chainer_chemistry.models.WeaveNet¶
-
class
chainer_chemistry.models.WeaveNet(weave_channels=None, hidden_dim=16, n_atom=20, n_sub_layer=1, n_atom_types=117, readout_mode='sum')[source]¶ WeaveNet implementation
Parameters: - weave_channels (list) – list of int, output dimension for each weave module
- hidden_dim (int) – hidden dim
- n_atom (int) – number of atom of input array
- n_sub_layer (int) – number of layer for each AtomToPair, PairToAtom layer
- n_atom_types (int) – number of atom id
- readout_mode (str) – ‘sum’ or ‘max’ or ‘summax’
-
__init__(weave_channels=None, hidden_dim=16, n_atom=20, n_sub_layer=1, n_atom_types=117, readout_mode='sum')[source]¶ Initialize self. See help(type(self)) for accurate signature.
Methods
__init__([weave_channels, hidden_dim, …])Initialize self. add_hook(hook[, name])Registers a link hook. add_link(name, link)Registers a child link to this chain. add_param(name[, shape, dtype, initializer])Registers a parameter to the link. add_persistent(name, value)Registers a persistent value to the link. addgrads(link)Accumulates gradient values from given link. children()Returns a generator of all child links. cleargrads()Clears all gradient arrays. copy([mode])Copies the link hierarchy to new one. copyparams(link[, copy_persistent])Copies all parameters from given link. count_params()Counts the total number of parameters. delete_hook(name)Unregisters the link hook. disable_update()Disables update rules of all parameters under the link hierarchy. enable_update()Enables update rules of all parameters under the link hierarchy. init_scope()Creates an initialization scope. links([skipself])Returns a generator of all links under the hierarchy. namedlinks([skipself])Returns a generator of all (path, link) pairs under the hierarchy. namedparams([include_uninit])Returns a generator of all (path, param) pairs under the hierarchy. params([include_uninit])Returns a generator of all parameters under the link hierarchy. register_persistent(name)Registers an attribute of a given name as a persistent value. repeat(n_repeat[, mode])Repeats this link multiple times to make a Sequential.serialize(serializer)Serializes the link object. to_cpu()Copies parameter variables and persistent values to CPU. to_gpu([device])Copies parameter variables and persistent values to GPU. to_intel64()Copies parameter variables and persistent values to CPU. zerograds()Initializes all gradient arrays by zero. Attributes
local_link_hooksOrdered dictionary of registered link hooks. update_enabledTrueif at least one parameter has an update rule enabled.within_init_scopeTrue if the current code is inside of an initialization scope. xpArray module for this link.