def get_param_names_svh(num_inputs,
layer_sizes,
num_outputs,
weight_shapes,
granularity=None,
n_stoc_var=0):
"""
writes list of param_names for weight array which corresponds to (row-wise)
weight matrices and bias vector w and b,
as well as prior stochastic hyperparameters h (which are the
standard deviation / scale parameters of the prior distributions of the neural network parameters)
and likelihood variance stochastic parameters v (which are the variance parameters of the likelihood function).
"""
weight_shapes = tools.get_weight_shapes(num_inputs, layer_sizes,
num_outputs)
param_names = []
i = 0
if granularity == 'single':
param_names.append(('p1', 'h_{1}'))
i += 1
elif granularity == 'layer':
for _ in range(len(weight_shapes) / 2):
param_names.append(('p%i' % (i + 1), 'h_{%i}' % (i + 1)))
i += 1
elif granularity == 'input_size':
for w in range(len(weight_shapes) / 2):
for n in range(weight_shape[2 * w][0] +
1): #+1 is for bias hyperparam term
param_names.append(
('p%i' % (i + 1), 'h_{%i, %i}' % (w + 1, n + 1)))
i += 1
else: #no stochastic prior hyperparams
pass
if n_stoc_var:
for j in range(n_stoc_var):
param_names.append(('p%i' % (i + 1), 'v_{%i}' % (j + 1)))
i += 1
else: #no stochastic lhood variance parameters
pass
for j in range(len(weight_shapes) / 2):
weight_row = weight_shapes[2 * j][0]
weight_col = weight_shapes[2 * j][1]
bias = weight_shapes[2 * j + 1][0]
for k in range(weight_row):
for l in range(weight_col):
param_names.append(
('p%i' % (i + 1), 'w_{%i,%i,%i}' % (j + 1, k + 1, l + 1)))
i += 1
for k in range(bias):
param_names.append(('p%i' % (i + 1), 'b_{%i,%i}' % (j + 1, k + 1)))
i += 1
return param_names
def get_param_names(num_inputs, layer_sizes, num_outputs):
"""
writes list of param_names for weight array which corresponds to (row-wise)
weight matrices and bias vector w and b respectively.
Length of weight_shapes should be even
"""
weight_shapes = tools.get_weight_shapes(num_inputs, layer_sizes,
num_outputs)
param_names = []
i = 0
for j in range(len(weight_shapes) / 2):
weight_row = weight_shapes[2 * j][0]
weight_col = weight_shapes[2 * j][1]
bias = weight_shapes[2 * j + 1][0]
for k in range(weight_row):
for l in range(weight_col):
param_names.append(
('p%i' % (i + 1), 'w_{%i,%i,%i}' % (j + 1, k + 1, l + 1)))
i += 1
for k in range(bias):
param_names.append(('p%i' % (i + 1), 'b_{%i,%i}' % (j + 1, k + 1)))
i += 1
return param_names
def inverse_stoc_hyper_priors_test14():
"""
real nn arch with 16 nn params, two hyperparams, input_size granularity,
degen dependent params
"""
num_inputs = 1
layer_sizes = [3, 2]
num_outputs = 1
print "num weights"
n_dims = tools.calc_num_weights(num_inputs, layer_sizes, num_outputs)
print tools.calc_num_weights(num_inputs, layer_sizes, num_outputs)
weight_shapes = tools.get_weight_shapes(num_inputs, layer_sizes,
num_outputs)
print "weight shapes"
print tools.get_weight_shapes(num_inputs, layer_sizes, num_outputs)
granularity = 'input_size'
hyper_dependence_lengths = tools.get_hyper_dependence_lengths(
weight_shapes, granularity)
n_stoc = len(hyper_dependence_lengths)
print "n_stoc"
print n_stoc
print "granularity"
print tools.get_hyper_dependence_lengths(weight_shapes, granularity)
print "number of weights per layer"
print tools.calc_num_weights_layers(weight_shapes)
dependence_lengths = tools.get_degen_dependence_lengths(weight_shapes)
print "degen dependence lengths"
print tools.get_degen_dependence_lengths(weight_shapes)
hyperprior_types = [9, 7]
prior_types = [4, 5]
hyperprior_params = [[1., 2.], [2., 0.]]
prior_hyperparams = [0., 1.]
param_hyperprior_types = [0, 1, 0, 0, 1, 1, 1, 0, 0]
param_prior_types = [0, 1, 0, 1, 0, 0, 1, 1, 0]
prior = isp.inverse_stoc_hyper_prior(hyperprior_types, prior_types,
hyperprior_params, prior_hyperparams,
hyper_dependence_lengths,
dependence_lengths,
param_hyperprior_types,
param_prior_types, n_stoc, n_dims)
p = np.array([
0.1, 0.5, 0.6, 0.7, 0.8, 0.9, 0.4, 0.2, 0.1, 0.5, 0.7, 0.8, 0.9, 0.4,
0.2, 0.1, 0.5, 0.9, 0.2, 0.7, 0.4, 0.9, 0.3, 0.5, 0.6, 0.8
])
prior(p)
u = [0., 0., 0., 1., 1., 1., 0., 0., 1., 1., 0., 0., 0., 0., 1., 1., 0.]
