def initialize(self, outchn, stride):
self.stride = stride
self.outchn = outchn
self.bn0 = M.BatchNorm()
self.c1 = M.ConvLayer(3,
outchn,
activation=M.PARAM_PRELU,
usebias=False,
batch_norm=True)
self.c2 = M.ConvLayer(3,
outchn,
stride=stride,
usebias=False,
batch_norm=True)
# se module
#self.c3 = M.ConvLayer(1, outchn//16, activation=M.PARAM_PRELU)
#self.c4 = M.ConvLayer(1, outchn, activation=M.PARAM_SIGMOID)
# shortcut
self.sc = M.ConvLayer(1,
outchn,
stride=stride,
usebias=False,
batch_norm=True)
def initialize(self, channel_list, blocknum_list, embedding_size, embedding_bn=True): self.head = HeadBlock(channel_list[0]) self.body = nn.ModuleList() for num, chn in zip(blocknum_list, channel_list[1:]): for i in range(num): self.body.append(ResBlock_v1(chn, 2 if i==0 else 1)) self.emb_bn = M.BatchNorm() self.embedding = M.Dense(embedding_size, batch_norm=embedding_bn, affine=False)
def initialize(self,
channel_list,
blocknum_list,
embedding_size,
embedding_bn=True):
self.c1 = M.ConvLayer(3,
channel_list[0],
1,
usebias=False,
activation=M.PARAM_PRELU,
batch_norm=True)
# self.u1 = ResBlock_v1(channel_list[1], stride=2)
self.stage1 = Stage(channel_list[1], blocknum_list[0])
self.stage2 = Stage(channel_list[2], blocknum_list[1])
self.stage3 = Stage(channel_list[3], blocknum_list[2])
self.stage4 = Stage(channel_list[4], blocknum_list[3])
self.bn1 = M.BatchNorm()
self.fc1 = M.Dense(512, usebias=False, batch_norm=True)
