def test_weights_derivative():
ly = layers.Weights((num_vis, num_hid))
p = penalties.l2_penalty(0.37)
ly.add_penalty({'matrix': p})
vis = be.randn((num_samples, num_vis))
hid = be.randn((num_samples, num_hid))
derivs = ly.derivatives(vis, hid)
def test_exponential_conditional_params():
ly = layers.ExponentialLayer(num_vis)
w = layers.Weights((num_vis, num_hid))
scaled_units = [be.randn((num_samples, num_hid))]
weights = [w.W_T()]
beta = be.rand((num_samples, 1))
ly._conditional_params(scaled_units, weights, beta)
def test_bernoulli_derivatives():
ly = layers.BernoulliLayer(num_vis)
w = layers.Weights((num_vis, num_hid))
vis = ly.random((num_samples, num_vis))
hid = [be.randn((num_samples, num_hid))]
weights = [w.W_T()]
ly.derivatives(vis, hid, weights)
def test_onehot_derivatives():
ly = layers.OneHotLayer(num_vis)
w = layers.Weights((num_vis, num_hid))
vis = ly.random((num_samples, num_vis))
hid = [be.randn((num_samples, num_hid))]
weights = [w.W_T()]
ly.derivatives(vis, hid, weights)
def test_gaussian_derivatives():
ly = layers.GaussianLayer(num_vis)
w = layers.Weights((num_vis, num_hid))
vis = ly.random((num_samples, num_vis))
hid = [be.randn((num_samples, num_hid))]
weights = [w.W_T()]
ly.derivatives(vis, hid, weights)
def test_onehot_conditional_params():
ly = layers.OneHotLayer(num_vis)
w = layers.Weights((num_vis, num_hid))
scaled_units = [be.randn((num_samples, num_hid))]
weights = [w.W(trans=True)]
beta = be.rand((num_samples, 1))
ly.conditional_params(scaled_units, weights, beta)
def test_exponential_update():
ly = layers.BernoulliLayer(num_vis)
w = layers.Weights((num_vis, num_hid))
scaled_units = [be.randn((num_samples, num_hid))]
weights = [w.W_T()]
beta = be.rand((num_samples, 1))
ly.update(scaled_units, weights, beta)
def test_weights_build_from_config():
ly = layers.Weights((num_vis, num_hid))
ly.add_constraint({'matrix': constraints.non_negative})
p = penalties.l2_penalty(0.37)
ly.add_penalty({'matrix': p})
ly_new = layers.Layer.from_config(ly.get_config())
assert ly_new.get_config() == ly.get_config()
def test_ising_update():
ly = layers.IsingLayer(num_vis)
w = layers.Weights((num_vis, num_hid))
scaled_units = [be.randn((num_samples, num_hid))]
weights = [w.W_T()]
beta = be.rand((num_samples, 1))
ly.update(scaled_units, weights, beta)
def test_ising_derivatives():
ly = layers.IsingLayer(num_vis)
w = layers.Weights((num_vis, num_hid))
vis = ly.random((num_samples, num_vis))
hid = [be.randn((num_samples, num_hid))]
weights = [w.W()]
beta = be.rand((num_samples, 1))
ly.derivatives(vis, hid, weights, beta)
def test_exponential_derivatives():
ly = layers.ExponentialLayer(num_vis)
w = layers.Weights((num_vis, num_hid))
vis = ly.random((num_samples, num_vis))
hid = [be.randn((num_samples, num_hid))]
weights = [w.W_T()]
beta = be.rand((num_samples, 1))
ly.derivatives(vis, hid, weights, beta)
def test_Weights_creation():
layers.Weights((num_vis, num_hid))
def test_weights_energy():
ly = layers.Weights((num_vis, num_hid))
vis = be.randn((num_samples, num_vis))
hid = be.randn((num_samples, num_hid))
ly.energy(vis, hid)
def test_enforce_constraints():
ly = layers.Weights((num_vis, num_hid))
ly.add_constraint({'matrix': constraints.non_negative})
ly.enforce_constraints()
def test_get_base_config():
ly = layers.Weights((num_vis, num_hid))
ly.add_constraint({'matrix': constraints.non_negative})
p = penalties.l2_penalty(0.37)
ly.add_penalty({'matrix': p})
ly.get_base_config()
def test_parameter_step():
ly = layers.Weights((num_vis, num_hid))
deltas = layers.ParamsWeights(be.randn(ly.shape))
ly.parameter_step(deltas)
def test_get_penalty_grad():
ly = layers.Weights((num_vis, num_hid))
p = penalties.l2_penalty(0.37)
ly.add_penalty({'matrix': p})
ly.get_penalty_grad(ly.W(), 'matrix')
def test_add_penalty():
ly = layers.Weights((num_vis, num_hid))
p = penalties.l2_penalty(0.37)
ly.add_penalty({'matrix': p})