def test_exponential_conditional_params():
num_visible_units = 100
num_hidden_units = 50
batch_size = 25
# set a seed for the random number generator
be.set_seed()
# set up some layer and model objects
vis_layer = layers.ExponentialLayer(num_visible_units)
hid_layer = layers.ExponentialLayer(num_hidden_units)
rbm = model.Model([vis_layer, hid_layer])
# randomly set the intrinsic model parameters
# for the exponential layers, we need a > 0, b > 0, and W < 0
a = be.rand((num_visible_units, ))
b = be.rand((num_hidden_units, ))
W = -be.rand((num_visible_units, num_hidden_units))
rbm.layers[0].params.loc[:] = a
rbm.layers[1].params.loc[:] = b
rbm.weights[0].params.matrix[:] = W
# generate a random batch of data
vdata = rbm.layers[0].random((batch_size, num_visible_units))
hdata = rbm.layers[1].random((batch_size, num_hidden_units))
# compute conditional parameters
hidden_rate = -be.dot(vdata, W) # (batch_size, num_hidden_units)
hidden_rate += be.broadcast(b, hidden_rate)
visible_rate = -be.dot(hdata,
be.transpose(W)) # (batch_size, num_visible_units)
visible_rate += be.broadcast(a, visible_rate)
# compute the conditional parameters using the layer functions
hidden_rate_func = rbm.layers[1]._conditional_params([vdata],
[rbm.weights[0].W()])
visible_rate_func = rbm.layers[0]._conditional_params(
[hdata], [rbm.weights[0].W_T()])
assert be.allclose(hidden_rate, hidden_rate_func), \
"hidden rate wrong in exponential-exponential rbm"
assert be.allclose(visible_rate, visible_rate_func), \
"visible rate wrong in exponential-exponential rbm"
def test_bernoulli_conditional_params():
num_visible_units = 100
num_hidden_units = 50
batch_size = 25
# set a seed for the random number generator
be.set_seed()
# set up some layer and model objects
vis_layer = layers.BernoulliLayer(num_visible_units)
hid_layer = layers.BernoulliLayer(num_hidden_units)
rbm = model.Model([vis_layer, hid_layer])
# randomly set the intrinsic model parameters
a = be.randn((num_visible_units, ))
b = be.randn((num_hidden_units, ))
W = be.randn((num_visible_units, num_hidden_units))
rbm.layers[0].params.loc[:] = a
rbm.layers[1].params.loc[:] = b
rbm.weights[0].params.matrix[:] = W
# generate a random batch of data
vdata = rbm.layers[0].random((batch_size, num_visible_units))
hdata = rbm.layers[1].random((batch_size, num_hidden_units))
# compute conditional parameters
hidden_field = be.dot(vdata, W) # (batch_size, num_hidden_units)
hidden_field += b
visible_field = be.dot(hdata,
be.transpose(W)) # (batch_size, num_visible_units)
visible_field += a
# compute conditional parameters with layer funcitons
hidden_field_layer = rbm.layers[1]._conditional_params(
[vdata], [rbm.weights[0].W()])
visible_field_layer = rbm.layers[0]._conditional_params(
[hdata], [rbm.weights[0].W_T()])
assert be.allclose(hidden_field, hidden_field_layer), \
"hidden field wrong in bernoulli-bernoulli rbm"
assert be.allclose(visible_field, visible_field_layer), \
"visible field wrong in bernoulli-bernoulli rbm"
def test_exponential_update():
num_visible_units = 100
num_hidden_units = 50
batch_size = 25
# set a seed for the random number generator
be.set_seed()
# set up some layer and model objects
vis_layer = layers.ExponentialLayer(num_visible_units)
hid_layer = layers.ExponentialLayer(num_hidden_units)
rbm = hidden.Model([vis_layer, hid_layer])
# randomly set the intrinsic model parameters
# for the exponential layers, we need a > 0, b > 0, and W < 0
a = be.rand((num_visible_units, ))
b = be.rand((num_hidden_units, ))
W = -be.rand((num_visible_units, num_hidden_units))
rbm.layers[0].int_params['loc'] = a
rbm.layers[1].int_params['loc'] = b
rbm.weights[0].int_params['matrix'] = W
# generate a random batch of data
vdata = rbm.layers[0].random((batch_size, num_visible_units))
hdata = rbm.layers[1].random((batch_size, num_hidden_units))
# compute extrinsic parameters
hidden_rate = -be.dot(vdata, W) # (batch_size, num_hidden_units)
