Created by: 20092136

def dnn_net(seq_dim,                                                                                                                            
                feat_dim,
                class_dim,
                emb_dim=128,
                hid_dim=512,
                lstm_dim=128,
                is_predict=False):
    """                     
    DNN 
    """                     
    bias_attr = ParameterAttribute(initial_std=0., l2_rate=0.0001)
    fc_para_attr = ParameterAttribute(learning_rate=2e-3)
    lstm_para_attr = ParameterAttribute(initial_std=0., learning_rate=2e-3)#, sparse_update=True)
    sparse_up = ParameterAttribute(sparse_update=True)
    para_attr = [lstm_para_attr, fc_para_attr]
    relu = ReluActivation()
                            
    feat_data = data_layer("feat", feat_dim)
    feat_layer_1 = fc_layer(input=feat_data, size=hid_dim, act=relu,
                   bias_attr=bias_attr, param_attr=sparse_up)
    feat_layer_2 = fc_layer(input=feat_layer_1, size=hid_dim, bias_attr=bias_attr)
    feat_layer_3 = fc_layer(input=feat_layer_2, size=hid_dim, bias_attr=bias_attr)
                            
    output = fc_layer(name='fc_ly_4', input=feat_layer_3, size=class_dim, act=SoftmaxActivation(),
                    bias_attr=bias_attr, param_attr=fc_para_attr)
                            
    if is_predict:          
        outputs(output)  
    else:                   
        outputs(            
            classification_cost(input=output, label=data_layer('label', 1), 

obj.input_types = [sparse_non_value_slot(6121), integer_value(888)]

use_remote_sparse = True,