def split_samples(args):
assets = AssetManager(args.base_dir)
data = np.load(assets.get_preprocess_file_path(args.input_data_name))
imgs, classes, contents = data['imgs'], data['classes'], data['contents']
n_classes = np.unique(classes).size
n_samples = imgs.shape[0]
n_test_samples = int(n_samples * args.test_split)
test_idx = np.random.choice(n_samples, size=n_test_samples, replace=False)
train_idx = ~np.isin(np.arange(n_samples), test_idx)
np.savez(file=assets.get_preprocess_file_path(args.test_data_name),
imgs=imgs[test_idx],
classes=classes[test_idx],
contents=contents[test_idx],
n_classes=n_classes)
np.savez(file=assets.get_preprocess_file_path(args.train_data_name),
imgs=imgs[train_idx],
classes=classes[train_idx],
contents=contents[train_idx],
n_classes=n_classes)
def train_encoders(args): assets = AssetManager(args.base_dir) model_dir = assets.get_model_dir(args.model_name) tensorboard_dir = assets.get_tensorboard_dir(args.model_name) data = np.load(assets.get_preprocess_file_path(args.data_name)) imgs, classes, contents, n_classes = data['imgs'], data['classes'], data['contents'], data['n_classes'] imgs = imgs.astype(np.float32) / 255.0 converter = Converter.load(model_dir, include_encoders=False) glo_backup_dir = os.path.join(model_dir, args.glo_dir) if not os.path.exists(glo_backup_dir): os.mkdir(glo_backup_dir) converter.save(glo_backup_dir) converter.train_encoders( imgs=imgs, classes=classes, batch_size=default_config['train_encoders']['batch_size'], n_epochs=default_config['train_encoders']['n_epochs'], model_dir=model_dir, tensorboard_dir=tensorboard_dir ) converter.save(model_dir)
def train_encoders(args): assets = AssetManager(args.base_dir) model_dir = assets.get_model_dir(args.model_name) tensorboard_dir = assets.get_tensorboard_dir(args.model_name) data = np.load(assets.get_preprocess_file_path(args.data_name)) imgs = data['imgs'].astype(np.float32) / 255.0 backup_dir = os.path.join(model_dir, 'latent') if not os.path.exists(backup_dir): lord = Lord.load(model_dir, include_encoders=False) os.mkdir(backup_dir) lord.save(backup_dir) else: lord = Lord.load(backup_dir, include_encoders=False) lord.train_encoders( imgs=imgs, classes=data['classes'], batch_size=default_config['train_encoders']['batch_size'], n_epochs=default_config['train_encoders']['n_epochs'], model_dir=model_dir, tensorboard_dir=tensorboard_dir ) lord.save(model_dir)
def train(args):
assets = AssetManager(args.base_dir)
model_dir = assets.recreate_model_dir(args.model_name)
tensorboard_dir = assets.recreate_tensorboard_dir(args.model_name)
data = np.load(assets.get_preprocess_file_path(args.data_name))
imgs = data['imgs'].astype(np.float32) / 255.0
config = Config(
img_shape=imgs.shape[1:],
n_imgs=imgs.shape[0],
n_classes=data['n_classes'].item(),
content_dim=default_config['content_dim'],
class_dim=default_config['class_dim'],
content_std=default_config['content_std'],
content_decay=default_config['content_decay'],
n_adain_layers=default_config['n_adain_layers'],
adain_dim=default_config['adain_dim'],
perceptual_loss_layers=default_config['perceptual_loss']['layers'],
perceptual_loss_weights=default_config['perceptual_loss']['weights'],
perceptual_loss_scales=default_config['perceptual_loss']['scales'])
lord = Lord.build(config)
lord.train(imgs=imgs,
classes=data['classes'],
batch_size=default_config['train']['batch_size'],
n_epochs=default_config['train']['n_epochs'],
model_dir=model_dir,
tensorboard_dir=tensorboard_dir)
lord.save(model_dir)
def train(args): assets = AssetManager(args.base_dir) model_dir = assets.recreate_model_dir(args.model_name) tensorboard_dir = assets.recreate_tensorboard_dir(args.model_name) data = np.load(assets.get_preprocess_file_path(args.data_name)) imgs = data['imgs'].astype(np.float32) / 255.0 config = dict( img_shape=imgs.shape[1:], n_imgs=imgs.shape[0], n_classes=data['n_classes'].item(), ) config.update(base_config) lord = Lord(config) lord.train_latent( imgs=imgs, classes=data['classes'], model_dir=model_dir, tensorboard_dir=tensorboard_dir ) lord.save(model_dir, latent=True, amortized=False)
