def test_pca_compare_var():
# create some random data
num_samples = 10000
dim = 10
batch_size = 100
num_components = 3
# generate some data
mean = np.random.random(dim)
cov_factor = np.random.random((dim, dim))
cov = np.dot(cov_factor, cov_factor.T)
samples = be.float_tensor(
np.random.multivariate_normal(mean, cov, size=num_samples))
samples_train, samples_validate = batch.split_tensor(samples, 0.9)
data = batch.Batch({
'train':
batch.InMemoryTable(samples_train, batch_size),
'validate':
batch.InMemoryTable(samples_validate, batch_size)
})
# find the principal directions
pca_sgd = factorization.PCA.from_batch(data,
num_components,
epochs=10,
grad_steps_per_minibatch=1,
stepsize=0.01)
pca_svd = factorization.PCA.from_svd(samples_train, num_components)
assert be.norm(pca_sgd.var - pca_svd.var) / be.norm(pca_sgd.var) < 1e-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 weight_norm_histogram(rbm, show_plot=False, filename=None):
import matplotlib.pyplot as plt
import seaborn as sns
fig, ax = plt.subplots()
for l in range(rbm.num_connections):
num_inputs = rbm.connections[l].shape[0]
norm = be.to_numpy_array(be.norm(rbm.connections[l].weights.W(), axis=0) / sqrt(num_inputs))
sns.distplot(norm, ax=ax, label=str(l))
ax.legend()
if show_plot:
fig
if filename is not None:
fig.savefig(filename)
plt.close(fig)
cd.train(opt, num_epochs, method=fit.pcd, mcsteps=mc_steps,
beta_std=beta_std, burn_in=1)
# evaluate the model
util.show_metrics(rbm, cd.monitor)
valid = data.get('validate')
util.show_reconstructions(rbm, valid, show_plot, n_recon=10, vertical=False)
util.show_fantasy_particles(rbm, valid, show_plot, n_fantasy=5)
util.show_weights(rbm, show_plot, n_weights=100)
# close the HDF5 store
data.close()
print("Done")
return rbm
if __name__ == "__main__":
rbm = run(show_plot = True)
import seaborn
import matplotlib.pyplot as plt
for conn in rbm.connections:
c = be.corr(conn.weights.W(), conn.weights.W())
fig, ax = plt.subplots()
seaborn.heatmap(be.to_numpy_array(c), vmin=-1, vmax=1, ax=ax)
fig
n = be.norm(conn.weights.W(), axis=0)
fig, ax = plt.subplots()
seaborn.distplot(be.to_numpy_array(n), ax=ax)
fig
def test_l2_normalize():
result_pre = [
be.norm(pre.l2_normalize(tensor), axis=1) for tensor in tensors
]
result_ref = [be.ones((len(tensor), )) for tensor in tensors]
assert compare_lists(result_pre, result_ref)