hidden_rate += be.broadcast(b, hidden_rate)
visible_rate = -be.dot(hdata,
be.transpose(W)) # (batch_size, num_visible_units)
visible_rate += be.broadcast(a, visible_rate)
# update the extrinsic parameter using the layer functions
rbm.layers[1].update(vdata, rbm.weights[0].W())
rbm.layers[0].update(hdata, be.transpose(rbm.weights[0].W()))
assert be.allclose(hidden_rate, rbm.layers[1].ext_params['rate']), \
"hidden rate wrong in exponential-exponential rbm"
assert be.allclose(visible_rate, rbm.layers[0].ext_params['rate']), \
"visible rate wrong in exponential-exponential rbm"
def test_bernoulli_update():
num_visible_units = 100
num_hidden_units = 50
batch_size = 25
# set a seed for the random number generator
be.set_seed()
# set up some layer and model objects
vis_layer = layers.BernoulliLayer(num_visible_units)
hid_layer = layers.BernoulliLayer(num_hidden_units)
rbm = hidden.Model([vis_layer, hid_layer])
# randomly set the intrinsic model parameters
a = be.randn((num_visible_units, ))
b = be.randn((num_hidden_units, ))
W = be.randn((num_visible_units, num_hidden_units))
rbm.layers[0].int_params.loc[:] = a
rbm.layers[1].int_params.loc[:] = b
rbm.weights[0].int_params.matrix[:] = W
# generate a random batch of data
vdata = rbm.layers[0].random((batch_size, num_visible_units))
hdata = rbm.layers[1].random((batch_size, num_hidden_units))
# compute extrinsic parameters
hidden_field = be.dot(vdata, W) # (batch_size, num_hidden_units)
hidden_field += be.broadcast(b, hidden_field)
visible_field = be.dot(hdata,
be.transpose(W)) # (batch_size, num_visible_units)
visible_field += be.broadcast(a, visible_field)
# update the extrinsic parameter using the layer functions
rbm.layers[0].update([hdata], [rbm.weights[0].W_T()])
rbm.layers[1].update([vdata], [rbm.weights[0].W()])
assert be.allclose(hidden_field, rbm.layers[1].ext_params.field), \
"hidden field wrong in bernoulli-bernoulli rbm"
assert be.allclose(visible_field, rbm.layers[0].ext_params.field), \
"visible field wrong in bernoulli-bernoulli rbm"
def compute_weights(rbm, n_weights=25, l=0, random=True):
# can't sample more than what we've got
n_weights = min(n_weights, rbm.connections[l].shape[1])
# floor to the nearest square below
grid_size = int(sqrt(n_weights))
n_weights = grid_size**2
if random:
idx = np.random.choice(range(rbm.connections[l].shape[1]),
n_weights, replace=False)
else:
idx = np.arange(n_weights)
wprod = rbm.connections[0].weights.W()
for i in range(1,l+1):
wprod = be.dot(wprod, rbm.connections[i].weights.W())
grid = np.array([be.to_numpy_array(wprod[:, i])
for i in idx])
return grid.reshape(grid_size, grid_size, -1)
def pdist(x: be.Tensor, y: be.Tensor) -> be.Tensor:
"""
Compute the pairwise distance matrix between the rows of x and y.
Args:
x (tensor (num_samples_1, num_units))
y (tensor (num_samples_2, num_units))
Returns:
tensor (num_samples_1, num_samples_2)
"""
inner = be.dot(x, be.transpose(y))
x_mag = be.norm(x, axis=1)**2
y_mag = be.norm(y, axis=1)**2
squared = be.add(be.unsqueeze(y_mag, axis=0),
be.add(be.unsqueeze(x_mag, axis=1), -2 * inner))
return be.sqrt(be.clip(squared, a_min=0))
def test_gaussian_update():
num_visible_units = 100
num_hidden_units = 50
batch_size = 25
# set a seed for the random number generator
be.set_seed()
# set up some layer and model objects
vis_layer = layers.GaussianLayer(num_visible_units)
hid_layer = layers.GaussianLayer(num_hidden_units)
rbm = hidden.Model([vis_layer, hid_layer])
# randomly set the intrinsic model parameters
a = be.randn((num_visible_units, ))
b = be.randn((num_hidden_units, ))
log_var_a = 0.1 * be.randn((num_visible_units, ))
log_var_b = 0.1 * be.randn((num_hidden_units, ))
W = be.randn((num_visible_units, num_hidden_units))
rbm.layers[0].int_params.loc[:] = a
rbm.layers[1].int_params.loc[:] = b
rbm.layers[0].int_params.log_var[:] = log_var_a
