def plot_state_sequence_and_overlap(state_sequence, pattern_list, reference_idx, color_map="brg", suptitle=None):
"""
For each time point t ( = index of state_sequence), plots the sequence of states and the overlap (barplot)
between state(t) and each pattern.
Args:
state_sequence: (list(numpy.ndarray))
pattern_list: (list(numpy.ndarray))
reference_idx: (int) identifies the pattern in pattern_list for which wrong pixels are colored.
"""
if reference_idx is None:
reference_idx = 0
reference = pattern_list[reference_idx]
f, ax = plt.subplots(2, len(state_sequence))
if len(state_sequence) == 1:
ax = [ax]
_plot_list(ax[0, :], state_sequence, reference, "S{0}", color_map)
for i in range(len(state_sequence)):
overlap_list = pattern_tools.compute_overlap_list(state_sequence[i], pattern_list)
ax[1, i].bar(range(len(overlap_list)), overlap_list)
ax[1, i].set_title("m = {1}".format(i, round(overlap_list[reference_idx], 2)))
ax[1, i].set_ylim([-1, 1])
ax[1, i].get_xaxis().set_major_locator(plt.MaxNLocator(integer=True))
if i > 0: # show lables only for the first subplot
ax[1, i].set_xticklabels([])
ax[1, i].set_yticklabels([])
if suptitle is not None:
f.suptitle(suptitle)
plt.show()
def main( plot = True ):
# set a seed to reproduce the same noise in the next run
# numpy.random.seed(123)
# access the first element and get it's size (they are all of same size)
pattern_shape = abc_dictionary['A'].shape
# create an instance of the class HopfieldNetwork
hopfield_net = network.HopfieldNetwork(
nr_neurons = pattern_shape[0]*pattern_shape[1]
)
pattern_list = [abc_dictionary[key] for key in letter_list ]
if plot:
plt.figure( figsize=(12, 6) )
for i, a in enumerate(pattern_list):
ax = plt.subplot( nRows, maxCols, i+1)
ax.imshow( a )
ax.axis('off')
# store the patterns
hopfield_net.store_patterns(pattern_list)
print( "[INFO ] Saved patterns into hopfield network." )
# create a noisy version of a pattern and use that to initialize the network
l = random.choice( letter_list )
noise_level = 0.5
if add_extra:
noise_level = 0.1
print( '[INFO] More patterns than net can handle. Catastrophic'
' forgetting going to happen.'
)
noisy_init_state = add_noise( l, noise_level= noise_level)
hopfield_net.set_state_from_pattern(noisy_init_state)
# from this initial state, let the network dynamics evolve.
states = hopfield_net.run_with_monitoring(nr_steps=4)
# each network state is a vector. reshape it to the same shape used to create the patterns.
states_as_patterns = pattern_tools.reshape_patterns(states, pattern_list[0].shape)
if plot:
for i, pat in enumerate( states_as_patterns ):
overlap_list = pattern_tools.compute_overlap_list(pat, pattern_list)
ax = plt.subplot( nRows, maxCols, maxCols+i+1 )
ax.imshow( pat )
ax.axis('off')
ax1 = plt.subplot( nRows, maxCols, 2*maxCols+i+1)
ax1.bar( range(len(overlap_list)), overlap_list )
# ax1.set_ylim( -1, 1 )
ax1.set_xticks( range(len(overlap_list)) )
ax1.set_xticklabels( letter_list )
plt.tight_layout()
outfile = 'figures/final_%s.png' % l
plt.savefig( outfile )
print( '|| Saved to %s' % outfile )
plt.show()
plt.close()
return pattern_list, noisy_init_state, states_as_patterns
def main(plot=True):
# set a seed to reproduce the same noise in the next run
# numpy.random.seed(123)
# access the first element and get it's size (they are all of same size)
pattern_shape = abc_dictionary['A'].shape
# create an instance of the class HopfieldNetwork
hopfield_net = network.HopfieldNetwork(nr_neurons=pattern_shape[0] *
pattern_shape[1])
pattern_list = [abc_dictionary[key] for key in letter_list]
if plot:
plt.figure(figsize=(12, 6))
for i, k in enumerate(letter_list):
a = abc_dictionary[k]
ax = plt.subplot(nRows, maxCols, i + 1)
ax.imshow(a)
ax.axis('off')
save_letter(a, '%s.txt' % k)
# store the patterns
hopfield_net.store_patterns(pattern_list)
print("[INFO ] Saved patterns into hopfield network.")
# create a noisy version of a pattern and use that to initialize the network
l = random.choice(letter_list)
noise_level = 0.5
if add_extra:
noise_level = 0.1
print('[INFO] More patterns than net can handle. Catastrophic'
' forgetting going to happen.')
noisy_init_state = add_noise(l, noise_level=noise_level)
hopfield_net.set_state_from_pattern(noisy_init_state)
# from this initial state, let the network dynamics evolve.
states = hopfield_net.run_with_monitoring(nr_steps=4)
# each network state is a vector. reshape it to the same shape used to create the patterns.
states_as_patterns = pattern_tools.reshape_patterns(
states, pattern_list[0].shape)
if plot:
for i, pat in enumerate(states_as_patterns):
overlap_list = pattern_tools.compute_overlap_list(
pat, pattern_list)
ax = plt.subplot(nRows, maxCols, maxCols + i + 1)
save_letter(pat, '%s%s.txt' % (l, i))
ax.imshow(pat)
ax.axis('off')
ax1 = plt.subplot(nRows, maxCols, 2 * maxCols + i + 1)
ax1.bar(range(len(overlap_list)), overlap_list)
# ax1.set_ylim( -1, 1 )
ax1.set_xticks(range(len(overlap_list)))
ax1.set_xticklabels(letter_list)
plt.tight_layout()
outfile = 'figures/final_%s.png' % l
plt.savefig(outfile)
print('|| Saved to %s' % outfile)
plt.show()
plt.close()
return pattern_list, noisy_init_state, states_as_patterns