def __init__(self, model_params):
super(Main, self).__init__(
build_ecfp=Finger_print.ECFP(model_params),
build_fcfp=Finger_print.FCFP(model_params),
ecfp_attension=L.Linear(model_params['fp_length'], 1),
fcfp_attension=L.Linear(model_params['fp_length'], 1),
dnn=Deep_neural_network.DNN(model_params),
)
def __init__(self, model_params): super(Main, self).__init__( build_ecfp = Finger_print.ECFP(model_params), build_fcfp = Finger_print.FCFP(model_params), ecfp_attension_1 = L.Linear(model_params['fp_length'], model_params['importance_l1_size']), fcfp_attension_1 = L.Linear(model_params['fp_length'], model_params['importance_l1_size']), ecfp_attension_2 = L.Linear(model_params['importance_l1_size'], model_params['importance_l2_size']), fcfp_attension_2 = L.Linear(model_params['importance_l1_size'], model_params['importance_l2_size']), ecfp_attension_3 = L.Linear(model_params['importance_l2_size'],model_params['fp_length']), fcfp_attension_3 = L.Linear(model_params['importance_l2_size'],model_params['fp_length']), dnn = Deep_neural_network.DNN(model_params), )
def __init__(self, model_params):
initializer = chainer.initializers.HeNormal()
super(Main, self).__init__(
build_ecfp=Finger_print.ECFP(model_params),
build_fcfp=Finger_print.FCFP(model_params),
attention_layer1=L.Linear(2 * model_params['fp_length'],
model_params['importance_l1_size'],
initialW=initializer),
attention_layer2=L.Linear(model_params['importance_l1_size'],
model_params['importance_l2_size'],
initialW=initializer),
attention_layer3=L.Linear(model_params['importance_l2_size'],
2,
initialW=initializer),
dnn=Deep_neural_network.DNN(model_params),
)
def __init__(self, model_params): super(Main, self).__init__( fp = Finger_print.FP(model_params), dnn = Deep_neural_network.DNN(model_params), )
def __init__(self, model_params):
super(Main, self).__init__(
build_ecfc=Finger_print.ECFC(model_params),
dnn=Deep_neural_network.DNN(model_params),
)