def test_multi_convolutional_feature_map_fprop():
cplane1 = ConvolutionalPlane((5, 5), (20, 20), bias=False)
cplane2 = ConvolutionalPlane((5, 5), (20, 20), bias=False)
sigmoid = TanhSigmoid((16, 16), bias=True)
mfmap = MultiConvolutionalFeatureMap((5, 5), (20, 20), 2)
mfmap.initialize()
cplane1.params[:] = mfmap.planes[0].params
cplane2.params[:] = mfmap.planes[1].params
sigmoid.params[:] = mfmap.params[0:1]
inputs1 = random.normal(size=(20, 20))
inputs2 = random.normal(size=(20, 20))
control = sigmoid.fprop(cplane1.fprop(inputs1) + cplane2.fprop(inputs2))
mfmap_out = mfmap.fprop([inputs1, inputs2])
assert_array_almost_equal(control, mfmap_out)
def __init__(self,
fsize,
imsize,
num,
inner=TANH_INNER,
outer=TANH_OUTER,
**kwargs):
"""
Construct a MultiConvolutionalFeatureMap.
All parameters are as in ConvolutionalFeatureMap; num is the
number of planes this MCFM has (and the length of the list
that fprop, bprop and grad expect for the "inputs" argument).
"""
# Filter size times the number of filters, plus a bias
filter_elems = np.prod(fsize)
nparams = filter_elems * num + 1
outsize = ConvolutionalPlane.outsize_from_imsize_and_fsize(
imsize, fsize)
super(MultiConvolutionalFeatureMap, self).__init__(outsize,
True,
nparams=nparams,
**kwargs)
self.planes = []
assert num > 0
for index in xrange(num):
param_range = slice(1 + (filter_elems * index),
1 + (filter_elems * (index + 1)))
thisparam = self.params[param_range]
thisgrad = self._grad[param_range]
thisplane = ConvolutionalPlane(fsize,
imsize,
params=thisparam,
grad=thisgrad,
bias=False)
self.planes.append(thisplane)
self._out_array = np.empty(outsize)
def test_multi_convolutional_feature_map_fprop():
cplane1 = ConvolutionalPlane((5, 5), (20, 20), bias=False)
cplane2 = ConvolutionalPlane((5, 5), (20, 20), bias=False)
sigmoid = TanhSigmoid((16, 16), bias=True)
mfmap = MultiConvolutionalFeatureMap((5, 5), (20, 20), 2)
mfmap.initialize()
cplane1.params[:] = mfmap.planes[0].params
cplane2.params[:] = mfmap.planes[1].params
sigmoid.params[:] = mfmap.params[0:1]
inputs1 = random.normal(size=(20, 20))
inputs2 = random.normal(size=(20, 20))
control = sigmoid.fprop(cplane1.fprop(inputs1) + cplane2.fprop(inputs2))
mfmap_out = mfmap.fprop([inputs1, inputs2])
assert_array_almost_equal(control, mfmap_out)
def __init__(self, fsize, imsize, num, inner=TANH_INNER, outer=TANH_OUTER,
**kwargs):
"""
Construct a MultiConvolutionalFeatureMap.
All parameters are as in ConvolutionalFeatureMap; num is the
number of planes this MCFM has (and the length of the list
that fprop, bprop and grad expect for the "inputs" argument).
"""
# Filter size times the number of filters, plus a bias
filter_elems = np.prod(fsize)
nparams = filter_elems * num + 1
outsize = ConvolutionalPlane.outsize_from_imsize_and_fsize(
imsize,
fsize
)
super(MultiConvolutionalFeatureMap, self).__init__(
outsize,
True,
nparams=nparams,
**kwargs
)
self.planes = []
assert num > 0
for index in xrange(num):
param_range = slice(1 + (filter_elems * index),
1 + (filter_elems * (index + 1)))
thisparam = self.params[param_range]
thisgrad = self._grad[param_range]
thisplane = ConvolutionalPlane(fsize, imsize,
params=thisparam,
grad=thisgrad,
bias=False
)
self.planes.append(thisplane)
self._out_array = np.empty(outsize)
def test_convolutional_plane_params_gradient_no_bias():
module = ConvolutionalPlane((5, 5), (20, 20), bias=False)
module.initialize()
inputs = random.normal(size=(20, 20))
params = random.normal(size=len(module.params))
check_parameter_gradient(module, inputs, params)
def __init__(self, fsize, imsize):
"""Construct a feature map with given filter size and image size."""
super(NaiveConvolutionalFeatureMap, self).__init__()
self.convolution = ConvolutionalPlane(fsize, imsize)
self.nonlinearity = TanhSigmoid(self.convolution.outsize)
class NaiveConvolutionalFeatureMap(BaseBPropComponent):
"""
One way to implement a standard feature map that takes input from a
single lower-level image. This serves two purposes: to demonstrate
how to write new learning modules by composing two existing modules,
and to serve as a sanity check for the more efficient implementation,
ConvolutionalFeatureMap.
