我们从Python开源项目中，提取了以下6个代码示例，用于说明如何使用lasagne.layers.concat()。
def get_params_internal(self, **tags): # this gives ALL the vars (not the params values) return L.get_all_params( # this lasagne function also returns all var below the passed layers L.concat(self._output_layers), **tags )
def build_model(): net = {} net['input'] = InputLayer((None, 512*20, 3, 3)) au_fc_layers=[] for i in range(20): net['roi_AU_N_'+str(i)]=SliceLayer(net['input'],indices=slice(i*512,(i+1)*512),axis=1) #try to adding upsampling here for more conv net['Roi_upsample_'+str(i)]=Upscale2DLayer(net['roi_AU_N_'+str(i)],scale_factor=2) net['conv_roi_'+str(i)]=ConvLayer(net['Roi_upsample_'+str(i)],512,3) net['au_fc_'+str(i)]=DenseLayer(net['conv_roi_'+str(i)],num_units=150) au_fc_layers+=[net['au_fc_'+str(i)]] # net['local_fc']=concat(au_fc_layers) net['local_fc2']=DenseLayer(net['local_fc'],num_units=2048) net['local_fc_dp']=DropoutLayer(net['local_fc2'],p=0.5) # net['fc_comb']=concat([net['au_fc_layer'],net['local_fc_dp']]) # net['fc_dense']=DenseLayer(net['fc_comb'],num_units=1024) # net['fc_dense_dp']=DropoutLayer(net['fc_dense'],p=0.3) net['real_out']=DenseLayer(net['local_fc_dp'],num_units=12,nonlinearity=sigmoid) # net['final']=concat([net['pred_pos_layer'],net['output_layer']]) return net
def __create_toplogy__(self, input_var_first=None, input_var_second=None): # define network topology if (self.conf.rep % 2 != 0): raise ValueError("Representation size should be divisible by two as it's formed by combining two crossmodal translations", self.conf.rep) # input layers l_in_first = InputLayer(shape=(self.conf.batch_size, self.conf.mod1size), input_var=input_var_first) l_in_second = InputLayer(shape=(self.conf.batch_size, self.conf.mod2size), input_var=input_var_second) # first -> second l_hidden1_first = DenseLayer(l_in_first, num_units=self.conf.hdn, nonlinearity=self.conf.act, W=GlorotUniform()) # enc1 l_hidden2_first = DenseLayer(l_hidden1_first, num_units=self.conf.rep//2, nonlinearity=self.conf.act, W=GlorotUniform()) # enc2 l_hidden2_first_d = DropoutLayer(l_hidden2_first, p=self.conf.dropout) l_hidden3_first = DenseLayer(l_hidden2_first_d, num_units=self.conf.hdn, nonlinearity=self.conf.act, W=GlorotUniform()) # dec1 l_out_first = DenseLayer(l_hidden3_first, num_units=self.conf.mod2size, nonlinearity=self.conf.act, W=GlorotUniform()) # dec2 if self.conf.untied: # FREE l_hidden1_second = DenseLayer(l_in_second, num_units=self.conf.hdn, nonlinearity=self.conf.act, W=GlorotUniform()) # enc1 l_hidden2_second = DenseLayer(l_hidden1_second, num_units=self.conf.rep//2, nonlinearity=self.conf.act, W=GlorotUniform()) # enc2 l_hidden2_second_d = DropoutLayer(l_hidden2_second, p=self.conf.dropout) l_hidden3_second = DenseLayer(l_hidden2_second_d, num_units=self.conf.hdn, nonlinearity=self.conf.act, W=GlorotUniform()) # dec1 l_out_second = DenseLayer(l_hidden3_second, num_units=self.conf.mod1size, nonlinearity=self.conf.act, W=GlorotUniform()) # dec2 else: # TIED middle l_hidden1_second = DenseLayer(l_in_second, num_units=self.conf.hdn, nonlinearity=self.conf.act, W=GlorotUniform()) # enc1 l_hidden2_second = DenseLayer(l_hidden1_second, num_units=self.conf.rep//2, nonlinearity=self.conf.act, W=l_hidden3_first.W.T) # enc2 l_hidden2_second_d = DropoutLayer(l_hidden2_second, p=self.conf.dropout) l_hidden3_second = DenseLayer(l_hidden2_second_d, num_units=self.conf.hdn, nonlinearity=self.conf.act, W=l_hidden2_first.W.T) # dec1 l_out_second = DenseLayer(l_hidden3_second, num_units=self.conf.mod1size, nonlinearity=self.conf.act, W=GlorotUniform()) # dec2 l_out = concat([l_out_first, l_out_second]) return l_out, l_hidden2_first, l_hidden2_second
