Did I find the right examples for you? yes no      Crawl my project      Python Jobs

All Samples(21)  |  Call(18)  |  Derive(0)  |  Import(3)

src/p/y/pylearn2-HEAD/pylearn2/models/dbm/layer.py   pylearn2(Download)
from pylearn2.space import VectorSpace, CompositeSpace, Conv2DSpace, Space
from pylearn2.utils import is_block_gradient
from pylearn2.utils import sharedX, safe_zip, py_integer_types, block_gradient
from pylearn2.utils.rng import make_theano_rng
"""
            self.learn_init_inpainting_state = 0
        if not self.learn_init_inpainting_state:
            masked_mean = block_gradient(masked_mean)
        masked_mean.name = 'masked_mean'
 
        z ,= owner.inputs
        if block_grad:
            z = block_gradient(z)
 
        if V.ndim != V_hat.ndim:
            self.learn_init_inpainting_state = 1
        if not self.learn_init_inpainting_state:
            rval = block_gradient(rval)
        return rval
 
            self.learn_init_inpainting_state = True
        if not self.learn_init_inpainting_state:
            masked_mu = block_gradient(masked_mu)
        masked_mu.name = 'masked_mu'
 

src/p/y/pylearn2-HEAD/pylearn2/models/dbm/inference_procedure.py   pylearn2(Download)
from pylearn2.models.dbm import block, flatten
from pylearn2.models.dbm.layer import Softmax
from pylearn2.utils import safe_izip, block_gradient, safe_zip
 
 
                if block_grad == i:
                    H_hat = block(H_hat)
                    V_hat = block_gradient(V_hat)
 
                history.append((new_V, list(H_hat)))
 
        if block_grad == 1:
            V_hat = block_gradient(V_hat)
            V_hat_unmasked = block_gradient(V_hat_unmasked)
            H_hat = block(H_hat)
            #end for j
            if block_grad == i:
                V_hat = block_gradient(V_hat)
                V_hat_unmasked = block_gradient(V_hat_unmasked)
                H_hat = block(H_hat)

src/p/y/pylearn2-HEAD/pylearn2/models/dbm/__init__.py   pylearn2(Download)
from pylearn2.expr.nnet import inverse_sigmoid_numpy
from pylearn2.blocks import Block
from pylearn2.utils import block_gradient
from pylearn2.utils.rng import make_theano_rng
 
            new.append(block(elem))
        else:
            new.append(block_gradient(elem))
    if isinstance(l, tuple):
        return tuple(new)