def preprocess(args): assets = AssetManager(args.base_dir) img_dataset = dataset.get_dataset(args.dataset_id, args.dataset_path) imgs, classes, contents = img_dataset.read_images() n_classes = np.unique(classes).size np.savez( file=assets.get_preprocess_file_path(args.data_name), imgs=imgs, classes=classes, contents=contents, n_classes=n_classes )
def main():
if '--paper' in sys.argv:
load_dotenv('env/paper.env')
elif '--live' in sys.argv:
load_dotenv('env/live.env')
asset_client = AssetManager()
assets = asset_client.get_available_assets()
charts = asset_client.get_charts(assets)
charts.sort(key=lambda c: c.last_percent_change or 0)
for chart in charts:
print(str(chart))
def run():
# initialize PyGame
if pygame.mixer:
pygame.mixer.pre_init(22050, -16, 2, 1024)
os.environ['SDL_VIDEO_CENTERED'] = '1'
pygame.init()
pygame.display.set_icon(pygame.image.load('images/icon.png'))
screen = pygame.display.set_mode(config.screen_size)
pygame.display.set_caption("Super Mario")
assets = AssetManager()
state_stack.push(MainMenu(assets))
# timer initialize
game_timer.reset()
accumulator = 0.0
while state_stack.top is not None:
state_stack.top.do_events()
game_timer.update()
# todo: fixed time step, or max time step?
accumulator += game_timer.elapsed
accumulator = min(0.10, accumulator)
while accumulator > config.PHYSICS_DT:
state_stack.update(config.PHYSICS_DT)
accumulator -= config.PHYSICS_DT
state_stack.draw(screen)
pygame.display.flip()
exit(0)
def __init__(self, parent=None):
super(MapEditor, self).__init__(parent)
self.setupUi(self)
self.setWindowIcon(QtGui.QIcon("assets/icon.png"))
print("Working Directory: %s"%(WORKING_DIR))
# Create our asset manager
self.assetManager = AssetManager(WORKING_DIR)
self.assetManager.load_asset("deny.png")
# Create the canvas :D
self.scene = EditorScene(self)
self.graphicsView = GraphicsView(self.scene)
self.graphicsView.setObjectName("graphicsView")
self.horizontalLayout.addWidget(self.graphicsView)
# We can now initialize the scene
self.scene.initialize_scene()
# The tool that is currently active
self.current_tool=None
self.current_status=None
# Init all available tools
self.initialize_tools()
def train(args):
wandb.config.update(default_config)
args_dict = vars(args)
args_dict.pop('func')
wandb.config.update(args_dict)
assets = AssetManager(args.base_dir)
model_dir = assets.recreate_model_dir(args.model_name)
tensorboard_dir = assets.recreate_tensorboard_dir(args.model_name)
data = np.load(assets.get_preprocess_file_path(args.data_name))
imgs, classes, contents, n_classes = data['imgs'], data['classes'], data['contents'], data['n_classes']
imgs = imgs.astype(np.float32) / 255.0
converter = Converter.build(
img_shape=imgs.shape[1:],
n_imgs=imgs.shape[0],
n_classes=n_classes,
content_dim=args.content_dim,
class_dim=args.class_dim,
content_std=args.content_std,
content_decay=args.content_decay,
n_adain_layers=default_config['n_adain_layers'],
adain_enabled=args.adain,
adain_dim=default_config['adain_dim'],
adain_normalize=args.adain_normalize,
perceptual_loss_layers=default_config['perceptual_loss']['layers'],
perceptual_loss_weights=default_config['perceptual_loss']['weights'],
perceptual_loss_scales=default_config['perceptual_loss']['scales'],
)
converter.train(
imgs=imgs,
classes=classes,
batch_size=default_config['train']['batch_size'],
n_epochs=default_config['train']['n_epochs'],
model_dir=model_dir,
tensorboard_dir=tensorboard_dir
)
converter.save(model_dir)
def train_encoders(args):
assets = AssetManager(args.base_dir)
model_dir = assets.get_model_dir(args.model_name)
tensorboard_dir = assets.get_tensorboard_dir(args.model_name)
data = np.load(assets.get_preprocess_file_path(args.data_name))
imgs = data['imgs'].astype(np.float32) / 255.0
lord = Lord()
lord.load(model_dir, latent=True, amortized=False)
lord.train_amortized(imgs=imgs,
classes=data['classes'],
model_dir=model_dir,
