def templatePatternVisualizer(self, collect_dynamic, ccore_flag=False):
net = syncpr(5, 0.1, 0.1, ccore=ccore_flag)
output_dynamic = net.simulate(10, 10, [-1, 1, -1, 1, -1],
solve_type.RK4, collect_dynamic)
syncpr_visualizer.show_pattern(output_dynamic, 5, 2)
syncpr_visualizer.animate_pattern_recognition(output_dynamic, 1, 5)
def template_recognition_image(images, steps, time, corruption=0.1):
samples = []
for file_name in images:
data = read_image(file_name)
image_pattern = rgb2gray(data)
for index_pixel in range(len(image_pattern)):
if (image_pattern[index_pixel] < 128):
image_pattern[index_pixel] = 1
else:
image_pattern[index_pixel] = -1
samples += [image_pattern]
net = syncpr(len(samples[0]), 0.3, 0.3, ccore=True)
net.train(samples)
# Recognize the each learned pattern
for i in range(len(samples)):
sync_output_dynamic = net.simulate(steps, time, samples[i],
solve_type.RK4, True)
syncpr_visualizer.show_output_dynamic(sync_output_dynamic)
syncpr_visualizer.show_pattern(sync_output_dynamic, 10, 10)
# corrupt a little bit by black and white pixels
for _ in range(math.floor(len(samples[i]) * corruption)):
random.seed()
random_pixel = math.floor(random.random() * len(samples[i]))
samples[i][random_pixel] = 1
random_pixel = math.floor(random.random() * len(samples[i]))
samples[i][random_pixel] = -1
sync_output_dynamic = net.simulate(steps, time, samples[i],
solve_type.RK4, True)
syncpr_visualizer.show_output_dynamic(sync_output_dynamic)
syncpr_visualizer.show_pattern(sync_output_dynamic, 10, 10)
syncpr_visualizer.animate_pattern_recognition(
sync_output_dynamic, 10, 10, title="Pattern Recognition")
def template_recognition_image(images, steps, time, corruption = 0.1):
samples = [];
for file_name in images:
data = read_image(file_name);
image_pattern = rgb2gray(data);
for index_pixel in range(len(image_pattern)):
if (image_pattern[index_pixel] < 128):
image_pattern[index_pixel] = 1;
else:
image_pattern[index_pixel] = -1;
samples += [ image_pattern ];
net = syncpr(len(samples[0]), 0.3, 0.3, ccore = True);
net.train(samples);
# Recognize the each learned pattern
for i in range(len(samples)):
sync_output_dynamic = net.simulate(steps, time, samples[i], solve_type.RK4, True);
syncpr_visualizer.show_output_dynamic(sync_output_dynamic);
syncpr_visualizer.show_pattern(sync_output_dynamic, 10, 10);
# corrupt a little bit by black and white pixels
for _ in range( math.floor(len(samples[i]) * corruption) ):
random.seed();
random_pixel = math.floor(random.random() * len(samples[i]));
samples[i][random_pixel] = 1;
random_pixel = math.floor(random.random() * len(samples[i]));
samples[i][random_pixel] = -1;
sync_output_dynamic = net.simulate(steps, time, samples[i], solve_type.RK4, True);
syncpr_visualizer.show_output_dynamic(sync_output_dynamic);
syncpr_visualizer.show_pattern(sync_output_dynamic, 10, 10);
syncpr_visualizer.animate_pattern_recognition(sync_output_dynamic, 10, 10, title = "Pattern Recognition");
def templatePatternVisualizer(collect_dynamic, ccore_flag = False):
net = syncpr(5, 0.1, 0.1, ccore = ccore_flag);
output_dynamic = net.simulate(10, 10, [-1, 1, -1, 1, -1], solve_type.RK4, collect_dynamic);
syncpr_visualizer.show_pattern(output_dynamic, 5, 2);
syncpr_visualizer.animate_pattern_recognition(output_dynamic, 1, 5);
def templatePatternVisualizer(self, collect_dynamic):
net = syncpr(5, 0.1, 0.1);
output_dynamic = net.simulate(10, 10, [-1, 1, -1, 1, -1], solve_type.RK4, collect_dynamic);
# test that we don't have any exception during vizualization.
syncpr_visualizer.show_pattern(output_dynamic, 5, 2);
def templatePatternVisualizer(self, collect_dynamic):
net = syncpr(5, 0.1, 0.1);
output_dynamic = net.simulate(10, 10, [-1, 1, -1, 1, -1], solve_type.RK4, collect_dynamic);
# test that we don't have any exception during vizualization.
syncpr_visualizer.show_pattern(output_dynamic, 5, 2);
