add weight initialization methods

mmcv/cnn/__init__.py

 from .resnet import ResNet, make_res_layer
+from .weight_init import xavier_init, normal_init, uniform_init, kaiming_init
 
-__all__ = ['ResNet', 'make_res_layer']
+__all__ = [
+    'ResNet', 'make_res_layer', 'xavier_init', 'normal_init', 'uniform_init',
+    'kaiming_init'
+]

mmcv/cnn/weight_init.py

+import torch.nn as nn
+
+
+def xavier_init(module, gain=1, bias=0, distribution='normal'):
+    assert distribution in ['uniform', 'normal']
+    if distribution == 'uniform':
+        nn.init.xavier_uniform_(module.weight, gain=gain)
+    else:
+        nn.init.xavier_normal_(module.weight, gain=gain)
+    if hasattr(module, 'bias'):
+        nn.init.constant_(module.bias, bias)
+
+
+def normal_init(module, mean=0, std=1, bias=0):
+    nn.init.normal_(module.weight, mean, std)
+    if hasattr(module, 'bias'):
+        nn.init.constant_(module.bias, bias)
+
+
+def uniform_init(module, a=0, b=1, bias=0):
+    nn.init.uniform_(module.weight, a, b)
+    if hasattr(module, 'bias'):
+        nn.init.constant_(module.bias, bias)
+
+
+def kaiming_init(module,
+                 mode='fan_out',
+                 nonlinearity='relu',
+                 bias=0,
+                 distribution='normal'):
+    assert distribution in ['uniform', 'normal']
+    if distribution == 'uniform':
+        nn.init.kaiming_uniform_(
+            module.weight, mode=mode, nonlinearity=nonlinearity)
+    else:
+        nn.init.kaiming_normal_(
+            module.weight, mode=mode, nonlinearity=nonlinearity)
+    if hasattr(module, 'bias'):
+        nn.init.constant_(module.bias, bias)