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, out_dim, hidden_dim=16, n_layers=4, max_degree=6, n_atom_types=MAX_ATOMIC_NUM, concat_hidden=False, model_params=None): super(NFP_attention, self).__init__() num_degree_type = max_degree + 1 with self.init_scope(): #self.embed = chainer_chemistry.links.EmbedAtomID( # in_size=n_atom_types, out_size=hidden_dim) #self.layers = chainer.ChainList( # *[NFPUpdate(hidden_dim, hidden_dim, max_degree=max_degree) # for _ in range(n_layers)]) #self.read_out_layers = chainer.ChainList( # *[NFPReadout(hidden_dim, out_dim) # for _ in range(n_layers)]) self.attention_layer_1 = chainer.links.Linear(out_dim,1) self.out_dim = out_dim self.hidden_dim = hidden_dim self.max_degree = max_degree self.num_degree_type = num_degree_type self.n_layers = n_layers self.concat_hidden = concat_hidden self.build_fp1 = Finger_print.ECFP(model_params) self.build_fp2 = Finger_print.FCFP(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),
)