def conv_1x1_bn(inp, oup):
weight = weight_variable()
return nn.SequentialCell([
nn.Conv2d(in_channels=inp, out_channels=oup, kernel_size=1, stride=1, padding=0, weight_init=weight,
has_bias=False),
nn.BatchNorm2d(oup, eps=0.001),
nn.HSwish()])
def conv_3x3_bn(inp, oup, stride):
weight = weight_variable()
return nn.SequentialCell([
nn.Conv2d(in_channels=inp, out_channels=oup, kernel_size=3, stride=stride, padding=1, weight_init=weight,
has_bias=False, pad_mode='pad'),
nn.BatchNorm2d(oup, eps=0.001), #, momentum=0.1),
nn.HSwish()])
def __init__(self, act_func):
super(Activation, self).__init__()
if act_func == 'relu':
self.act = nn.ReLU()
elif act_func == 'relu6':
self.act = nn.ReLU6()
elif act_func in ('hsigmoid', 'hard_sigmoid'):
self.act = MyHSigmoid() # nn.HSigmoid()
elif act_func in ('hswish', 'hard_swish'):
self.act = nn.HSwish()
else:
raise NotImplementedError
def Act(type='default'):
if type in ['default', 'def']:
return Act(DEFAULTS['activation'])
if type == 'relu':
return nn.ReLU()
elif type == 'sigmoid':
return nn.Sigmoid()
elif type == 'hswish':
return nn.HSwish()
elif type == 'leaky_relu':
return nn.LeakyReLU(alpha=DEFAULTS['leaky_relu']['alpha'])
else:
raise ValueError("Unsupported activation type: %s" % type)