rbm.layers[1].int_params.log_var[:] = log_var_b
rbm.weights[0].int_params.matrix[:] = W
# generate a random batch of data
vdata = rbm.layers[0].random((batch_size, num_visible_units))
hdata = rbm.layers[1].random((batch_size, num_hidden_units))
# compute the variance
visible_var = be.exp(log_var_a)
hidden_var = be.exp(log_var_b)
# rescale the data
vdata_scaled = vdata / be.broadcast(visible_var, vdata)
hdata_scaled = hdata / be.broadcast(hidden_var, hdata)
# test rescale
assert be.allclose(vdata_scaled, rbm.layers[0].rescale(vdata)),\
"visible rescale wrong in gaussian-gaussian rbm"
assert be.allclose(hdata_scaled, rbm.layers[1].rescale(hdata)),\
"hidden rescale wrong in gaussian-gaussian rbm"
# compute the mean
hidden_mean = be.dot(vdata_scaled, W) # (batch_size, num_hidden_units)
hidden_mean += be.broadcast(b, hidden_mean)
visible_mean = be.dot(hdata_scaled,
be.transpose(W)) # (batch_size, num_hidden_units)
visible_mean += be.broadcast(a, visible_mean)
# update the extrinsic parameters using the layer functions
rbm.layers[0].update([hdata_scaled], [rbm.weights[0].W_T()])
rbm.layers[1].update([vdata_scaled], [rbm.weights[0].W()])
assert be.allclose(visible_var, rbm.layers[0].ext_params.variance),\
"visible variance wrong in gaussian-gaussian rbm"
assert be.allclose(hidden_var, rbm.layers[1].ext_params.variance),\
"hidden variance wrong in gaussian-gaussian rbm"
assert be.allclose(visible_mean, rbm.layers[0].ext_params.mean),\
"visible mean wrong in gaussian-gaussian rbm"
assert be.allclose(hidden_mean, rbm.layers[1].ext_params.mean),\
"hidden mean wrong in gaussian-gaussian rbm"
def test_gaussian_conditional_params():
num_visible_units = 100
num_hidden_units = 50
batch_size = 25
# set a seed for the random number generator
be.set_seed()
# set up some layer and model objects
vis_layer = layers.GaussianLayer(num_visible_units)
hid_layer = layers.GaussianLayer(num_hidden_units)
rbm = BoltzmannMachine([vis_layer, hid_layer])
# randomly set the intrinsic model parameters
a = be.randn((num_visible_units,))
b = be.randn((num_hidden_units,))
log_var_a = 0.1 * be.randn((num_visible_units,))
log_var_b = 0.1 * be.randn((num_hidden_units,))
W = be.randn((num_visible_units, num_hidden_units))
rbm.layers[0].params.loc[:] = a
rbm.layers[1].params.loc[:] = b
rbm.layers[0].params.log_var[:] = log_var_a
rbm.layers[1].params.log_var[:] = log_var_b
rbm.connections[0].weights.params.matrix[:] = W
# generate a random batch of data
vdata = rbm.layers[0].random((batch_size, num_visible_units))
hdata = rbm.layers[1].random((batch_size, num_hidden_units))
# compute the variance
visible_var = be.exp(log_var_a)
hidden_var = be.exp(log_var_b)
# rescale the data
vdata_scaled = vdata / visible_var
hdata_scaled = hdata / hidden_var
# test rescale
assert be.allclose(vdata_scaled, rbm.layers[0].rescale(vdata)),\
"visible rescale wrong in gaussian-gaussian rbm"
assert be.allclose(hdata_scaled, rbm.layers[1].rescale(hdata)),\
"hidden rescale wrong in gaussian-gaussian rbm"
# compute the mean
hidden_mean = be.dot(vdata_scaled, W) # (batch_size, num_hidden_units)
hidden_mean += b
visible_mean = be.dot(hdata_scaled, be.transpose(W)) # (batch_size, num_hidden_units)
visible_mean += a
# update the conditional parameters using the layer functions
vis_mean_func, vis_var_func = rbm.layers[0].conditional_params(
[hdata_scaled], [rbm.connections[0].W(trans=True)])
hid_mean_func, hid_var_func = rbm.layers[1].conditional_params(
[vdata_scaled], [rbm.connections[0].W()])
assert be.allclose(visible_var, vis_var_func),\
"visible variance wrong in gaussian-gaussian rbm"
assert be.allclose(hidden_var, hid_var_func),\
"hidden variance wrong in gaussian-gaussian rbm"
assert be.allclose(visible_mean, vis_mean_func),\
"visible mean wrong in gaussian-gaussian rbm"
assert be.allclose(hidden_mean, hid_mean_func),\
"hidden mean wrong in gaussian-gaussian rbm"
