mirror of
https://github.com/KrisKennaway/ii-pix.git
synced 2024-11-18 01:06:41 +00:00
Checkpoint
- switch to pyclustering for kmedians - allow choosing the same palette as previous line, with a multiplicative penalty to distance in case it's much better - iterate kmedians multiple times and choose the best, since it's only a local optimum
This commit is contained in:
kris
parent
643e50349e
commit
b363d60754
99
convert.py
99
convert.py
@ -11,6 +11,8 @@ import colour
|
||||
from PIL import Image
|
||||
import numpy as np
|
||||
from pyclustering.cluster.kmedians import kmedians
|
||||
from pyclustering.cluster.kmeans import kmeans
|
||||
from pyclustering.utils.metric import distance_metric, type_metric
|
||||
from pyclustering.cluster.center_initializer import kmeans_plusplus_initializer
|
||||
|
||||
import dither as dither_pyx
|
||||
@ -25,7 +27,7 @@ import screen as screen_py
|
||||
# - support HGR
|
||||
|
||||
def cluster_palette(image: Image):
|
||||
line_to_palette = {}
|
||||
# line_to_palette = {}
|
||||
|
||||
# shuffle_lines = liprint(st(range(200))
|
||||
# random.shuffle(shuffle_lines)
|
||||
@ -40,13 +42,13 @@ def cluster_palette(image: Image):
|
||||
# else:
|
||||
# line_to_palette[line] = np.clip(int(line / (200 / 16)) + 2, 0, 15)
|
||||
|
||||
for line in range(200):
|
||||
if line % 3 == 0:
|
||||
line_to_palette[line] = int(line / (200 / 16))
|
||||
elif line % 3 == 1:
|
||||
line_to_palette[line] = np.clip(int(line / (200 / 16)) + 1, 0, 15)
|
||||
else:
|
||||
line_to_palette[line] = np.clip(int(line / (200 / 16)) + 2, 0, 15)
|
||||
# for line in range(200):
|
||||
# if line % 3 == 0:
|
||||
# line_to_palette[line] = int(line / (200 / 16))
|
||||
# elif line % 3 == 1:
|
||||
# line_to_palette[line] = np.clip(int(line / (200 / 16)) + 1, 0, 15)
|
||||
# else:
|
||||
# line_to_palette[line] = np.clip(int(line / (200 / 16)) + 2, 0, 15)
|
||||
|
||||
colours_rgb = np.asarray(image).reshape((-1, 3))
|
||||
with colour.utilities.suppress_warnings(colour_usage_warnings=True):
|
||||
@ -55,6 +57,7 @@ def cluster_palette(image: Image):
|
||||
palettes_rgb = np.empty((16, 16, 3), dtype=np.float32)
|
||||
palettes_cam = np.empty((16, 16, 3), dtype=np.float32)
|
||||
for palette_idx in range(16):
|
||||
print("Fitting palette %d" % palette_idx)
|
||||
p_lower = max(palette_idx - 2, 0)
|
||||
p_upper = min(palette_idx + 2, 16)
|
||||
palette_pixels = colours_cam[
|
||||
@ -71,12 +74,23 @@ def cluster_palette(image: Image):
|
||||
# 16, palette_pixels, fixed_centroids=fixed_centroids,
|
||||
# tolerance=1e-6)
|
||||
|
||||
initial_centers = kmeans_plusplus_initializer(
|
||||
palette_pixels, 16).initialize()
|
||||
kmedians_instance = kmedians(palette_pixels, initial_centers)
|
||||
kmedians_instance.process()
|
||||
best_wce = 1e9
|
||||
best_medians = None
|
||||
for i in range(500):
|
||||
# print(i)
|
||||
initial_centers = kmeans_plusplus_initializer(
|
||||
palette_pixels, 16).initialize()
|
||||
kmedians_instance = kmedians(
|
||||
palette_pixels, initial_centers, tolerance=0.1, itermax=100,
|
||||
metric=distance_metric(type_metric.MANHATTAN))
|
||||
kmedians_instance.process()
|
||||
if kmedians_instance.get_total_wce() < best_wce:
|
||||
best_wce = kmedians_instance.get_total_wce()
|
||||
print(i, best_wce)
|
||||
best_medians = kmedians_instance
|
||||
print("Best %f" % best_wce)
|
||||
palettes_cam[palette_idx, :, :] = np.array(
|
||||
kmedians_instance.get_medians()).astype(np.float32)
|
||||
best_medians.get_medians()).astype(np.float32)
|
||||
