Add causal person fusion and MuVAP stage-3 baselines

third_party/EgoSpeak/MiniROAD/model/weights_init.py

@@ -0,0 +1,35 @@
+# FROM LSTR
+import math
+import torch.nn as nn
+
+def weights_init(m):
+    if isinstance(m, nn.Linear):
+        nn.init.kaiming_uniform_(m.weight.data, a=math.sqrt(5))
+    elif isinstance(m, nn.Conv1d):
+        nn.init.normal_(m.weight.data)
+        if m.bias is not None:
+            nn.init.normal_(m.bias.data)
+    elif isinstance(m, nn.Conv2d):
+        nn.init.xavier_normal_(m.weight.data)
+        if m.bias is not None:
+            nn.init.normal_(m.bias.data)
+    elif isinstance(m, nn.ConvTranspose1d):
+        nn.init.normal_(m.weight.data)
+        if m.bias is not None:
+            nn.init.normal_(m.bias.data)
+    elif isinstance(m, nn.ConvTranspose2d):
+        nn.init.xavier_normal_(m.weight.data)
+        if m.bias is not None:
+            nn.init.normal_(m.bias.data)
+    elif isinstance(m, nn.BatchNorm1d):
+        nn.init.normal_(m.weight.data, mean=1, std=0.02)
+        nn.init.constant_(m.bias.data, 0)
+    elif isinstance(m, nn.BatchNorm2d):
+        nn.init.normal_(m.weight.data, mean=1, std=0.02)
+        nn.init.constant_(m.bias.data, 0)
+    elif isinstance(m, nn.GRUCell):
+        for param in m.parameters():
+            if len(param.shape) >= 2:
+                nn.init.orthogonal_(param.data)
+            else:
+                nn.init.normal_(param.data)