tensorboard_dir=tensorboard_dir)
lord.save(model_dir, latent=False, amortized=True)
def split_samples(args):
assets = AssetManager(args.base_dir)
data = np.load(assets.get_preprocess_file_path(args.input_data_name))
imgs, classes, contents = data['imgs'], data['classes'], data['contents']
n_classes = np.unique(classes).size
# NOTE: This is a static split, valid only for CIFAR-10
test_idx = np.arange(50000, 60000)
train_idx = np.arange(50000)
np.savez(
file=assets.get_preprocess_file_path(args.test_data_name),
imgs=imgs[test_idx], classes=classes[test_idx], contents=contents[test_idx], n_classes=n_classes
)
np.savez(
file=assets.get_preprocess_file_path(args.train_data_name),
imgs=imgs[train_idx], classes=classes[train_idx], contents=contents[train_idx], n_classes=n_classes
)
def __init__(self,
subset=None,
base_dir='results',
model_name='minst_10_model',
data_name='minst_10_test',
include_encoders=True):
self.data_name = data_name
assets = AssetManager(base_dir)
data = np.load(assets.get_preprocess_file_path(data_name))
imgs, classes, contents, n_classes = data['imgs'], data[
'classes'], data['contents'], data['n_classes']
imgs = imgs.astype(np.float32) / 255.0
if subset is not None:
self.curr_imgs = imgs[:subset]
self.classes = classes[:subset]
else:
self.curr_imgs = imgs
self.classes = classes
self.onehot_enc = OneHotEncoder()
self.onehot_classes = self.onehot_enc.fit_transform(
self.classes.reshape(-1, 1))
self.n_classes = self.onehot_classes.shape[1]
self.n_images = self.curr_imgs.shape[0]
self.converter = Converter.load(assets.get_model_dir(model_name),
include_encoders=include_encoders)
self.content_codes = self.converter.content_encoder.predict(
self.curr_imgs)
self.class_codes = self.converter.class_encoder.predict(self.curr_imgs)
class_adain_params = self.converter.class_modulation.predict(
self.class_codes)
self.class_adain_params = class_adain_params.reshape(
class_adain_params.shape[0], -1)
self.curr_imgs, self.classes, self.onehot_classes, self.content_codes, self.class_codes, self.class_adain_params = \
shuffle(self.curr_imgs, self.classes, self.onehot_classes, self.content_codes, self.class_codes,
self.class_adain_params)
def split_classes(args):
assets = AssetManager(args.base_dir)
data = np.load(assets.get_preprocess_file_path(args.input_data_name))
imgs, classes, contents = data['imgs'], data['classes'], data['contents']
# Seed
np.random.seed(2020)
n_classes = np.unique(classes).size
test_classes = np.random.choice(n_classes, size=args.num_test_classes, replace=False)
test_idx = np.isin(classes, test_classes)
train_idx = ~np.isin(classes, test_classes)
np.savez(
file=assets.get_preprocess_file_path(args.test_data_name),
imgs=imgs[test_idx], classes=classes[test_idx], contents=contents[test_idx], n_classes=n_classes
)
np.savez(
file=assets.get_preprocess_file_path(args.train_data_name),
imgs=imgs[train_idx], classes=classes[train_idx], contents=contents[train_idx], n_classes=n_classes
)
def __init__(self,
digit,
subset=None,
base_dir='results',
model_name='minst_10_model',
data_name='minst_10_test'):
self.digit = digit
assets = AssetManager(base_dir)
data = np.load(assets.get_preprocess_file_path(data_name))
imgs, classes, contents, n_classes = data['imgs'], data[
'classes'], data['contents'], data['n_classes']
imgs = imgs.astype(np.float32) / 255.0
curr_zero_idx = (classes == digit)
curr_zero_idx[subset:] = False # if have the time use np.csum isntead
self.curr_imgs = imgs[curr_zero_idx, ]
self.n_images = self.curr_imgs.shape[0]
self.converter = Converter.load(assets.get_model_dir(model_name),
include_encoders=True)
self.content_codes = self.converter.content_encoder.predict(
self.curr_imgs)
class_codes = self.converter.class_encoder.predict(self.curr_imgs)
self.class_adain_params = self.converter.class_modulation.predict(
class_codes)
def ligning_plot(model_name, base_dir, adain_enabled):
assets = AssetManager(base_dir)
converter = Converter.load(assets.get_model_dir(model_name),
include_encoders=True)