v = [
4.35688457, 4.35688457, 4.35688457, 2., 2., 2., 1.47740087, 1.47740087,
1.28886271, 1.28886271, 2., 2., 2., 2., 2., 2.9938003, 4.35688457
]
print isp.gaussian_prior()(p[9], u[0], v[0])
print isp.gaussian_prior()(p[10], u[1], v[1])
print isp.gaussian_prior()(p[11], u[2], v[2])
print isp.laplace_prior()(p[12], u[3], v[3])
print isp.laplace_prior()(p[13], u[4], v[4])
print isp.laplace_prior()(p[14], u[5], v[5])
print isp.gaussian_prior()(p[15], u[6], v[6])
print isp.gaussian_prior()(p[16], u[7], v[7])
print isp.laplace_prior()(p[17], u[8], v[8])
print isp.laplace_prior()(p[18], u[9], v[9])
print isp.gaussian_prior()(p[19], u[10], v[10])
print isp.gaussian_prior()(p[20], u[11], v[11])
print isp.gaussian_prior()(p[21], u[12], v[12])
print isp.gaussian_prior()(p[22], u[13], v[13])
print isp.laplace_prior()(p[23], u[14], v[14])
print isp.laplace_prior()(p[24], u[15], v[15])
print isp.gaussian_prior()(p[25], u[16], v[16])
def inverse_stoc_hyper_priors_test9():
"""
real nn arch with 16 nn params, two hyperparams, layer granularity,
independent params
"""
num_inputs = 1
layer_sizes = [3, 2]
num_outputs = 1
print "num weights"
n_dims = tools.calc_num_weights(num_inputs, layer_sizes, num_outputs)
print tools.calc_num_weights(num_inputs, layer_sizes, num_outputs)
weight_shapes = tools.get_weight_shapes(num_inputs, layer_sizes,
num_outputs)
print "weight shapes"
print tools.get_weight_shapes(num_inputs, layer_sizes, num_outputs)
granularity = 'layer'
hyper_dependence_lengths = tools.get_hyper_dependence_lengths(
weight_shapes, granularity)
n_stoc = len(hyper_dependence_lengths)
print "number of weights per layer"
print tools.calc_num_weights_layers(weight_shapes)
dependence_lengths = tools.get_degen_dependence_lengths(weight_shapes,
independent=True)
print "degen dependence lengths"
print tools.get_degen_dependence_lengths(weight_shapes, independent=True)
hyperprior_types = [9, 7]
prior_types = [4]
hyperprior_params = [[1., 2.], [2., 0.]]
prior_hyperparams = [0.]
param_hyperprior_types = [1, 0, 1]
param_prior_types = [0]
prior = isp.inverse_stoc_hyper_prior(hyperprior_types, prior_types,
hyperprior_params, prior_hyperparams,
hyper_dependence_lengths,
dependence_lengths,
param_hyperprior_types,
param_prior_types, n_stoc, n_dims)
p = np.array([
0.1, 0.5, 0.6, 0.7, 0.8, 0.9, 0.4, 0.2, 0.1, 0.5, 0.7, 0.8, 0.9, 0.4,
0.2, 0.1, 0.5, 0.9, 0.2, 0.7
])
prior(p)
u = [0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0., 0.]
v = [
2., 2., 2., 2., 2., 2., 1.6986436, 1.6986436, 1.6986436, 1.6986436,
1.6986436, 1.6986436, 1.6986436, 1.6986436, 2., 2., 2.
