Demo.ipynb not Runnable

[wisalkhanmv]

I've tried running the demo notebook but it doesn't run majorly because it's missing arcface models.

I downloaded the model from

wget -P ./arcface_model https://github.com/neuralchen/SimSwap/releases/download/1.0/arcface_checkpoint.tar

but this just gives error:

{
    "name": "TypeError",
    "message": "'ResNet' object is not subscriptable",
    "stack": "---------------------------------------------------------------------------
TypeError                                 Traceback (most recent call last)
Cell In[3], line 16
     14 starG = stargan_model()
     15 opt = TestOptions().parse()
---> 16 simG = simswap_model(opt)

File ~/stuff/Lowerated/services/P-46/Git/DF_RAP/deepfakes.py:37, in simswap_model(opt)
     35 def simswap_model(opt):
     36     from SimSwap.models.models import create_model
---> 37     model = create_model(opt)
     38     model.eval()
     39     return model.to(device)

File ~/stuff/Lowerated/services/P-46/Git/DF_RAP/SimSwap/models/models.py:17, in create_model(opt)
     14     from .ui_model import UIModel
     15     model = UIModel()
---> 17 model.initialize(opt)
     18 if opt.verbose:
     19     print(\"model [%s] was created\" % (model.name()))

File ~/stuff/Lowerated/services/P-46/Git/DF_RAP/SimSwap/models/fs_model.py:66, in fsModel.initialize(self, opt)
     64 netArc_checkpoint = opt.Arc_path
     65 netArc_checkpoint = torch.load(netArc_checkpoint)
---> 66 self.netArc = netArc_checkpoint['model'].module
     67 self.netArc = self.netArc.to(device)
     68 self.netArc.eval()

TypeError: 'ResNet' object is not subscriptable"
}

so, i thought the problem would be with how we're using it in fs_model.py so i changed the loading code to this:

 # Load the ArcFace model
        netArc_checkpoint = opt.Arc_path
        self.netArc = torch.load(netArc_checkpoint)
        self.netArc = self.netArc.to(device)
        self.netArc.eval()

then i downloaded the checkpoint models from here. https://drive.google.com/drive/folders/1jV6_0FIMPC53FZ2HzZNJZGMe55bbu17R

unzipped them, now they run but arcface_models.py is missing.

i downloaded from the baseline repo you provided but there is tensor shape error:

RuntimeError: view size is not compatible with input tensor's size and stride (at least one dimension spans across two contiguous subspaces). Use .reshape(...) instead.

so i updated the resnet model as well.

this is the new file.

import math
import torch
import torch.nn.functional as F
from torch import nn
from torch.nn import Parameter
from .config import device, num_classes

class SEBlock(nn.Module):
    def __init__(self, channel, reduction=16):
        super(SEBlock, self).__init__()
        self.avg_pool = nn.AdaptiveAvgPool2d(1)
        self.fc = nn.Sequential(
            nn.Linear(channel, channel // reduction),
            nn.PReLU(),
            nn.Linear(channel // reduction, channel),
            nn.Sigmoid()
        )

    def forward(self, x):
        b, c, _, _ = x.size()
        y = self.avg_pool(x).view(b, c)
        y = self.fc(y).view(b, c, 1, 1)
        return x * y

class IRBlock(nn.Module):
    expansion = 1

    def __init__(self, inplanes, planes, stride=1, downsample=None, use_se=True):
        super(IRBlock, self).__init__()
        self.bn0 = nn.BatchNorm2d(inplanes)
        self.conv1 = conv3x3(inplanes, inplanes)
        self.bn1 = nn.BatchNorm2d(inplanes)
        self.prelu = nn.PReLU()
        self.conv2 = conv3x3(inplanes, planes, stride)
        self.bn2 = nn.BatchNorm2d(planes)
        self.downsample = downsample
        self.stride = stride
        self.use_se = use_se
        if self.use_se:
            self.se = SEBlock(planes)

    def forward(self, x):
        residual = x
        out = self.bn0(x)
        out = self.conv1(out)
        out = self.bn1(out)
        out = self.prelu(out)

        out = self.conv2(out)
        out = self.bn2(out)
        if self.use_se:
            out = self.se(out)