data_base_dir = 'data/small_norb_lord'
azimuths = []
elevations = []
lightings = []
lt_rts = []
classes = []
img_paths = []
regex = re.compile(r'azimuth(\d+)_elevation(\d+)_lighting(\d+)_(\w+).jpg')
for category in tqdm(os.listdir(data_base_dir)):
for instance in os.listdir(os.path.join(data_base_dir, category)):
for file_name in os.listdir(
os.path.join(data_base_dir, category, instance)):
img_path = os.path.join(data_base_dir, category, instance,
file_name)
azimuth, elevation, lighting, lt_rt = regex.match(
file_name).groups()
class_id = (int(category) * 10) + int(instance)
azimuths.append(int(azimuth))
elevations.append(int(elevation))
lightings.append(int(lighting))
lt_rts.append(lt_rt)
classes.append(class_id)
img_paths.append(img_path)
df = pd.DataFrame({
'azimuth': azimuths,
'elevation': elevations,
'lighting': lightings,
'lt_rt': lt_rts,
'classe': classes,
'img_path': img_paths,
})
df = df.sample(frac=1).reset_index(drop=True)
fxd_content = [df[df.lighting == i]['img_path'].iloc[0] for i in range(6)]
fxd_class = df[df.classe == 0]['img_path'][:10]
l2li = lambda x: [
np.expand_dims(cv2.cvtColor(cv2.resize(plt.imread(i), dsize=(64, 64)),
cv2.COLOR_BGR2GRAY),
axis=2).astype(np.float32) / 255.0 for i in x
]
fxd_content_img = l2li(fxd_content)
fxd_class_img = l2li(fxd_class)
fxd_content_cnt, fxd_content_cls = pred_imgs(converter, fxd_content_img,
adain_enabled)
fxd_class_cnt, fxd_class_cls = pred_imgs(converter, fxd_class_img,
adain_enabled)
plt.rcParams["figure.figsize"] = (20, 20)
blank = np.zeros_like(fxd_content_img[0])
output = [np.concatenate([blank] + list(fxd_content_img), axis=1)]
for i in tqdm(range(10)):
generated_imgs = [
converter.generator.predict(
[fxd_content_cnt[[j]], fxd_class_cls[[i]]])[0]
for j in range(6)
]
converted_imgs = [fxd_class_img[i]] + generated_imgs
output.append(np.concatenate(converted_imgs, axis=1))
merged_img = np.concatenate(output, axis=0)
plt.xlabel('Content')
plt.ylabel('Class')
plt.imshow(np.squeeze(merged_img), cmap='gray')
wandb.log({"Lighting plot": plt})
class MapEditor(QtGui.QMainWindow, Ui_MapEditor):
def __init__(self, parent=None):
super(MapEditor, self).__init__(parent)
self.setupUi(self)
self.setWindowIcon(QtGui.QIcon("assets/icon.png"))
print("Working Directory: %s"%(WORKING_DIR))
# Create our asset manager
self.assetManager = AssetManager(WORKING_DIR)
self.assetManager.load_asset("deny.png")
# Create the canvas :D
self.scene = EditorScene(self)
self.graphicsView = GraphicsView(self.scene)
self.graphicsView.setObjectName("graphicsView")
self.horizontalLayout.addWidget(self.graphicsView)
# We can now initialize the scene
self.scene.initialize_scene()
# The tool that is currently active
self.current_tool=None
self.current_status=None
# Init all available tools
self.initialize_tools()
def initialize_tools(self):
self.toolSetLayout = QtGui.QVBoxLayout(self.scrollAreaWidgetContents)
# Add tool status
self.current_status = QtGui.QLabel("Tool: None", self)
self.toolSetLayout.addWidget(self.current_status)
# Add world building elements
self._add_tool_section("Brushes:",elements.ELEM_BRUSH_CLASSES)
self._add_tool_section("Player:",elements.ELEM_PLAYER_CLASSES)
self._add_tool_section("Building:",elements.ELEM_WORLD_CLASSES)
self._add_tool_section("Enemies:",elements.ELEM_ENEMY_CLASSES)
self._add_tool_section("Power-Ups:",elements.ELEM_POWERUP_CLASSES)
def _add_tool_section(self, title, tools):
self.toolSetLayout.addWidget(QtGui.QLabel(title, self))
i=0
for tool in tools:
# Create a new horizontal layout for every 2 tools
if i == 0:
currentContainer = QtGui.QWidget(self.centralwidget)
currentSetLayout = QtGui.QHBoxLayout(currentContainer)
self.toolSetLayout.addWidget(currentContainer)
currentSetLayout.addWidget(ToolSet(tool, self))
i=(i+1)%2
def set_current_tool(self, tool):
self.current_tool = tool
self.current_status.setText("Tool: %s"%tool.get_tool_name())
def element_clicked(self, element):
if self.current_tool:
self.current_tool.element_clicked(element)
