def display(self, style):
"""Display mode.
Args:
style (str): Name of the style.
"""
self.stl = Style(style, mc_version='1.15.2')
with open(self.stl.info['schem_pth'], 'rb') as schem_file:
o_tlmp = Schematic.load(schem_file, self.stl.info['mc_version'])
g_tlmp = self.stl.generate(shape=(64, 16, 64))
o_w, o_h, o_l = o_tlmp.shape
g_w, g_h, g_l = g_tlmp.shape
spacing = 16
combined = Schematic(shape=(
o_w + g_w + spacing,
max(o_h, g_h),
max(o_l, g_l),
),
version=self.stl.info['mc_version'])
combined[:o_w, :o_h, :o_l] = o_tlmp
combined[o_w + spacing:, :g_h, :g_l] = g_tlmp
app = App()
app.tlmp = combined
app.start_gui()
def train(self, style):
"""Training mode.
This subcommand has no additional parameters.
Args:
style (str): Name of the style.
"""
self.stl = Style(style, mc_version='1.15.2')
self.stl.train(vae=True, batch_size=64, epochs=300)
def test_load_save(self):
# Creating stlye
stl1 = Style('test_style',
mc_version='1.15.2',
icon_pth=join(dirname(__file__), 'icon_test.jpeg'))
# Saving style
stl1.save()
# Loading
stl2 = Style('test_style')
self.assertEqual(stl1.name, stl2.name)
self.assertEqual(stl1.info['mc_version'], stl2.info['mc_version'])
def test_init(self):
stl = Style('test_style',
mc_version='1.15.2',
icon_pth=join(dirname(__file__), 'icon_test.jpeg'))
with self.assertRaises(IconFileMissing):
stl = Style('test_style',
mc_version='1.15.2',
icon_pth='this_img_does_not_exists.jpeg')
with self.assertRaises(InvalidStyleName):
stl = Style('test style with a space',
mc_version='1.15.2',
icon_pth=join(dirname(__file__), 'icon_test.jpeg'))
def display(self, style):
"""Display mode.
This subcommand displays a plot of the latent space.
Args:
style (str): Name of the style.
"""
self.stl = Style(style, mc_version='1.15.2')
vae = self.stl.models.vae
vae_data = Tile.vectorize_all(self.stl.info['mc_version'])
encodings = vae.encoder.predict(vae_data)[0]
tiles = [
Tile('minecraft:quartz_stairs[half=bottom]', version='1.15.2'),
Tile('minecraft:birch_stairs[half=bottom]', version='1.15.2'),
Tile('minecraft:brick_stairs[half=bottom]', version='1.15.2'),
Tile('minecraft:bricks', version='1.15.2'),
Tile('minecraft:nether_bricks', version='1.15.2'),
Tile('minecraft:white_carpet', version='1.15.2'),
Tile('minecraft:snow[layers=1]', version='1.15.2')
]
vae_data = vectorize(tiles, pad_to=vae.input_dim)
encodings_subset = vae.encoder.predict(vae_data)[0]
import matplotlib.pyplot as plt
fig = plt.figure()
ax = fig.add_subplot(111)
ax.scatter(encodings[:, 0],
encodings[:, 1],
c=[[.9, .9, .9]],
marker='x')
ax.scatter(encodings_subset[:, 0],
encodings_subset[:, 1],
color='r',
marker='x')
for idx, t in enumerate(tiles):
ax.annotate(t.name,
(encodings_subset[idx, 0], encodings_subset[idx, 1]))
ax.set_title('Minecraft tile-ok 2D látenstere')
plt.show()
def train(self, style, schem, batch_size=16, epochs=100):
"""Training mode.
This subcommand optimizes a single tensor for the loss.
Args:
style (str): Name of the style.
schem (str): Path to a schematic file.
batch_size (int): Batch size.
epochs (int): Epochs.
