Model initialization exception

[wangqiim]

Thanks for sharing your code. I find some anomalous code In msdnet.py#L322.
these three "if branch" will not be excuted in func _init_weights(self, m).

MSDNet-PyTorch/models/msdnet.py

Lines 242 to 264 in c16a62b

	for m in self.blocks:
	if hasattr(m, '__iter__'):
	for _m in m:
	self._init_weights(_m)
	else:
	self._init_weights(m)
	for m in self.classifier:
	if hasattr(m, '__iter__'):
	for _m in m:
	self._init_weights(_m)
	else:
	self._init_weights(m)
	def _init_weights(self, m):
	if isinstance(m, nn.Conv2d):
	n = m.kernel_size[0] * m.kernel_size[1] * m.out_channels
	m.weight.data.normal_(0, math.sqrt(2. / n))
	elif isinstance(m, nn.BatchNorm2d):
	m.weight.data.fill_(1)
	m.bias.data.zero_()
	elif isinstance(m, nn.Linear):
	m.bias.data.zero_()