]
print isp.gaussian_prior()(p[3], u[0], v[0])
print isp.gaussian_prior()(p[4], u[1], v[1])
print isp.gaussian_prior()(p[5], u[2], v[2])
print isp.gaussian_prior()(p[6], u[3], v[3])
print isp.gaussian_prior()(p[7], u[4], v[4])
print isp.gaussian_prior()(p[8], u[5], v[5])
print isp.gaussian_prior()(p[9], u[6], v[6])
print isp.gaussian_prior()(p[10], u[7], v[7])
print isp.gaussian_prior()(p[11], u[8], v[8])
print isp.gaussian_prior()(p[12], u[9], v[9])
print isp.gaussian_prior()(p[13], u[10], v[10])
print isp.gaussian_prior()(p[14], u[11], v[11])
print isp.gaussian_prior()(p[15], u[12], v[12])
print isp.gaussian_prior()(p[16], u[13], v[13])
print isp.gaussian_prior()(p[17], u[14], v[14])
print isp.gaussian_prior()(p[18], u[15], v[15])
print isp.gaussian_prior()(p[19], u[16], v[16])
def inverse_stoc_hyper_priors_test7():
"""
real nn arch with 16 nn params, one hyperparam, single granularity,
degen dependent params (2 priors)
"""
num_inputs = 1
layer_sizes = [3, 2]
num_outputs = 1
print "num weights"
n_dims = tools.calc_num_weights(num_inputs, layer_sizes, num_outputs)
print tools.calc_num_weights(num_inputs, layer_sizes, num_outputs)
weight_shapes = tools.get_weight_shapes(num_inputs, layer_sizes,
num_outputs)
print "weight shapes"
print tools.get_weight_shapes(num_inputs, layer_sizes, num_outputs)
granularity = 'single'
hyper_dependence_lengths = tools.get_hyper_dependence_lengths(
weight_shapes, granularity)
n_stoc = len(hyper_dependence_lengths)
print "number of weights per layer"
print tools.calc_num_weights_layers(weight_shapes)
dependence_lengths = tools.get_degen_dependence_lengths(weight_shapes)
print "degen dependence lengths"
print tools.get_degen_dependence_lengths(weight_shapes)
hyperprior_types = [9]
prior_types = [4, 5]
hyperprior_params = [[1., 2.]]
prior_hyperparams = [0., 1.]
param_hyperprior_types = [0]
param_prior_types = [0, 1, 0, 1, 0, 0, 1, 1, 0]
prior = isp.inverse_stoc_hyper_prior(hyperprior_types, prior_types,
hyperprior_params, prior_hyperparams,
hyper_dependence_lengths,
dependence_lengths,
param_hyperprior_types,
param_prior_types, n_stoc, n_dims)
p = np.array([
0.1, 0.5, 0.6, 0.7, 0.8, 0.9, 0.4, 0.2, 0.1, 0.5, 0.7, 0.8, 0.9, 0.4,
0.2, 0.1, 0.5, 0.9
])
prior(p)
u = [0., 0., 0., 1., 1., 1., 0., 0., 1., 1., 0., 0., 0., 0., 1., 1., 0.]
v = [
4.35688457, 4.35688457, 4.35688457, 4.35688457, 4.35688457, 4.35688457,
4.35688457, 4.35688457, 4.35688457, 4.35688457, 4.35688457, 4.35688457,
4.35688457, 4.35688457, 4.35688457, 4.35688457, 4.35688457
]
print isp.gaussian_prior()(p[1], u[0], v[0])
print isp.gaussian_prior()(p[2], u[1], v[1])
print isp.gaussian_prior()(p[3], u[2], v[2])
print isp.laplace_prior()(p[4], u[3], v[3])
print isp.laplace_prior()(p[5], u[4], v[4])
print isp.laplace_prior()(p[6], u[5], v[5])
print isp.gaussian_prior()(p[7], u[6], v[6])
print isp.gaussian_prior()(p[8], u[7], v[7])
print isp.laplace_prior()(p[9], u[8], v[8])
print isp.laplace_prior()(p[10], u[9], v[9])
print isp.gaussian_prior()(p[11], u[10], v[10])
print isp.gaussian_prior()(p[12], u[11], v[11])
print isp.gaussian_prior()(p[13], u[12], v[12])
print isp.gaussian_prior()(p[14], u[13], v[13])
print isp.laplace_prior()(p[15], u[14], v[14])
print isp.laplace_prior()(p[16], u[15], v[15])
print isp.gaussian_prior()(p[17], u[16], v[16])
make pred .paramnames file from scratch.
note file is saved to base_dir/file_root.paramnames
"""
param_names = get_pred_param_names(num_outputs)
param_f = base_dir + file_root + '.paramnames'
make_param_names_file(param_names, param_f)
if __name__ == '__main__':
num_inputs = 1
layer_sizes = [3, 2]
num_outputs = 1
print "num weights"
n_dims = tools.calc_num_weights(num_inputs, layer_sizes, num_outputs)
print tools.calc_num_weights(num_inputs, layer_sizes, num_outputs)
weight_shapes = tools.get_weight_shapes(num_inputs, layer_sizes,
num_outputs)
print "weight shapes"
print weight_shapes
granularity = 'input_size'
hyper_dependence_lengths = tools.get_hyper_dependence_lengths(
weight_shapes, granularity)
n_stoc = len(hyper_dependence_lengths)
print "n_stoc"
print n_stoc
print "granularity"
print hyper_dependence_lengths
print "degen dependence lengths"
print tools.get_degen_dependence_lengths(weight_shapes)
print "param names"
print get_param_names_sh(num_inputs, layer_sizes, num_outputs,
weight_shapes, granularity)