def __init__(self, out_dim, hidden_channels=32, n_update_layers=4,
n_atom_types=MAX_ATOMIC_NUM,
use_batch_norm=False, readout=None, dropout_ratio=0.5):
super(RSGCN, self).__init__()
in_dims = [hidden_channels for _ in range(n_update_layers)]
out_dims = [hidden_channels for _ in range(n_update_layers)]
out_dims[n_update_layers - 1] = out_dim
if readout is None:
readout = GeneralReadout()
with self.init_scope():
self.embed = chainer_chemistry.links.EmbedAtomID(out_size=hidden_channels, in_size=n_atom_types)
self.gconvs = chainer.ChainList(
*[RSGCNUpdate(in_dims[i], out_dims[i])
for i in range(n_update_layers)])
if use_batch_norm:
self.bnorms = chainer.ChainList(
*[chainer_chemistry.links.GraphBatchNormalization(
out_dims[i]) for i in range(n_update_layers)])
else:
self.bnorms = [None for _ in range(n_update_layers)]
if isinstance(readout, chainer.Link):
self.readout = readout
if not isinstance(readout, chainer.Link):
self.readout = readout
self.out_dim = out_dim
self.hidden_channels = hidden_channels
self.n_update_layers = n_update_layers
self.dropout_ratio = dropout_ratio
def __init__(self, n_channel, n_layer, n_atom, mode='sum'):
super(PairToAtom, self).__init__()
with self.init_scope():
self.linearLayer = chainer.ChainList(
*[links.Linear(None, n_channel) for _ in range(n_layer)])
self.readout = GeneralReadout(mode=mode)
self.n_atom = n_atom
self.n_channel = n_channel
self.mode = mode
def __init__(
self,
out_dim,
hidden_dim=32,
hidden_dim_super=32,
n_layers=4,
n_heads=8,
n_atom_types=MAX_ATOMIC_NUM,
n_super_feature=2 + 2 +
MAX_ATOMIC_NUM * 2, #4 + 2 + 4 + MAX_ATOMIC_NUM*2,
use_batch_norm=False,
readout=None,
dropout_ratio=0.5):
super(RSGCN_GWM, self).__init__()
in_dims = [hidden_dim for _ in range(n_layers)]
out_dims = [hidden_dim for _ in range(n_layers)]
out_dims[n_layers - 1] = out_dim
if readout is None:
readout = GeneralReadout()
with self.init_scope():
self.embed = chainer_chemistry.links.EmbedAtomID(
in_size=n_atom_types, out_size=hidden_dim)
self.gconvs = chainer.ChainList(*[
RSGCNUpdate(in_dims[i], out_dims[i]) for i in range(n_layers)
])
# GWM
self.embed_super = links.Linear(in_size=n_super_feature,
out_size=hidden_dim_super)
self.gwm = GWM(hidden_dim=hidden_dim,
hidden_dim_super=hidden_dim_super,
n_layers=n_layers,
n_heads=n_heads,
dropout_ratio=dropout_ratio,
tying_flag=False,
gpu=-1)
if use_batch_norm:
self.bnorms = chainer.ChainList(*[
chainer_chemistry.links.GraphBatchNormalization(
out_dims[i]) for i in range(n_layers)
])
else:
self.bnorms = [None for _ in range(n_layers)]
if isinstance(readout, chainer.Link):
self.readout = readout
self.linear_for_concat_super = links.Linear(in_size=None,
out_size=out_dim)
if not isinstance(readout, chainer.Link):
self.readout = readout
self.out_dim = out_dim
self.hidden_dim = hidden_dim
self.hidden_dim_super = hidden_dim_super
self.n_layers = n_layers
self.dropout_ratio = dropout_ratio
def __init__(self,
weave_channels=None,
hidden_dim=16,
n_atom=WEAVE_DEFAULT_NUM_MAX_ATOMS,
n_sub_layer=1,
n_atom_types=MAX_ATOMIC_NUM,
readout_mode='sum'):
weave_channels = weave_channels or WEAVENET_DEFAULT_WEAVE_CHANNELS
weave_module = [
WeaveModule(n_atom, c, n_sub_layer, readout_mode=readout_mode)
for c in weave_channels
]
super(WeaveNet, self).__init__()
with self.init_scope():
self.embed = EmbedAtomID(out_size=hidden_dim, in_size=n_atom_types)
self.weave_module = chainer.ChainList(*weave_module)
self.readout = GeneralReadout(mode=readout_mode)
self.readout_mode = readout_mode
def test_forward_cpu_assert_raises(data):
atom_data = data[0]
readout = GeneralReadout(mode='invalid')
with pytest.raises(ValueError):
cuda.to_cpu(readout(atom_data).data)
def readouts():
modes = ['sum', 'max', 'summax']
return (GeneralReadout(mode=mode) for mode in modes)