Use torch instead of scipy for random initialization of inception and googlenet weights (#4256)

using nn.init.trunc_normal_ instead of scipy.stats.truncnorm
Co-authored-by: Vincent Moens <vmoens@fb.com>

torchvision/models/googlenet.py

@@ -124,12 +124,7 @@ class GoogLeNet(nn.Module):
     def _initialize_weights(self) -> None:
         for m in self.modules():
             if isinstance(m, nn.Conv2d) or isinstance(m, nn.Linear):
-                import scipy.stats as stats
-                X = stats.truncnorm(-2, 2, scale=0.01)
-                values = torch.as_tensor(X.rvs(m.weight.numel()), dtype=m.weight.dtype)
-                values = values.view(m.weight.size())
-                with torch.no_grad():
-                    m.weight.copy_(values)
+                torch.nn.init.trunc_normal_(m.weight, mean=0.0, std=0.01, a=-2, b=2)
             elif isinstance(m, nn.BatchNorm2d):
                 nn.init.constant_(m.weight, 1)
                 nn.init.constant_(m.bias, 0)

torchvision/models/inception.py

@@ -120,13 +120,8 @@ class Inception3(nn.Module):
         if init_weights:
             for m in self.modules():
                 if isinstance(m, nn.Conv2d) or isinstance(m, nn.Linear):
-                    import scipy.stats as stats
-                    stddev = m.stddev if hasattr(m, 'stddev') else 0.1
-                    X = stats.truncnorm(-2, 2, scale=stddev)
-                    values = torch.as_tensor(X.rvs(m.weight.numel()), dtype=m.weight.dtype)
-                    values = values.view(m.weight.size())
-                    with torch.no_grad():
-                        m.weight.copy_(values)
+                    stddev = float(m.stddev) if hasattr(m, 'stddev') else 0.1  # type: ignore
+                    torch.nn.init.trunc_normal_(m.weight, mean=0.0, std=stddev, a=-2, b=2)
                 elif isinstance(m, nn.BatchNorm2d):
                     nn.init.constant_(m.weight, 1)
                     nn.init.constant_(m.bias, 0)