|
||||
# palette_colours = collections.defaultdict(list)
|
||||
# for line in range(200):
|
||||
@ -122,7 +136,7 @@ def cluster_palette(image: Image):
|
||||
# line_pixels, palettes_cam, best_palette)
|
||||
# line_to_palette[line] = best_palette
|
||||
# print(line, line_to_palette[line])
|
||||
return palettes_cam, palettes_rgb, line_to_palette
|
||||
return palettes_cam, palettes_rgb
|
||||
|
||||
|
||||
def main():
|
||||
@ -185,7 +199,7 @@ def main():
|
||||
gamma=args.gamma_correct, srgb_output=True)).astype(
|
||||
np.float32) / 255
|
||||
|
||||
palettes_cam, palettes_rgb, line_to_palette = cluster_palette(rgb)
|
||||
palettes_cam, palettes_rgb = cluster_palette(rgb)
|
||||
# print(palette_rgb)
|
||||
# screen.set_palette(0, (image_py.linear_to_srgb_array(palette_rgb) *
|
||||
# 15).astype(np.uint8))
|
||||
@ -193,36 +207,37 @@ def main():
|
||||
screen.set_palette(i, (np.round(palettes_rgb[i, :, :] * 15)).astype(
|
||||
np.uint8))
|
||||
|
||||
output_4bit, line_to_palette = dither_pyx.dither_shr(
|
||||
rgb, palettes_cam, palettes_rgb, rgb_to_cam16)
|
||||
screen.set_pixels(output_4bit)
|
||||
output_rgb = np.zeros((200, 320, 3), dtype=np.uint8)
|
||||
for i in range(200):
|
||||
screen.line_palette[i] = line_to_palette[i]
|
||||
output_rgb[i, :, :] = (
|
||||
palettes_rgb[line_to_palette[i]][
|
||||
output_4bit[i, :]] * 255).astype(np.uint8)
|
||||
output_srgb = image_py.linear_to_srgb(output_rgb).astype(np.uint8)
|
||||
for penalty in [1,2,3,4,5,6,7,8,9,10,1e9]:
|
||||
output_4bit, line_to_palette = dither_pyx.dither_shr(
|
||||
rgb, palettes_cam, palettes_rgb, rgb_to_cam16, float(penalty))
|
||||
screen.set_pixels(output_4bit)
|
||||
output_rgb = np.zeros((200, 320, 3), dtype=np.uint8)
|
||||
for i in range(200):
|
||||
screen.line_palette[i] = line_to_palette[i]
|
||||
output_rgb[i, :, :] = (
|
||||
palettes_rgb[line_to_palette[i]][
|
||||
output_4bit[i, :]] * 255).astype(np.uint8)
|
||||
output_srgb = image_py.linear_to_srgb(output_rgb).astype(np.uint8)
|
||||
|
||||
# dither = dither_pattern.PATTERNS[args.dither]()
|
||||
# bitmap = dither_pyx.dither_image(
|
||||
# screen, rgb, dither, args.lookahead, args.verbose, rgb_to_cam16)
|
||||
# dither = dither_pattern.PATTERNS[args.dither]()
|
||||
# bitmap = dither_pyx.dither_image(
|
||||
# screen, rgb, dither, args.lookahead, args.verbose, rgb_to_cam16)
|
||||
|
||||
# Show output image by rendering in target palette
|
||||
# output_palette_name = args.show_palette or args.palette
|
||||
# output_palette = palette_py.PALETTES[output_palette_name]()
|
||||
# output_screen = screen_py.DHGRScreen(output_palette)
|
||||
# if output_palette_name == "ntsc":
|
||||
# output_srgb = output_screen.bitmap_to_image_ntsc(bitmap)
|
||||
# else:
|
||||
# output_srgb = image_py.linear_to_srgb(
|
||||
# output_screen.bitmap_to_image_rgb(bitmap)).astype(np.uint8)
|
||||
out_image = image_py.resize(
|
||||
Image.fromarray(output_srgb), screen.X_RES, screen.Y_RES,
|
||||
srgb_output=False) # XXX true
|
||||
# Show output image by rendering in target palette
|
||||
# output_palette_name = args.show_palette or args.palette
|
||||
# output_palette = palette_py.PALETTES[output_palette_name]()
|
||||
# output_screen = screen_py.DHGRScreen(output_palette)
|
||||
# if output_palette_name == "ntsc":
|
||||
# output_srgb = output_screen.bitmap_to_image_ntsc(bitmap)
|
||||
# else:
|
||||
# output_srgb = image_py.linear_to_srgb(
|
||||
# output_screen.bitmap_to_image_rgb(bitmap)).astype(np.uint8)
|
||||
out_image = image_py.resize(
|
