audioClassifier_lasagne.py 文件源码

def build_network(self, input_var=None):
        if not input_var is None: self.sinputs = input_var

        self.network['input'] = lasagne.layers.InputLayer(shape=(self.batch_size, 1, self.input_size['audio'][0],self.input_size['audio'][1]),
                                                          input_var=self.sinputs[0])

        self.network['Conv2D_1'] = batch_norm(lasagne.layers.Conv2DLayer(
            lasagne.layers.dropout(self.network['input'], p=self.dropout_rates[0]) , num_filters=25, filter_size=(5, 5),
            nonlinearity=lasagne.nonlinearities.tanh,
            W=lasagne.init.GlorotUniform()))

        self.network['MaxPool2D_1'] = lasagne.layers.MaxPool2DLayer(self.network['Conv2D_1'], pool_size=(1, 1))

        self.network['FC_1'] = batch_norm(lasagne.layers.DenseLayer(
            lasagne.layers.dropout(self.network['MaxPool2D_1'], p=self.dropout_rates[1]),
            num_units=self.fc_layers[0],
            nonlinearity=lasagne.nonlinearities.tanh))

        self.network['FC_N'] = batch_norm(lasagne.layers.DenseLayer(lasagne.layers.dropout(self.network['FC_1'], p=self.dropout_rates[2]),
            num_units=self.fc_layers[1],
            nonlinearity=lasagne.nonlinearities.tanh))


        self.network['prob'] =  batch_norm(lasagne.layers.DenseLayer(
            lasagne.layers.dropout(self.network['FC_N'], p=self.dropout_rates[3]),
            num_units=self.nclasses,
            nonlinearity=lasagne.nonlinearities.softmax))

        return self.network