Create model.py

src/model.py

@@ -0,0 +1,52 @@
+import torch as t, torch.nn as nn, torch.nn.functional as F
+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 t.tanh(x / 3) * 3
+class B(nn.Module):
+    def __init__(self, n_in, n_out):
+        super().__init__()
+        self.conv = 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))
+def E(latent_channels=4):
+    return nn.Sequential(
+        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):
+    return nn.Sequential(
+        Clamp(), 
+        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):
+        super().__init__()
+        if lc is None: lc = s.glc(str(ep))
+        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()}
+            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.")
+        s.e.requires_grad_(False)
+        s.d.requires_grad_(False)
+    def glc(s, ep): return 16 if "taef1" in ep or "taesd3" in ep else 4
+    @staticmethod
+    def sl(x): return x.div(2 * M.lm).add(M.ls).clamp(0, 1)
+    @staticmethod
+    def ul(x): return x.sub(M.ls).mul(2 * M.lm)
+    def forward(s, x, rl=False):
+        l, o = s.e(x), s.d(s.e(x))
+        return (o.clamp(0, 1), l) if rl else o.clamp(0, 1)