def __init__(self,
input_dim,
output_dim,
weight_bias_init,
act_str,
keep_prob=0.8,
scale_coef=1.0,
use_activation=True,
convert_dtype=True,
drop_out=False):
super(DenseLayer, self).__init__()
weight_init, bias_init = weight_bias_init
self.weight = init_method(weight_init, [input_dim, output_dim],
name="weight")
self.bias = init_method(bias_init, [output_dim], name="bias")
self.act_func = self._init_activation(act_str)
self.matmul = P.MatMul(transpose_b=False)
self.bias_add = P.BiasAdd()
self.cast = P.Cast()
self.dropout = Dropout(keep_prob=keep_prob)
self.mul = P.Mul()
self.realDiv = P.RealDiv()
self.scale_coef = scale_coef
self.use_activation = use_activation
self.convert_dtype = convert_dtype
self.drop_out = drop_out
def __init__(self, keep_prob, seed0, seed1, strategy=None):
super(Net, self).__init__()
self.drop = Dropout(keep_prob,
seed0,
seed1,
dtype=ms.float32,
strategy=strategy)
def __init__(self, in_channels, out_channels, dropout):
layers = [
Norm(in_channels),
Act(),
Conv2d(in_channels, out_channels, kernel_size=3),
Norm(out_channels),
Act(),
Conv2d(out_channels, out_channels, kernel_size=3),
]
if dropout:
layers.insert(5, Dropout(dropout))
super().__init__(layers)
def __init__(self, in_channels, out_channels, stride, dropout):
super().__init__()
self.norm1 = Norm(in_channels)
self.act1 = Act()
self.conv1 = Conv2d(in_channels,
out_channels,
kernel_size=3,
stride=stride)
self.norm2 = Norm(out_channels)
self.act2 = Act()
self.dropout = Dropout(dropout) if dropout else Identity()
self.conv2 = Conv2d(out_channels, out_channels, kernel_size=3)
self.shortcut = Conv2d(in_channels,
out_channels,
kernel_size=1,
stride=stride)
