def plot_reference_spiral_for_ICLR_paper(simulated_frames_output_dir,
n_simulated_samples, n_iter):
# Plot the reference graph for the ICLR paper.
import debian_spiral
original_spiral_samples = debian_spiral.sample(
n_simulated_samples * n_iter, 0.0).reshape((1, -1, 2))
write_simulated_samples_frames(
original_spiral_samples,
lambda i: os.path.join(simulated_frames_output_dir,
"original_spiral_samples_width_0.5.png"),
window_width=0.5)
write_simulated_samples_frames(
original_spiral_samples,
lambda i: os.path.join(simulated_frames_output_dir,
"original_spiral_samples_width_1.0.png"),
window_width=1.0)
write_simulated_samples_frames(
original_spiral_samples,
lambda i: os.path.join(simulated_frames_output_dir,
"original_spiral_samples_width_2.0.png"),
window_width=2.0)
# plot_reference_spiral_for_ICLR_paper("/u/alaingui/Documents/tmp/14", 100, 100)
# python dae_langevin_sampling.py $HOME/umontreal/denoising_autoencoder/plots/experiment_970584/results.pkl $HOME/Documents/tmp/1
# ffmpeg -i /u/alaingui/Documents/tmp/4/simulation_frame_%05d.png -vcodec mpeg4 /u/alaingui/Documents/tmp/4/sequence.avi
def plot_spiral_into_axes(axes):
from matplotlib.lines import Line2D
import debian_spiral
N = 80
spiral_samples = debian_spiral.sample(N, 0.0, want_sorted_data = True, want_evenly_spaced = True)
for i in range(N-1):
l = Line2D([spiral_samples[i,0],spiral_samples[i+1,0]],
[spiral_samples[i,1],spiral_samples[i+1,1]],
linestyle='--', linewidth=1.0, c='#f9a21d')
axes.add_line(l)
def plot_spiral_into_axes(axes):
from matplotlib.lines import Line2D
import debian_spiral
N = 80
spiral_samples = debian_spiral.sample(N,
0.0,
want_sorted_data=True,
want_evenly_spaced=True)
for i in range(N - 1):
l = Line2D([spiral_samples[i, 0], spiral_samples[i + 1, 0]],
[spiral_samples[i, 1], spiral_samples[i + 1, 1]],
linestyle='--',
linewidth=1.0,
c='#f9a21d')
axes.add_line(l)
def compare_gradients(self, input_noise_scale = 1.0, use_spiral = False):
if use_spiral:
if not (self.mydae.n_visibles == 2):
print "It doesn't make sense to ask to use the spiral if you don't have 2 input units."
assert(self.mydae.n_visibles == 2)
import debian_spiral
N = 10
(X0,Y0) = debian_spiral.sample(N, 0.0)
X = numpy.vstack((X0,Y0)).T
else:
N = 10
X = numpy.zeros((N, self.n_visibles))
if input_noise_scale > 0:
noise = numpy.random.normal(scale = input_noise_scale, size = X.shape)
else:
noise = numpy.zeros(X.shape)
noisy_X = X + noise
dae_grad_W, dae_grad_b, dae_grad_c = self.mydae.theano_gradients(self.mydae.W,
self.mydae.b,
self.mydae.c,
noisy_X, X)
ref_grad_W, ref_grad_b, ref_grad_c = reference_gradients(self.mydae.W,
self.mydae.b,
self.mydae.c,
noisy_X, X)
print "--- ref ---"
print ref_grad_W
print ref_grad_b
print ref_grad_c
print "--- dae ---"
