def __init__(self,
in_features,
out_features,
bias=True,
use_bn=False,
act_func=None,
dropout_rate=0,
ops_order='weight_bn_act'):
super(LinearLayer, self).__init__()
self.in_features = in_features
self.out_features = out_features
self.bias = bias
self.use_bn = use_bn
self.act_func = act_func
self.dropout_rate = dropout_rate
self.ops_order = ops_order
""" modules """
modules = {}
# batch norm
if self.use_bn:
if self.bn_before_weight:
modules['bn'] = nn.BatchNorm1d(in_features)
else:
modules['bn'] = nn.BatchNorm1d(out_features)
else:
modules['bn'] = None
# activation
modules['act'] = build_activation(self.act_func,
self.ops_list[0] != 'act')
# dropout
if self.dropout_rate > 0:
modules['dropout'] = nn.Dropout(self.dropout_rate, inplace=True)
else:
modules['dropout'] = None
# linear
modules['weight'] = {
'linear': nn.Linear(self.in_features, self.out_features, self.bias)
}
# add modules
for op in self.ops_list:
if modules[op] is None:
continue
elif op == 'weight':
if modules['dropout'] is not None:
self.add_module('dropout', modules['dropout'])
for key in modules['weight']:
self.add_module(key, modules['weight'][key])
else:
self.add_module(op, modules[op])
self.sequence = nn.Sequential(self._modules)
def __init__(self):
super(Fuse, self).__init__()
self.conv = nn.Conv1d(16, 33, 3, stride=2)
self.bn = nn.BatchNorm1d(33)
def __init__(self):
super().__init__()
self.m = nn.BatchNorm1d(2)
