image = image.reshape([HEIGHT, WIDTH])
# print(np.max(image),np.min(image))
# image = np.clip(image+0.5,0,1)
images += [image]
return images
### GENERATE SECTION
print('GENERATE SECTION')
for current_iteration in range(N):
print('CURRENT_ITERATION:', current_iteration)
if START_SERVER is True:
viz.start_image_server(generate_image, COLOR_STRING,
SEED + current_iteration)
break
else:
if TRAIN_NNET is True:
print('\tTRAINING NNET')
training_image = train_nnet(SEED + current_iteration)
print('\tGENERATING IMAGE')
# images = generate_neuron_images(COLOR_STRING, SEED + current_iteration)
images = generate_image(COLOR_STRING, SEED + current_iteration)
if SAVE_IMAGES is True:
print('\tSAVING IMAGE')
file.export_image('%d_%d_%d' %
(current_iteration, SEED + current_iteration,
gridpatterny = m.RMM(values=valuesy, self_length=20)
parenty = m.SProg(values=gridpatterny)
gridx = m.generate_grid_lines(parentx, WIDTH)
# gridy = m.generate_grid_lines(parenty,HEIGHT)
gridy = [HEIGHT // 2]
# print(gridx)
# print(gridy)
color_repository = color.build_color_repository(color_string)
final_img = r.call_and_bind(generate_image, gridx, gridy,
color_repository)
return final_img
# imgs = generate_full_image(COLOR_STRING)
# file.export_image(
# '%d_%d' % (current_iteration,int(round(time.time() * 1000))),
# imgs.astype('uint8'),format='png')
#
if N == 1:
viz.start_image_server(COLOR_STRING, generate_full_image,
SEED + current_iteration)
else:
imgs = generate_full_image(COLOR_STRING, SEED)
file.export_image('%d_%d_%d' %
(current_iteration, SEED + current_iteration,
int(round(time.time() * 1000))),
imgs.astype('uint8'),
format='png')
