Update src/model.py

src/model.py

@@ -1,62 +1,35 @@
 import torch as t, torch.nn as nn, torch.nn.functional as F
-def cv(n_i, n_o, **kw): return nn.Conv2d(n_i, n_o, 3, padding=1, **kw)
-class C(nn.Module):
-    def forward(self, x): return t.tanh(x / 3) * 3
-class B(nn.Module):
-    def __init__(s, n_i, n_o):
-        super().__init__()
-        s.c = nn.Sequential(cv(n_i, n_o), nn.ReLU(), cv(n_o, n_o), nn.ReLU(), cv(n_o, n_o))
-        s.s = nn.Conv2d(n_i, n_o, 1, bias=False) if n_i != n_o else nn.Identity()
-        s.f = nn.ReLU()
-    def forward(s, x): return s.f(s.c(x) + s.s(x))
-
-import torch
-import torch as th
-import torch.nn as nn
-import torch.nn.functional as F
-
-def conv(n_in, n_out, **kwargs):
+def C(n_in, n_out, **kwargs):
     return nn.Conv2d(n_in, n_out, 3, padding=1, **kwargs)
-
 class Clamp(nn.Module):
     def forward(self, x):
         return torch.tanh(x / 3) * 3
-
-class Block(nn.Module):
+class B(nn.Module):
     def __init__(self, n_in, n_out):
         super().__init__()
-        self.conv = nn.Sequential(conv(n_in, n_out), nn.ReLU(), conv(n_out, n_out), nn.ReLU(), conv(n_out, n_out))
+        self.C = nn.Sequential(C(n_in, n_out), nn.ReLU(), C(n_out, n_out), nn.ReLU(), C(n_out, n_out))
         self.skip = nn.Conv2d(n_in, n_out, 1, bias=False) if n_in != n_out else nn.Identity()
         self.fuse = nn.ReLU()
     def forward(self, x):
-        return self.fuse(self.conv(x) + self.skip(x))
-
+        return self.fuse(self.C(x) + self.skip(x))
 def E(latent_channels=4):
     return nn.Sequential(
-        conv(3, 64), Block(64, 64),
-        conv(64, 64, stride=2, bias=False), Block(64, 64), Block(64, 64), Block(64, 64),
-        conv(64, 64, stride=2, bias=False), Block(64, 64), Block(64, 64), Block(64, 64),
-        conv(64, 64, stride=2, bias=False), Block(64, 64), Block(64, 64), Block(64, 64),
-        conv(64, latent_channels),
+        C(3, 64), B(64, 64),
+        C(64, 64, stride=2, bias=False), B(64, 64), B(64, 64), B(64, 64),
+        C(64, 64, stride=2, bias=False), B(64, 64), B(64, 64), B(64, 64),
+        C(64, 64, stride=2, bias=False), B(64, 64), B(64, 64), B(64, 64),
+        C(64, latent_channels),
     )
 
-def D(latent_channels=16):  # Adjusted to match expected input channels
+def D(latent_channels=16):
     return nn.Sequential(
         Clamp(), 
-        conv(latent_channels, 48),  # Reduced from 64 to 48 channels
-        nn.ReLU(),
-        Block(48, 48), Block(48, 48),  # Reduced number of blocks
-        nn.Upsample(scale_factor=2), conv(48, 48, bias=False),
-        Block(48, 48), Block(48, 48),  # Reduced number of blocks
-        nn.Upsample(scale_factor=2), conv(48, 48, bias=False),
-        Block(48, 48),  # Further reduction in blocks
-        nn.Upsample(scale_factor=2), conv(48, 48, bias=False),
-        Block(48, 48), 
-        conv(48, 3),  # Final convolution to output channels
-    )
-
-
-    
+        C(latent_channels, 48),nn.ReLU(),B(48, 48), B(48, 48),
+        nn.Upsample(scale_factor=2), C(48, 48, bias=False),B(48, 48), B(48, 48), 
+        nn.Upsample(scale_factor=2), C(48, 48, bias=False),B(48, 48),
+        nn.Upsample(scale_factor=2), C(48, 48, bias=False),B(48, 48), 
+        C(48, 3), 
+    )    
 class M(nn.Module):
     lm, ls = 3, 0.5
     def __init__(s, ep="encoder.pth", dp="decoder.pth", lc=None):
@@ -65,7 +38,6 @@ class M(nn.Module):
         s.e, s.d = E(lc), D(lc)
         def f(sd, mod, pfx):
             f_sd = {k.strip(pfx): v for k, v in sd.items() if k.strip(pfx) in mod.state_dict() and v.size() == mod.state_dict()[k.strip(pfx)].size()}
-            print(f"num keys: {len(f_sd)} of {len(mod.state_dict())}")
             mod.load_state_dict(f_sd, strict=False)
         if ep: f(t.load(ep, map_location="cpu", weights_only=True), s.e, "encoder.")
         if dp: f(t.load(dp, map_location="cpu", weights_only=True), s.d, "decoder.")