print dae_grad_W
print dae_grad_b
print dae_grad_c
# We scaled the output of the tanh for the DAE.
# That results in all the gradients being multiplied
# by 4 so we have to correct for this.
alpha = self.mydae.output_scaling_factor ** 2
assert_total_difference(self.test, dae_grad_W, alpha * ref_grad_W, 0.01)
assert_total_difference(self.test, dae_grad_b, alpha * ref_grad_b, 0.01)
assert_total_difference(self.test, dae_grad_c, alpha * ref_grad_c, 0.01)
def plot_reference_spiral_for_ICLR_paper(simulated_frames_output_dir, n_simulated_samples, n_iter):
# Plot the reference graph for the ICLR paper.
import debian_spiral
original_spiral_samples = debian_spiral.sample(n_simulated_samples * n_iter, 0.0).reshape((1,-1,2))
write_simulated_samples_frames(original_spiral_samples,
lambda i: os.path.join(simulated_frames_output_dir, "original_spiral_samples_width_0.5.png"),
window_width=0.5)
write_simulated_samples_frames(original_spiral_samples,
lambda i: os.path.join(simulated_frames_output_dir, "original_spiral_samples_width_1.0.png"),
window_width=1.0)
write_simulated_samples_frames(original_spiral_samples,
lambda i: os.path.join(simulated_frames_output_dir, "original_spiral_samples_width_2.0.png"),
window_width=2.0)
# plot_reference_spiral_for_ICLR_paper("/u/alaingui/Documents/tmp/14", 100, 100)
# python dae_langevin_sampling.py $HOME/umontreal/denoising_autoencoder/plots/experiment_970584/results.pkl $HOME/Documents/tmp/1
# ffmpeg -i /u/alaingui/Documents/tmp/4/simulation_frame_%05d.png -vcodec mpeg4 /u/alaingui/Documents/tmp/4/sequence.avi
def get_starting_point_for_spiral():
import debian_spiral
spiral_samples = debian_spiral.sample(1000, 0.0, want_sorted_data=True)
return spiral_samples[0, :]
# Now that we fix the training data, we have to insist
# on the difference between original data and noisy replicated
# versions of that original data.
if 'n_spiral_original_samples' not in override_params.keys():
n_spiral_original_samples = 1000
else:
n_spiral_original_samples = override_params['n_spiral_original_samples']
if 'spiral_samples_noise_stddev' not in override_params.keys():
spiral_samples_noise_stddev = 0.0
else:
spiral_samples_noise_stddev = override_params[
'spiral_samples_noise_stddev']
angle_restriction = 1.0
original_data = debian_spiral.sample(n_spiral_original_samples,
spiral_samples_noise_stddev,
want_sorted_data=False,
angle_restriction=angle_restriction)
replication_factor = 10
n_spiral_replicated_samples = n_spiral_original_samples * replication_factor
if 'train_noise_stddev' not in override_params.keys():
train_noise_stddev = 0.01
else:
train_noise_stddev = override_params['train_noise_stddev']
clean_data = np.tile(original_data, (replication_factor, 1))
np.random.shuffle(clean_data)
noisy_data = clean_data + np.random.normal(size=clean_data.shape,
scale=train_noise_stddev)
# 5% of the values will have noise 10 times as larger applied to them
import dae_theano
#dae_theano = reload(dae_theano)
mydae = dae_theano.DAE(n_hiddens=56,
epochs=1000,
learning_rate=0.01,
prob_large_noise=0.000,
large_noise_sigma=1.0,
jacobi_penalty=0.01,
batch_size=25)
import debian_spiral
import numpy
n_spiral_samples = 2000
spiral_samples_noise = 0.01
(X,Y) = debian_spiral.sample(n_spiral_samples, spiral_samples_noise)
data = numpy.vstack((X,Y)).T
mydae.fit(data, verbose=True)
mydae.set_params_to_best_noisy()
# print "mydae.W is "
# print mydae.W
# print "mydae.b is "
# print mydae.b
# print "mydae.c is "
# print mydae.c
# print data
def get_starting_point_for_spiral():
import debian_spiral
spiral_samples = debian_spiral.sample(1000, 0.0, want_sorted_data = True)
return spiral_samples[0,:]
