def upscale(args, selected_experiment_folder):
target_image = Image.open(
os.path.join(selected_experiment_folder, "target.png"))
upscaling_factor = args.upscaling_factor
original_emoji_size = (args.emoji_size, args.emoji_size)
original_image_size = target_image.size
upscaled_emoji_size = (
original_emoji_size[0] * upscaling_factor,
original_emoji_size[1] * upscaling_factor,
)
upscaled_image_size = (
original_image_size[0] * upscaling_factor,
original_image_size[1] * upscaling_factor,
)
upscaled_emojies = get_emojies(size=upscaled_emoji_size[0])
stored_individual_paths = get_file_paths(selected_experiment_folder,
file_extensions=("pkl", ))
stored_individual_paths.sort(key=lambda f: f.name)
best_stored_individual_path = stored_individual_paths[-1]
genotype = joblib.load(best_stored_individual_path)
genotype[:, 1] *= upscaling_factor # x
genotype[:, 2] *= upscaling_factor # y
image = generate_alpha_image_from_scratch(genotype, upscaled_image_size,
upscaled_emojies)
image.save(
os.path.join(selected_experiment_folder,
best_stored_individual_path.stem + "_upscaled.png"))
print("Done")
def get_emojies(size):
emoji_paths = get_file_paths(EMOJI_DIR)
emojies = []
for path in emoji_paths:
emoji = Image.open(path).resize((size, size), Image.LANCZOS)
emojies.append(emoji)
return emojies
def make_gif(folder, max_num_frames=16):
frame_paths = get_file_paths(folder)
frame_paths = [p for p in frame_paths if p.name != "target.png"]
if len(frame_paths) > max_num_frames:
frame_indexes = np.linspace(start=0,
stop=len(frame_paths) - 1,
endpoint=True,
num=max_num_frames,
dtype=np.int).tolist()
frame_indexes = set(frame_indexes)
frame_paths = [
path for i, path in enumerate(frame_paths) if i in frame_indexes
]
gif_output_path = os.path.join(folder, "evolution.gif")
durations = [0.2] * len(frame_paths)
durations[-1] = 1.5
images = [imageio.imread(frame_path) for frame_path in frame_paths]
imageio.mimsave(gif_output_path, images, duration=durations)
target_image = Image.open(
os.path.join(selected_experiment_folder, "target.png")).convert("RGB")
upscaling_factor = 1
original_emoji_size = (args.emoji_size, args.emoji_size)
original_image_size = target_image.size
upscaled_image_size = (
original_image_size[0] * upscaling_factor,
original_image_size[1] * upscaling_factor,
)
upscaled_emoji_size = (
original_emoji_size[0] * upscaling_factor,
original_emoji_size[1] * upscaling_factor,
)
stored_individual_paths = get_file_paths(selected_experiment_folder,
file_extensions=("pkl", ))
stored_individual_paths.sort(key=lambda f: f.name)
best_stored_individual_path = stored_individual_paths[-1]
genotype = joblib.load(best_stored_individual_path)
upscaled_emojies = get_emojies(size=upscaled_emoji_size[0])
fitness_evaluator = LABDeltaESSIMFitnessEvaluator(target_image)
image = generate_image_from_scratch(genotype, upscaled_image_size,
upscaled_emojies).convert("RGB")
base_individual = Individual(image)
fitness_evaluator.evaluate_fitness([base_individual])
current_fitness = base_individual.fitness
print("Base fitness: {}".format(current_fitness))
current_genotype = genotype