chainer_chemistry.models.Regressor¶

class chainer_chemistry.models.Regressor(predictor, lossfun=<function mean_squared_error>, metrics_fun=None, label_key=-1, device=-1)[source]¶

A simple regressor model.

This is an example of chain that wraps another chain. It computes the loss and metrics based on a given input/label pair.

Parameters:

predictor (Link) – Predictor network.
lossfun (function) – Loss function.
metrics_fun (function or dict or None) – Function that computes metrics.
label_key (int or str) – Key to specify label variable from arguments. When it is int, a variable in positional arguments is used. And when it is str, a variable in keyword arguments is used.
device (int) – GPU device id of this Regressor to be used. -1 indicates to use in CPU.

predictor¶

Predictor network.

Type:	Link

lossfun¶

Loss function.

Type:	function

y¶

Prediction for the last minibatch.

Type:	Variable

loss¶

Loss value for the last minibatch.

Type:	Variable

metrics¶

Metrics computed in last minibatch

Type:	dict

compute_metrics¶

If True, compute metrics on the forward computation. The default value is True.

Type:	bool

__init__(predictor, lossfun=<function mean_squared_error>, metrics_fun=None, label_key=-1, device=-1)[source]¶: Initialize self. See help(type(self)) for accurate signature.

Methods

`__init__`(predictor[, lossfun, metrics_fun, …])	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.
`get_device`()
`init_scope`()	Creates an initialization scope.
`initialize`([device])	Initialization of the model.
`links`([skipself])	Returns a generator of all links under the hierarchy.
`load_pickle`(filepath[, device])	Load the model from filepath of pickle file, and send to device
`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.
`predict`(data[, batchsize, converter, …])	Predict label of each category by taking .
`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`.
`save_pickle`(filepath[, protocol])	Save the model to filepath as a pickle file
`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.
`update_device`([device])
`zerograds`()	Initializes all gradient arrays by zero.

Attributes

`compute_metrics`
`local_link_hooks`	Ordered dictionary of registered link hooks.
`update_enabled`	`True` if at least one parameter has an update rule enabled.
`within_init_scope`	True if the current code is inside of an initialization scope.
`xp`	Array module for this link.