||||
Image.fromarray(output_srgb), screen.X_RES, screen.Y_RES,
|
||||
srgb_output=False) # XXX true
|
||||
|
||||
if args.show_output:
|
||||
out_image.show()
|
||||
if args.show_output:
|
||||
out_image.show()
|
||||
|
||||
# Save Double hi-res image
|
||||
outfile = os.path.join(os.path.splitext(args.output)[0] + "-preview.png")
|
||||
|
||||
15
dither.pyx
15
dither.pyx
@ -339,7 +339,7 @@ import colour
|
||||
|
||||
@cython.boundscheck(False)
|
||||
@cython.wraparound(False)
|
||||
def dither_shr(float[:, :, ::1] working_image, float[:, :, ::1] palettes_cam, float[:, :, ::1] palettes_rgb, float[:,::1] rgb_to_cam16ucs):
|
||||
def dither_shr(float[:, :, ::1] working_image, float[:, :, ::1] palettes_cam, float[:, :, ::1] palettes_rgb, float[:,::1] rgb_to_cam16ucs, float penalty):
|
||||
cdef int y, x, idx, best_colour_idx, best_palette
|
||||
cdef float best_distance, distance
|
||||
cdef float[::1] best_colour_rgb, pixel_cam, colour_rgb, colour_cam
|
||||
@ -354,13 +354,13 @@ def dither_shr(float[:, :, ::1] working_image, float[:, :, ::1] palettes_cam, fl
|
||||
cdef int[::1] line_to_palette = np.zeros(200, dtype=np.int32)
|
||||
best_palette = 15
|
||||
for y in range(200):
|
||||
print(y)
|
||||
# print(y)
|
||||
for x in range(320):
|
||||
colour_cam = convert_rgb_to_cam16ucs(
|
||||
rgb_to_cam16ucs, working_image[y,x,0], working_image[y,x,1], working_image[y,x,2])
|
||||
line_cam[x, :] = colour_cam
|
||||
|
||||
best_palette = best_palette_for_line(line_cam, palettes_cam, <int>(y * 16 / 200), best_palette)
|
||||
best_palette = best_palette_for_line(line_cam, palettes_cam, <int>(y * 16 / 200), best_palette, penalty)
|
||||
# print("-->", best_palette)
|
||||
palette_rgb = palettes_rgb[best_palette, :, :]
|
||||
line_to_palette[y] = best_palette
|
||||
@ -509,7 +509,7 @@ def k_means_with_fixed_centroids(
|
||||
|
||||
@cython.boundscheck(False)
|
||||
@cython.wraparound(False)
|
||||
cdef int best_palette_for_line(float [:, ::1] line_cam, float[:, :, ::1] palettes_cam, int base_palette_idx, int last_palette_idx) nogil:
|
||||
cdef int best_palette_for_line(float [:, ::1] line_cam, float[:, :, ::1] palettes_cam, int base_palette_idx, int last_palette_idx, float last_penalty) nogil:
|
||||
cdef int palette_idx, best_palette_idx, palette_entry_idx, pixel_idx
|
||||
cdef float best_total_dist, total_dist, best_pixel_dist, pixel_dist
|
||||
cdef float[:, ::1] palette_cam
|
||||
@ -517,20 +517,23 @@ cdef int best_palette_for_line(float [:, ::1] line_cam, float[:, :, ::1] palette
|
||||
|
||||
best_total_dist = 1e9
|
||||
best_palette_idx = -1
|
||||
cdef float penalty
|
||||
cdef int line_size = line_cam.shape[0]
|
||||
for palette_idx in range(16):
|
||||
palette_cam = palettes_cam[palette_idx, :, :]
|
||||
if palette_idx < (base_palette_idx - 1) or palette_idx > (base_palette_idx + 1):
|
||||
continue
|
||||
if palette_idx == last_palette_idx:
|
||||
continue
|
||||
penalty = last_penalty
|
||||
else:
|
||||
penalty = 1.0
|
||||
total_dist = 0
|
||||
best_pixel_dist = 1e9
|
||||
for pixel_idx in range(line_size):
|
||||
pixel_cam = line_cam[pixel_idx]
|
||||
for palette_entry_idx in range(16):
|
||||
palette_entry = palette_cam[palette_entry_idx, :]
|
||||
pixel_dist = colour_distance_squared(pixel_cam, palette_entry)
|
||||
pixel_dist = colour_distance_squared(pixel_cam, palette_entry) * penalty
|
||||
if pixel_dist < best_pixel_dist:
|
||||
best_pixel_dist = pixel_dist
|
||||
total_dist += best_pixel_dist
|
||||
|
||||
Loading…
Reference in New Issue
Block a user