def main():
graph, sess = load_graph(FLAGS.pre_trained_model_path)
cap = cv2.VideoCapture(0)
cap.set(cv2.CAP_PROP_FRAME_WIDTH, FLAGS.width)
cap.set(cv2.CAP_PROP_FRAME_HEIGHT, FLAGS.height)
mp = _mp.get_context("spawn")
v = mp.Value('i', 0)
lock = mp.Lock()
process = mp.Process(target=mario, args=(v, lock))
process.start()
while True:
key = cv2.waitKey(10)
if key == ord("q"):
break
_, frame = cap.read()
frame = cv2.flip(frame, 1)
frame = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
boxes, scores, classes = detect_hands(frame, graph, sess)
frame = cv2.cvtColor(frame, cv2.COLOR_RGB2BGR)
results = predict(boxes, scores, classes, FLAGS.threshold, FLAGS.width, FLAGS.height)
if len(results) == 1:
x_min, x_max, y_min, y_max, category = results[0]
x = int((x_min + x_max) / 2)
y = int((y_min + y_max) / 2)
cv2.circle(frame, (x, y), 5, RED, -1)
if category == "Open" and x <= FLAGS.width / 3:
action = 7 # Left jump
text = "Jump left"
elif category == "Closed" and x <= FLAGS.width / 3:
action = 6 # Left
text = "Run left"
elif category == "Open" and FLAGS.width / 3 < x <= 2 * FLAGS.width / 3:
action = 5 # Jump
text = "Jump"
elif category == "Closed" and FLAGS.width / 3 < x <= 2 * FLAGS.width / 3:
action = 0 # Do nothing
text = "Stay"
elif category == "Open" and x > 2 * FLAGS.width / 3:
action = 2 # Right jump
text = "Jump right"
elif category == "Closed" and x > 2 * FLAGS.width / 3:
action = 1 # Right
text = "Run right"
else:
action = 0
text = "Stay"
with lock:
v.value = action
cv2.putText(frame, "{}".format(text), (x_min, y_min - 5),
cv2.FONT_HERSHEY_SIMPLEX, 0.5, GREEN, 2)
overlay = frame.copy()
cv2.rectangle(overlay, (0, 0), (int(FLAGS.width / 3), FLAGS.height), ORANGE, -1)
cv2.rectangle(overlay, (int(2 * FLAGS.width / 3), 0), (FLAGS.width, FLAGS.height), ORANGE, -1)
cv2.addWeighted(overlay, FLAGS.alpha, frame, 1 - FLAGS.alpha, 0, frame)
cv2.imshow('Detection', frame)
cap.release()
cv2.destroyAllWindows()
def main():
graph, sess = load_graph(FLAGS.pre_trained_model_path)
cap = cv2.VideoCapture(0)
cap.set(cv2.CAP_PROP_FRAME_WIDTH, FLAGS.width)
cap.set(cv2.CAP_PROP_FRAME_HEIGHT, FLAGS.height)
mp = _mp.get_context("spawn")
v = mp.Value('i', 0)
lock = mp.Lock()
process = mp.Process(target=battle_city, args=(v, lock))
process.start()
x_center = int(FLAGS.width / 2)
y_center = int(FLAGS.height / 2)
radius = int(min(FLAGS.width, FLAGS.height) / 6)
while True:
key = cv2.waitKey(10)
if key == ord("q"):
break
_, frame = cap.read()
frame = cv2.flip(frame, 1)
frame = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
boxes, scores, classes = detect_hands(frame, graph, sess)
frame = cv2.cvtColor(frame, cv2.COLOR_RGB2BGR)
results = predict(boxes, scores, classes, FLAGS.threshold, FLAGS.width, FLAGS.height)
if len(results) == 1:
x_min, x_max, y_min, y_max, category = results[0]
x = int((x_min + x_max) / 2)
y = int((y_min + y_max) / 2)
cv2.circle(frame, (x, y), 5, RED, -1)
if category == "Closed" and np.linalg.norm((x - x_center, y - y_center)) <= radius:
action = 0 # Stay
text = "Stay"
elif category == "Closed" and is_in_triangle((x, y), [(0, 0), (FLAGS.width, 0),
(x_center, y_center)]):
action = 1 # Up
text = "Up"
elif category == "Closed" and is_in_triangle((x, y), [(0, FLAGS.height),
(FLAGS.width, FLAGS.height), (x_center, y_center)]):
action = 2 # Down
text = "Down"
elif category == "Closed" and is_in_triangle((x, y), [(0, 0),
(0, FLAGS.height),
(x_center, y_center)]):
action = 3 # Left
text = "Left"
elif category == "Closed" and is_in_triangle((x, y), [(FLAGS.width, 0), (FLAGS.width, FLAGS.height),
(x_center, y_center)]):
action = 4 # Right
text = "Right"
elif category == "Open":
action = 5 # Fire
text = "Fire"
else:
action = 0
text = "Stay"
with lock:
v.value = action
cv2.putText(frame, "{}".format(text), (x_min, y_min - 5),
cv2.FONT_HERSHEY_SIMPLEX, 0.5, GREEN, 2)
overlay = frame.copy()
cv2.drawContours(overlay, [np.array([(0, 0), (FLAGS.width, 0), (x_center, y_center)])], 0,
