Fix #15 app.py

app.py

@@ -13,24 +13,31 @@ from huggingface_hub import hf_hub_download
 class ResBlk(nn.Module):
     def __init__(self, dim_in, dim_out, normalize=False, downsample=False):
         super().__init__()
-        self.normalize = normalize
+        self.conv1 = nn.Conv2d(dim_in, dim_out, 3, 1, 1)
+        self.norm1 = nn.InstanceNorm2d(dim_out, affine=True) if normalize else None
+        self.relu1 = nn.ReLU(inplace=True)
+        self.conv2 = nn.Conv2d(dim_out, dim_out, 3, 1, 1)
+        self.norm2 = nn.InstanceNorm2d(dim_out, affine=True) if normalize else None
+        self.relu2 = nn.ReLU(inplace=True)
         self.downsample = downsample
-        self.main = nn.Sequential(
-            nn.Conv2d(dim_in, dim_out, 3, 1, 1),
-            nn.InstanceNorm2d(dim_out, affine=True) if normalize else nn.Identity(),
-            nn.ReLU(inplace=True),
-            nn.Conv2d(dim_out, dim_out, 3, 1, 1),
-            nn.InstanceNorm2d(dim_out, affine=True) if normalize else nn.Identity()
-        )
-        self.downsample_layer = nn.AvgPool2d(2) if downsample else nn.Identity()
-        self.skip = nn.Conv2d(dim_in, dim_out, 1, 1, 0, bias=False)
+        if self.downsample:
+            self.avg_pool = nn.AvgPool2d(2)
 
     def forward(self, x):
-        out = self.main(x)
-        out = self.downsample_layer(out)
-        skip = self.skip(x)
-        skip = self.downsample_layer(skip)
-        return (out + skip) / math.sqrt(2)
+        residual = x
+        out = self.conv1(x)
+        if self.norm1:
+            out = self.norm1(out)
+        out = self.relu1(out)
+        out = self.conv2(out) # <--- Corrección aquí
+        if self.norm2:
+            out = self.norm2(out)
+        out = self.relu2(out)
+        if self.downsample:
+            out = self.avg_pool(out)
+            residual = self.avg_pool(residual)
+        out = out + residual
+        return out
 
 class AdainResBlk(nn.Module):
     def __init__(self, dim_in, dim_out, style_dim=64, w_hpf=1, upsample=False):
@@ -170,10 +177,10 @@ class Generator(nn.Module):
 
 # FUNCIÓN PARA CARGAR EL MODELO
 def load_pretrained_model(ckpt_path, img_size=256, style_dim=64, num_domains=3, device='cpu'):
-    num_domains_mappin = 2
-    latent_dim_for_mapping = 14
+    num_domains_mappin  = 3
+    latent_dim_for_mapping = 13
     G = Generator(img_size, style_dim).to(device)
-    M = MappingNetwork(latent_dim_for_mapping, style_dim, num_domains).to(device)
+    M = MappingNetwork(latent_dim_for_mapping, style_dim, num_domains_mappin).to(device)
     S = StyleEncoder(img_size, style_dim, num_domains).to(device)
     checkpoint = torch.load(ckpt_path, map_location=device)
     G.load_state_dict(checkpoint['generator'])