"""
self.stl = Style(style, mc_version='1.15.2')
self.stl.info['schem_pth'] = schem
vae = self.stl.models.vae
self.stl.models.generator = DummyGeneratorNetwork(256,
vae.latent_dim,
shape=(32, 16, 32))
self.stl.models.generator.build()
self.stl.train(generator=True,
schem_pth=schem,
batch_size=batch_size,
epochs=epochs)
class LossTest(CommandlineInterface):
"""Testing feature-loss.
This is a simple test program for the feature loss implemented in
creAI/ml/losses/feature_loss.py
"""
def __init__(self):
super(LossTest, self).__init__()
@command
def train(self, style, schem, batch_size=16, epochs=100):
"""Training mode.
This subcommand optimizes a single tensor for the loss.
Args:
style (str): Name of the style.
schem (str): Path to a schematic file.
batch_size (int): Batch size.
epochs (int): Epochs.
"""
self.stl = Style(style, mc_version='1.15.2')
self.stl.info['schem_pth'] = schem
vae = self.stl.models.vae
self.stl.models.generator = DummyGeneratorNetwork(256,
vae.latent_dim,
shape=(32, 16, 32))
self.stl.models.generator.build()
self.stl.train(generator=True,
schem_pth=schem,
batch_size=batch_size,
epochs=epochs)
@command
def display(self, style):
"""Display mode.
Args:
style (str): Name of the style.
"""
self.stl = Style(style, mc_version='1.15.2')
with open(self.stl.info['schem_pth'], 'rb') as schem_file:
o_tlmp = Schematic.load(schem_file, self.stl.info['mc_version'])
g_tlmp = self.stl.generate(shape=(64, 16, 64))
o_w, o_h, o_l = o_tlmp.shape
g_w, g_h, g_l = g_tlmp.shape
spacing = 16
combined = Schematic(shape=(
o_w + g_w + spacing,
max(o_h, g_h),
max(o_l, g_l),
),
version=self.stl.info['mc_version'])
combined[:o_w, :o_h, :o_l] = o_tlmp
combined[o_w + spacing:, :g_h, :g_l] = g_tlmp
app = App()
app.tlmp = combined
app.start_gui()
class VaeTest(CommandlineInterface):
"""Testing VAE.
This is a simple test program for the VAE implemented in
creAI/ml/models/vae.py
"""
def __init__(self):
super(VaeTest, self).__init__()
@command
def train(self, style):
"""Training mode.
This subcommand has no additional parameters.
Args:
style (str): Name of the style.
"""
self.stl = Style(style, mc_version='1.15.2')
self.stl.train(vae=True, batch_size=64, epochs=300)
@command
def display(self, style):
"""Display mode.
This subcommand displays a plot of the latent space.
Args:
style (str): Name of the style.
"""
self.stl = Style(style, mc_version='1.15.2')
vae = self.stl.models.vae
vae_data = Tile.vectorize_all(self.stl.info['mc_version'])
encodings = vae.encoder.predict(vae_data)[0]
tiles = [
Tile('minecraft:quartz_stairs[half=bottom]', version='1.15.2'),
Tile('minecraft:birch_stairs[half=bottom]', version='1.15.2'),
Tile('minecraft:brick_stairs[half=bottom]', version='1.15.2'),
Tile('minecraft:bricks', version='1.15.2'),
Tile('minecraft:nether_bricks', version='1.15.2'),
Tile('minecraft:white_carpet', version='1.15.2'),
Tile('minecraft:snow[layers=1]', version='1.15.2')
]
vae_data = vectorize(tiles, pad_to=vae.input_dim)
encodings_subset = vae.encoder.predict(vae_data)[0]
import matplotlib.pyplot as plt
fig = plt.figure()
ax = fig.add_subplot(111)
ax.scatter(encodings[:, 0],
encodings[:, 1],
c=[[.9, .9, .9]],
marker='x')
ax.scatter(encodings_subset[:, 0],
encodings_subset[:, 1],
color='r',
marker='x')
for idx, t in enumerate(tiles):
ax.annotate(t.name,
(encodings_subset[idx, 0], encodings_subset[idx, 1]))
ax.set_title('Minecraft tile-ok 2D látenstere')
plt.show()