, num_grow_ch, 3, 1, 1) |
| self.conv2 = nn.Conv2d(num_feat + num_grow_ch, num_grow_ch, 3, 1, 1) |
| self.conv3 = nn.Conv2d(num_feat + 2 * num_grow_ch, num_grow_ch, 3, 1, 1) |
| self.conv4 = nn.Conv2d(num_feat + 3 * num_grow_ch, num_grow_ch, 3, 1, 1) |
| self.conv5 = nn.Conv2d(num_feat + 4 * num_grow_ch, num_feat, 3, 1, 1) |
| self.lrelu = nn.LeakyReLU(negative_slope=0.2, inplace=True) |
|
|
| def forward(self, x): |
| x1 = self.lrelu(self.conv1(x)) |
| x2 = self.lrelu(self.conv2(torch.cat((x, x1), 1))) |
| x3 = self.lrelu(self.conv3(torch.cat((x, x1, x2), 1))) |
| x4 = self.lrelu(self.conv4(torch.cat((x, x1, x2, x3), 1))) |
| x5 = self.conv5(torch.cat((x, x1, x2, x3, x4), 1)) |
| return x5 * 0.2 + x |
|
|
|
|
| class RRDB(nn.Module): |
| """Residual-in-residual dense block.""" |
|
|
| def __init__(self, num_feat, num_grow_ch=32): |
| super().__init__() |
| self.rdb1 = ResidualDenseBlock(num_feat, num_grow_ch) |
| self.rdb2 = ResidualDenseBlock(num_feat, num_grow_ch) |
| self.rdb3 = ResidualDenseBlock(num_feat, num_grow_ch) |
|
|
| def forward(self, x): |
| out = self.rdb1(x) |
| out = self.rdb2(out) |
| out = self.rdb3(out) |
| return out * 0.2 + x |
|
|
|
|
| class RRDBNet(nn.Module): |
| """The ESRGAN / Real-ESRGAN generator. |
| |
| `RealESRGAN_x4plus` uses num_feat=64, num_block=23, num_grow_ch=32, scale=4. |
| """ |
|
|
| def __init__(self, num_in_ch=3, num_out_ch=3, scale=4, num_feat=64, num_block=23, num_grow_ch=32): |
| super().__init__() |
| self.scale = scale |
| if scale == 2: |
| num_in_ch = num_in_ch * 4 |
| elif scale == 1: |
| num_in_ch = num_in_ch * 16 |
| self.conv_first = nn.Conv2d(num_in_ch, num_feat, 3, 1, 1) |
| self.body = nn.Sequential(*[RRDB(num_feat, num_grow_ch) for _ in range(num_block)]) |
| self.conv_body = nn.Conv2d(num_feat, num_feat, 3, 1, 1) |
| self.conv_up1 = nn.Conv2d(num_feat, num_feat, 3, 1, 1) |
| self.conv_up2 = nn.Conv2d(num_feat, num_feat, 3, 1, 1) |
| self.conv_hr = nn.Conv2d(num_feat, num_feat, 3, 1, 1) |
| self.conv_last = nn.Conv2d(num_feat, num_out_ch, 3, 1, 1) |
| self.lrelu = nn.LeakyReLU(negative_slope=0.2, inplace=True) |
|
|
| def forward(self, x): |
| feat = self.conv_first(x) |
| body_feat = self.conv_body(self.body(feat)) |
| feat = feat + body_feat |
| feat = self.lrelu(self.conv_up1(F.interpolate(feat, scale_factor=2, mode='nearest'))) |
| feat = self.lrelu(self.conv_up2(F.interpolate(feat, scale_factor=2, mode='nearest'))) |
| return self.conv_last(self.lrelu(self.conv_hr(feat))) |
