def init():
window = pyglet.window.Window(width=800,height=600, resizable=True, visible=False)
window.clear()
window.resize = resize
window.set_visible(True)
window.resize(window.width, window.height)
current_dir = os.path.abspath(os.path.dirname(__file__))
load_files_from_dir = 'data'
data_dir = os.path.normpath(os.path.join(current_dir, '..', load_files_from_dir))
game_data = {}
scanDirectory(data_dir, game_data)
loadImages(game_data['data']['agents']['Monster01']['animations'])
loadImages(game_data['data']['map']['elements']['House01'])
game_data["window"] = window
state = GameState(game_data)
game_data["game"] = state
map = Map(32, 32, game_data, 32)
spawner = Spawn(game_data)
map.populate()
render = Render(game_data)
print game_data
def fitModel(epochs, batch_size):
print("\n>>>TRAINING MODEL<<<")
print("\n\tLoading images...")
trainX, trainY = loadImages("processed_images/TRAIN")
print("\tDONE! Images are loaded.")
encoder = LabelEncoder()
encoder.fit(trainY)
encoded_y_train = encoder.transform(trainY)
trainY = np_utils.to_categorical(encoded_y_train)
model = neural_network_model()
model.fit(trainX, trainY, epochs=epochs, batch_size=batch_size)
model.save_weights('network.h5')
return model
def predict(model):
print("\n>>>PREDICTING ON TEST DATA<<<")
# testSimpleX,testSimpleY = loadImages("images/TEST_SIMPLE");
print("\n\tLoading images...")
testX, testY = loadImages("processed_images/TEST")
print("\tDONE! Images are loaded.")
encoder = LabelEncoder()
encoder.fit(testY)
encoded_y_test = encoder.transform(testY)
testY = np_utils.to_categorical(encoded_y_test)
prediction_matching = np.rint(model.predict(testX))
print(accuracy_score(testY, prediction_matching))
def main():
model = None
while True:
try:
print("\n1.Process images ")
print("2.Fit new model")
print("3.Load existing model")
print("4.Predict test data")
select = int(input("Please enter a number: "))
if select == 1:
print("\n\tProccesing train images...")
loadImages("images/TRAIN", True)
print("\tDONE! Train images are processed.")
print("\n\tProccesing test images...")
loadImages("images/TEST", True)
print("\tDONE! Test images are loaded.")
elif select == 2:
model = fitModel(epochs, batch_size)
elif select == 3:
try:
model = loadModel("network.h5")
except OSError:
print(
"\n!!! Model doesn't exist. You need first to fit model."
)
elif select == 4:
if model is not None:
predict(model)
else:
print("\n!!! You must first fit or load model")
except ValueError:
print("\n!!! That was no valid number. Try again...")
def train(model):
import data
# Prepare input
x_train, y_train, x_test, y_test = data.loadImages("input_iconsets", -1,
args.split)
hintbot.fit(x_train,
y_train,
nb_epoch=args.epochs,
batch_size=256,
shuffle=True,
validation_data=(x_test, y_test))
# Save weights
if (save_weights_filepath):
print("saving weights")
hintbot.save_weights(save_weights_filepath, overwrite=True)
def main():
data.trace("started main")
pygame.init()
pygame.font.init()
pygame.display.set_caption("The Mimic Slime and the Forbidden Dungeon")
g.simpleFont = pygame.font.Font(data.filepath("vera.ttf"), 8)
data.trace("reading "+str(len(sys.argv)-1)+" arguments")
data.trace("creating screen")
g.screen = pygame.display.set_mode(g.screen_size)
data.trace("loading images")
if not data.loadImages():
return
for i in range((g.images["base.png"].get_size()[1])/32):
for j in range((g.images["base.png"].get_size()[0])/32):
tempSurface = g.simpleFont.render(str(j)+", "+str(i), False,
(255,255,255))
g.images["base.png"].blit(tempSurface, (j*32, i*32))
pygame.image.save(g.images["base.png"], "base_with_xy.png")
data.trace("complete!")
def main():
data.trace("started main")
pygame.init()
pygame.font.init()
pygame.display.set_caption("The Mimic Slime and the Forbidden Dungeon")
g.simpleFont = pygame.font.Font(data.filepath("vera.ttf"), 8)
data.trace("reading " + str(len(sys.argv) - 1) + " arguments")
data.trace("creating screen")
g.screen = pygame.display.set_mode(g.screen_size)
data.trace("loading images")
if not data.loadImages():
return
for i in range((g.images["base.png"].get_size()[1]) / 32):
for j in range((g.images["base.png"].get_size()[0]) / 32):
tempSurface = g.simpleFont.render(
str(j) + ", " + str(i), False, (255, 255, 255))
g.images["base.png"].blit(tempSurface, (j * 32, i * 32))
pygame.image.save(g.images["base.png"], "base_with_xy.png")
data.trace("complete!")
import matplotlib.pyplot as plt
from skimage.feature import hog
from tqdm import tqdm
import numpy as np
import cv2
import glob
import json
import pickle
import time
from sklearn.preprocessing import StandardScaler
from data import loadImages
from hog import *
from scipy.ndimage.measurements import label
cars_imgs, noncars_imgs = loadImages()
car_features = []
noncar_features = []
# Define a function you will pass an image
# and the list of windows to be searched (output of slide_windows())
def search_windows(img, windows, clf, scaler):
#1) Create an empty list to receive positive detection windows
on_windows = []
#2) Iterate over all windows in the list
for window in windows:
#3) Extract the test window from original image
test_img = cv2.resize(
img[window[0][1]:window[1][1], window[0][0]:window[1][0]],
(64, 64))
