apunkt/GPy
1
0
Fork 0
mirror of https://github.com/SheffieldML/GPy.git synced 2026-05-08 11:32:39 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions

some work on the linear mapping

Browse source
This commit is contained in:
James Hensman 2014-03-20 12:22:57 +00:00
parent 6f9c97ee72
commit dfe325b571
2 changed files with 15 additions and 30 deletions
Download patch file Download diff file Expand all files Collapse all files

4
GPy/core/mapping.py
View file

@ -10,11 +10,11 @@ class Mapping(Parameterized):
Base model for shared behavior between models that can act like a mapping. Base model for shared behavior between models that can act like a mapping.
""" """
def __init__(self, input_dim, output_dim): def __init__(self, input_dim, output_dim, name='mapping'):
self.input_dim = input_dim self.input_dim = input_dim
self.output_dim = output_dim self.output_dim = output_dim
super(Mapping, self).__init__() super(Mapping, self).__init__(name=name)
# Model.__init__(self) # Model.__init__(self)
# All leaf nodes should call self._set_params(self._get_params()) at # All leaf nodes should call self._set_params(self._get_params()) at
# the end # the end

35
GPy/mappings/linear.py
View file

@ -3,6 +3,7 @@
import numpy as np import numpy as np
from ..core.mapping import Mapping from ..core.mapping import Mapping
from ..core.parameterization import Param
class Linear(Mapping): class Linear(Mapping):
""" """
@ -19,35 +20,19 @@ class Linear(Mapping):
""" """
def __init__(self, input_dim=1, output_dim=1): def __init__(self, input_dim=1, output_dim=1, name='linear_map'):
self.name = 'linear' Mapping.__init__(self, input_dim=input_dim, output_dim=output_dim, name=name)
Mapping.__init__(self, input_dim=input_dim, output_dim=output_dim) self.W = Param('W',np.array((self.input_dim, self.output_dim)))
self.num_params = self.output_dim*(self.input_dim + 1) self.bias = Param('bias',np.array(self.output_dim))
self.W = np.array((self.input_dim, self.output_dim)) self.add_parameters(self.W, self.bias)
self.bias = np.array(self.output_dim)
self.randomize()
def _get_param_names(self):
return sum([['W_%i_%i' % (n, d) for d in range(self.output_dim)] for n in range(self.input_dim)], []) + ['bias_%i' % d for d in range(self.output_dim)]
def _get_params(self):
return np.hstack((self.W.flatten(), self.bias))
def _set_params(self, x):
self.W = x[:self.input_dim * self.output_dim].reshape(self.input_dim, self.output_dim).copy()
self.bias = x[self.input_dim*self.output_dim:].copy()
def randomize(self):
self.W = np.random.randn(self.input_dim, self.output_dim)/np.sqrt(self.input_dim + 1)
self.bias = np.random.randn(self.output_dim)/np.sqrt(self.input_dim + 1)
def f(self, X): def f(self, X):
return np.dot(X,self.W) + self.bias return np.dot(X,self.W) + self.bias
def df_dtheta(self, dL_df, X): def df_dtheta(self, dL_df, X):
self._df_dW = (dL_df[:, :, None]*X[:, None, :]).sum(0).T df_dW = (dL_df[:, :, None]*X[:, None, :]).sum(0).T
self._df_dbias = (dL_df.sum(0)) df_dbias = (dL_df.sum(0))
return np.hstack((self._df_dW.flatten(), self._df_dbias)) return np.hstack((df_dW.flatten(), df_dbias))
def df_dX(self, dL_df, X): def dL_dX(self, dL_df, X):
return (dL_df[:, None, :]*self.W[None, :, :]).sum(2) return (dL_df[:, None, :]*self.W[None, :, :]).sum(2)