Has, as members, a ConvolutionalPlane with standard bias configuration
and a TanhSigmoid object that does the squashing.
This is a little wasteful since each of the modules has separate output
array members. See FeatureMap for a slightly more memory efficient
implementation that uses subclassing.
"""
def __init__(self, fsize, imsize):
"""Construct a feature map with given filter size and image size."""
super(NaiveConvolutionalFeatureMap, self).__init__()
self.convolution = ConvolutionalPlane(fsize, imsize)
self.nonlinearity = TanhSigmoid(self.convolution.outsize)
def fprop(self, inputs):
"""Forward propagate input through this module."""
return self.nonlinearity.fprop(self.convolution.fprop(inputs))
def bprop(self, dout, inputs):
"""
Backpropagate derivatives through this module to get derivatives
with respect to this module's input.
"""
squash_inputs = self.convolution.fprop(inputs)
squash_derivs = self.nonlinearity.bprop(dout, squash_inputs)
return self.convolution.bprop(squash_derivs, inputs)
def grad(self, dout, inputs):
"""
Gradient of the error with respect to the parameters of this module.
Parameters:
* dout -- derivative of the outputs of this module
(will be size of input - size of filter + 1, elementwise)
* inputs -- inputs to this module
"""
squash_inputs = self.convolution.fprop(inputs)
squash_derivs = self.nonlinearity.bprop(dout, squash_inputs)
return self.convolution.grad(squash_derivs, inputs)
def initialize(self):
"""Initialize the module's weights."""
self.convolution.initialize()
@property
def outsize(self):
"""Output size."""
return self.convolution.outsize
@property
def imsize(self):
"""Image input size."""
return self.convolution.imsize
@property
def fsize(self):
"""Filter shape."""
return self.convolution.filter.shape
def __init__(self, fsize, imsize):
"""Construct a feature map with given filter size and image size."""
super(NaiveConvolutionalFeatureMap, self).__init__()
self.convolution = ConvolutionalPlane(fsize, imsize)
self.nonlinearity = TanhSigmoid(self.convolution.outsize)
class NaiveConvolutionalFeatureMap(BaseBPropComponent):
"""
One way to implement a standard feature map that takes input from a
single lower-level image. This serves two purposes: to demonstrate
how to write new learning modules by composing two existing modules,
and to serve as a sanity check for the more efficient implementation,
ConvolutionalFeatureMap.
Has, as members, a ConvolutionalPlane with standard bias configuration
and a TanhSigmoid object that does the squashing.
This is a little wasteful since each of the modules has separate output
array members. See FeatureMap for a slightly more memory efficient
implementation that uses subclassing.
"""
def __init__(self, fsize, imsize):
"""Construct a feature map with given filter size and image size."""
super(NaiveConvolutionalFeatureMap, self).__init__()
self.convolution = ConvolutionalPlane(fsize, imsize)
self.nonlinearity = TanhSigmoid(self.convolution.outsize)
def fprop(self, inputs):
"""Forward propagate input through this module."""
return self.nonlinearity.fprop(self.convolution.fprop(inputs))
def bprop(self, dout, inputs):
"""
Backpropagate derivatives through this module to get derivatives
with respect to this module's input.
"""
squash_inputs = self.convolution.fprop(inputs)
squash_derivs = self.nonlinearity.bprop(dout, squash_inputs)
return self.convolution.bprop(squash_derivs, inputs)
def grad(self, dout, inputs):
"""
Gradient of the error with respect to the parameters of this module.
Parameters:
* dout -- derivative of the outputs of this module
(will be size of input - size of filter + 1, elementwise)
* inputs -- inputs to this module
"""
squash_inputs = self.convolution.fprop(inputs)
squash_derivs = self.nonlinearity.bprop(dout, squash_inputs)
return self.convolution.grad(squash_derivs, inputs)
def initialize(self):
"""Initialize the module's weights."""
self.convolution.initialize()
@property
def outsize(self):
"""Output size."""
return self.convolution.outsize
@property
def imsize(self):
"""Image input size."""
return self.convolution.imsize
@property
def fsize(self):
"""Filter shape."""
return self.convolution.filter.shape
def test_convolutional_plane_params_gradient_no_bias():
module = ConvolutionalPlane((5, 5), (20, 20), bias=False)
module.initialize()
inputs = random.normal(size=(20, 20))
params = random.normal(size=len(module.params))
check_parameter_gradient(module, inputs, params)