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

        out += residual
        out = self.prelu(out)

        return out

class ResNet(nn.Module):
    def __init__(self, block, layers, use_se=True):
        self.inplanes = 64
        self.use_se = use_se
        super(ResNet, self).__init__()
        self.conv1 = nn.Conv2d(3, 64, kernel_size=3, stride=1, bias=False)
        self.bn1 = nn.BatchNorm2d(64)
        self.prelu = nn.PReLU()
        self.maxpool = nn.MaxPool2d(kernel_size=2, stride=2)
        self.layer1 = self._make_layer(block, 64, layers[0])
        self.layer2 = self._make_layer(block, 128, layers[1], stride=2)
        self.layer3 = self._make_layer(block, 256, layers[2], stride=2)
        self.layer4 = self._make_layer(block, 512, layers[3], stride=2)
        self.bn2 = nn.BatchNorm2d(512)
        self.dropout = nn.Dropout()
        self.fc = nn.Linear(512 * 7 * 7, 512)
        self.bn3 = nn.BatchNorm1d(512)

        for m in self.modules():
            if isinstance(m, nn.Conv2d):
                nn.init.xavier_normal_(m.weight)
            elif isinstance(m, nn.BatchNorm2d) or isinstance(m, nn.BatchNorm1d):
                nn.init.constant_(m.weight, 1)
                nn.init.constant_(m.bias, 0)
            elif isinstance(m, nn.Linear):
                nn.init.xavier_normal_(m.weight)
                nn.init.constant_(m.bias, 0)

    def _make_layer(self, block, planes, blocks, stride=1):
        downsample = None
        if stride != 1 or self.inplanes != planes * block.expansion:
            downsample = nn.Sequential(
                nn.Conv2d(self.inplanes, planes * block.expansion,
                          kernel_size=1, stride=stride, bias=False),
                nn.BatchNorm2d(planes * block.expansion),
            )

        layers = []
        layers.append(block(self.inplanes, planes, stride, downsample, use_se=self.use_se))
        self.inplanes = planes
        for i in range(1, blocks):
            layers.append(block(self.inplanes, planes, use_se=self.use_se))

        return nn.Sequential(*layers)

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

        x = self.layer1(x)
        x = self.layer2(x)
        x = self.layer3(x)
        x = self.layer4(x)

        x = self.bn2(x)
        x = self.dropout(x)
        # feature = x
        x = x.reshape(x.size(0), -1)  # Updated to reshape
        x = self.fc(x)
        x = self.bn3(x)

        return x

class ArcMarginModel(nn.Module):
    def __init__(self, args):
        super(ArcMarginModel, self).__init__()

        self.weight = Parameter(torch.FloatTensor(num_classes, args.emb_size))
        nn.init.xavier_uniform_(self.weight)

        self.easy_margin = args.easy_margin
        self.m = args.margin_m
        self.s = args.margin_s

        self.cos_m = math.cos(self.m)
        self.sin_m = math.sin(self.m)
        self.th = math.cos(math.pi - self.m)
        self.mm = math.sin(math.pi - self.m) * self.m

    def forward(self, input, label):
        x = F.normalize(input)
        W = F.normalize(self.weight)
        cosine = F.linear(x, W)
        sine = torch.sqrt(1.0 - torch.pow(cosine, 2))
        phi = cosine * self.cos_m - sine * self.sin_m  # cos(theta + m)
        if self.easy_margin:
            phi = torch.where(cosine > 0, phi, cosine)
        else:
            phi = torch.where(cosine > self.th, phi, cosine - self.mm)
        one_hot = torch.zeros(cosine.size(), device=device)
        one_hot.scatter_(1, label.view(-1, 1).long(), 1)
        output = (one_hot * phi) + ((1.0 - one_hot) * cosine)
        output *= self.s
        return output

finally, inside the drawing results in demo.ipynb, i changed the lines to these:

# Load the ArcFace model
netArc_checkpoint = opt.Arc_path
netArc_checkpoint = torch.load(netArc_checkpoint)
netArc = netArc_checkpoint.to(device)
netArc.eval()

Now it runs.

[ZOMIN28]

Thanks for your fix very mush🙂🙂!! This might have been caused by the version of Arc_face.