Mercurial > pylearn
diff algorithms/logistic_regression.py @ 497:a272f4cbf004
'x' => 'input'
'y' => 'output'
| author | Joseph Turian <turian@gmail.com> |
|---|---|
| date | Tue, 28 Oct 2008 12:25:04 -0400 |
| parents | 7560817a07e8 |
| children | a419edf4e06c |
line wrap: on
line diff
--- a/algorithms/logistic_regression.py Tue Oct 28 12:09:49 2008 -0400 +++ b/algorithms/logistic_regression.py Tue Oct 28 12:25:04 2008 -0400 @@ -18,10 +18,10 @@ self.lr = 0.01 self.__hide__ = ['params'] - def __init__(self, x=None, targ=None, w=None, b=None, lr=None, regularize=False): + def __init__(self, input=None, targ=None, w=None, b=None, lr=None, regularize=False): super(Module_Nclass, self).__init__() #boilerplate - self.x = x if x is not None else T.matrix() + self.input = input if input is not None else T.matrix('input') self.targ = targ if targ is not None else T.lvector() self.w = w if w is not None else module.Member(T.dmatrix()) @@ -30,22 +30,22 @@ self.params = [p for p in [self.w, self.b] if p.owner is None] - xent, y = nnet.crossentropy_softmax_1hot( - T.dot(self.x, self.w) + self.b, self.targ) + xent, output = nnet.crossentropy_softmax_1hot( + T.dot(self.input, self.w) + self.b, self.targ) sum_xent = T.sum(xent) - self.y = y + self.output = output self.sum_xent = sum_xent self.cost = sum_xent #define the apply method - self.pred = T.argmax(T.dot(self.x, self.w) + self.b, axis=1) - self.apply = module.Method([self.x], self.pred) + self.pred = T.argmax(T.dot(self.input, self.w) + self.b, axis=1) + self.apply = module.Method([self.input], self.pred) if self.params: gparams = T.grad(sum_xent, self.params) - self.update = module.Method([self.x, self.targ], sum_xent, + self.update = module.Method([self.input, self.targ], sum_xent, updates = dict((p, p - self.lr * g) for p, g in zip(self.params, gparams))) class Module(module.FancyModule): @@ -58,10 +58,10 @@ self.lr = 0.01 self.__hide__ = ['params'] - def __init__(self, x=None, targ=None, w=None, b=None, lr=None, regularize=False): + def __init__(self, input=None, targ=None, w=None, b=None, lr=None, regularize=False): super(Module, self).__init__() #boilerplate - self.x = x if x is not None else T.matrix() + self.input = input if input is not None else T.matrix('input') self.targ = targ if targ is not None else T.lcol() self.w = w if w is not None else module.Member(T.dmatrix()) @@ -70,23 +70,23 @@ self.params = [p for p in [self.w, self.b] if p.owner is None] - y = nnet.sigmoid(T.dot(self.x, self.w)) - xent = -self.targ * T.log(y) - (1.0 - self.targ) * T.log(1.0 - y) + output = nnet.sigmoid(T.dot(self.x, self.w)) + xent = -self.targ * T.log(output) - (1.0 - self.targ) * T.log(1.0 - output) sum_xent = T.sum(xent) - self.y = y + self.output = output self.xent = xent self.sum_xent = sum_xent self.cost = sum_xent #define the apply method - self.pred = (T.dot(self.x, self.w) + self.b) > 0.0 - self.apply = module.Method([self.x], self.pred) + self.pred = (T.dot(self.input, self.w) + self.b) > 0.0 + self.apply = module.Method([self.input], self.pred) #if this module has any internal parameters, define an update function for them if self.params: gparams = T.grad(sum_xent, self.params) - self.update = module.Method([self.x, self.targ], sum_xent, + self.update = module.Method([self.input, self.targ], sum_xent, updates = dict((p, p - self.lr * g) for p, g in zip(self.params, gparams)))