bisnet/resnet.py

#######################################################################################
#
# MIT License
#
# Copyright (c) [2025] [leonelhs@gmail.com]
#
# Permission is hereby granted, free of charge, to any person obtaining a copy
# of this software and associated documentation files (the "Software"), to deal
# in the Software without restriction, including without limitation the rights
# to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
# copies of the Software, and to permit persons to whom the Software is
# furnished to do so, subject to the following conditions:
#
# The above copyright notice and this permission notice shall be included in all
# copies or substantial portions of the Software.
#
# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
# SOFTWARE.
#
#######################################################################################
#
# This project is one of several repositories exploring image segmentation techniques.
# All related projects and interactive demos can be found at:
# https://huggingface.co/spaces/leonelhs/removators
# Self app: https://huggingface.co/spaces/leonelhs/rembg
#
# Source code is based on or inspired by several projects.
# For more details and proper attribution, please refer to the following resources:
#
# - [face-makeup.PyTorch] - [https://github.com/zllrunning/face-makeup.PyTorch]
# - [BiSeNet] [https://github.com/CoinCheung/BiSeNet]

import torch
import torch.nn as nn
import torch.nn.functional as F
from huggingface_hub import hf_hub_download

# from modules.bn import InPlaceABNSync as BatchNorm2d

REPO_ID = "leonelhs/faceparser"
CKPT = "resnet18-5c106cde.pth"
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")

def conv3x3(in_planes, out_planes, stride=1):
    """3x3 convolution with padding"""
    return nn.Conv2d(in_planes, out_planes, kernel_size=3, stride=stride,
                     padding=1, bias=False)


class BasicBlock(nn.Module):
    def __init__(self, in_chan, out_chan, stride=1):
        super(BasicBlock, self).__init__()
        self.conv1 = conv3x3(in_chan, out_chan, stride)
        self.bn1 = nn.BatchNorm2d(out_chan)
        self.conv2 = conv3x3(out_chan, out_chan)
        self.bn2 = nn.BatchNorm2d(out_chan)
        self.relu = nn.ReLU(inplace=True)
        self.downsample = None
        if in_chan != out_chan or stride != 1:
            self.downsample = nn.Sequential(
                nn.Conv2d(in_chan, out_chan,
                          kernel_size=1, stride=stride, bias=False),
                nn.BatchNorm2d(out_chan),
            )

    def forward(self, x):
        residual = self.conv1(x)
        residual = F.relu(self.bn1(residual))
        residual = self.conv2(residual)
        residual = self.bn2(residual)

        shortcut = x
        if self.downsample is not None:
            shortcut = self.downsample(x)

        out = shortcut + residual
        out = self.relu(out)
        return out


def create_layer_basic(in_chan, out_chan, bnum, stride=1):
    layers = [BasicBlock(in_chan, out_chan, stride=stride)]
    for i in range(bnum - 1):
        layers.append(BasicBlock(out_chan, out_chan, stride=1))
    return nn.Sequential(*layers)


class Resnet18(nn.Module):
    def __init__(self):
        super(Resnet18, self).__init__()
        self.conv1 = nn.Conv2d(3, 64, kernel_size=7, stride=2, padding=3,
                               bias=False)
        self.bn1 = nn.BatchNorm2d(64)
        self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)
        self.layer1 = create_layer_basic(64, 64, bnum=2, stride=1)
        self.layer2 = create_layer_basic(64, 128, bnum=2, stride=2)
        self.layer3 = create_layer_basic(128, 256, bnum=2, stride=2)
        self.layer4 = create_layer_basic(256, 512, bnum=2, stride=2)
        self.init_weight()

    def forward(self, x):
        x = self.conv1(x)
        x = F.relu(self.bn1(x))
        x = self.maxpool(x)

        x = self.layer1(x)
        feat8 = self.layer2(x)  # 1/8
        feat16 = self.layer3(feat8)  # 1/16
        feat32 = self.layer4(feat16)  # 1/32
        return feat8, feat16, feat32

    def init_weight(self):
        checkpoint = hf_hub_download(repo_id=REPO_ID, filename=CKPT)
        state_dict = torch.load(checkpoint, map_location=device, weights_only=False)
        self_state_dict = self.state_dict()
        for k, v in state_dict.items():
            if 'fc' in k: continue
            self_state_dict.update({k: v})
        self.load_state_dict(self_state_dict)

    def get_params(self):
        wd_params, nowd_params = [], []
        for name, module in self.named_modules():
            if isinstance(module, (nn.Linear, nn.Conv2d)):
                wd_params.append(module.weight)
                if not module.bias is None:
                    nowd_params.append(module.bias)
            elif isinstance(module, nn.BatchNorm2d):
                nowd_params += list(module.parameters())
        return wd_params, nowd_params


if __name__ == "__main__":
    net = Resnet18()
    x = torch.randn(16, 3, 224, 224)
    out = net(x)
    print(out[0].size())
    print(out[1].size())
    print(out[2].size())
    net.get_params()