Change default ReLU slope to .2 BREAKS COMPATIBILITY

This conforms my ConvGnLelu implementation with the generally accepted negative_slope=.2. I have no idea where I got .1. This will break backwards compatibility with some older models but will likely improve their performance when freshly trained. I did some auditing to find what these models might be, and I am not actively using any of them, so probably OK.

codes/models/arch_util.py

@@ -366,7 +366,7 @@ class ConvGnLelu(nn.Module):
         else:
             self.gn = None
         if activation:
-            self.lelu = nn.LeakyReLU(negative_slope=.1)
+            self.lelu = nn.LeakyReLU(negative_slope=.2)
         else:
             self.lelu = None