CYAN, -1)
cv2.drawContours(overlay, [
np.array([(0, FLAGS.height), (FLAGS.width, FLAGS.height), (x_center, y_center)])], 0,
CYAN, -1)
cv2.drawContours(overlay, [
np.array([(0, 0), (0, FLAGS.height), (x_center, y_center)])], 0,
YELLOW, -1)
cv2.drawContours(overlay, [np.array([(FLAGS.width, 0), (FLAGS.width, FLAGS.height), (x_center, y_center)])], 0,
YELLOW, -1)
cv2.circle(overlay, (x_center, y_center), radius, BLUE, -1)
cv2.addWeighted(overlay, FLAGS.alpha, frame, 1 - FLAGS.alpha, 0, frame)
cv2.imshow('Detection', frame)
cap.release()
cv2.destroyAllWindows()
def main():
graph, sess = load_graph(FLAGS.pre_trained_model_path)
cap = cv2.VideoCapture(0)
cap.set(cv2.CAP_PROP_FRAME_WIDTH, FLAGS.width)
cap.set(cv2.CAP_PROP_FRAME_HEIGHT, FLAGS.height)
mp = _mp.get_context("spawn")
v = mp.Value('i', 0)
lock = mp.Lock()
process = mp.Process(target=mimic, args=(v, lock))
process.start()
x_center = int(FLAGS.width / 2)
y_center = int(FLAGS.height / 2)
radius = int(min(FLAGS.width, FLAGS.height) / 4)
while True:
key = cv2.waitKey(10)
if key == ord("q"):
break
_, frame = cap.read()
frame = cv2.flip(frame, 1)
frame = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
boxes, scores, classes = detect_hands(frame, graph, sess)
results = predict(boxes, scores, classes, FLAGS.threshold, FLAGS.width,
FLAGS.height)
text = "Oof"
top_left_square_corr = np.array([(0, 0), (FLAGS.width // 3, 0),
(FLAGS.width // 3, FLAGS.height // 2),
(0, FLAGS.height // 2)])
bottom_left_square_corr = np.array([(0, FLAGS.height),
(0, FLAGS.height // 2),
(FLAGS.width // 3,
FLAGS.height // 2),
(FLAGS.width // 3, FLAGS.height)])
bottom_right_square_corr = np.array([
(FLAGS.width, FLAGS.height),
(FLAGS.width - FLAGS.width // 3, FLAGS.height),
(FLAGS.width - FLAGS.width // 4, FLAGS.height - FLAGS.height // 3),
(FLAGS.width, FLAGS.height - FLAGS.height // 3)
])
top_right_square_corr = np.array([(FLAGS.width, 0),
(FLAGS.width - FLAGS.width // 4, 0),
(FLAGS.width - FLAGS.width // 4,
FLAGS.height // 3),
(FLAGS.width, FLAGS.height // 3)])
if len(results) == 1:
x_min, x_max, y_min, y_max, category = results[0]
x = int((x_min + x_max) / 2)
y = int((y_min + y_max) / 2)
cv2.circle(frame, (x, y), 10, RED, -1)
if category == "Open" and np.linalg.norm(
(x - x_center, y - y_center)) <= radius:
action = 1
text = action
elif category == "Open" and is_in_square(
(x, y), top_left_square_corr):
action = 3
text = action
elif category == "Open" and is_in_square(
(x, y), top_right_square_corr):
action = 2
text = action
elif category == "Closed" and is_in_square(
(x, y), bottom_right_square_corr):
action = 4
text = action
else:
action = 0
with lock:
v.value = action
cv2.putText(frame, "{}".format(text), (x_min, y_min - 5),
cv2.FONT_HERSHEY_SIMPLEX, 0.5, GREEN, 2)
overlay = frame.copy()
height = FLAGS.height // 3
width = FLAGS.width // 3
cv2.drawContours(overlay, [top_left_square_corr], 0, CYAN, -1)
cv2.drawContours(overlay, [bottom_right_square_corr], 0, RED, -1)
cv2.drawContours(overlay, [bottom_left_square_corr], 0, GREEN, -1)
cv2.drawContours(overlay, [top_right_square_corr], 0, YELLOW, -1)
cv2.circle(overlay, (x_center, y_center), radius, BLUE, -1)
cv2.addWeighted(overlay, FLAGS.alpha, frame, 1 - FLAGS.alpha, 0, frame)
cv2.imshow('Detection', frame)
cap.release()
cv2.destroyAllWindows()
import numpy as np
import cv2
import math
from tkinter import *
import threading
import tensorflow as tf
from src.utils import load_graph, detect_hands, predict
#VISION SETTINGS
def nothing(x):
pass
font = cv2.FONT_HERSHEY_SIMPLEX
graph, sess = load_graph("src/pretrained_model.pb")
def keypress(p):
y = p[1]
x = p[0]
if y >= 100 and y <= 150:
if x >= 330 and x <= 380:
pyautogui.typewrite('A')
elif x >= 380 and x <= 430:
pyautogui.typewrite('B')
elif x >= 430 and x <= 480:
pyautogui.typewrite('C')
elif x >= 480 and x <= 530:
pyautogui.typewrite('D')
elif x >= 530 and x <= 580:
p=args["p"],
model=args["model"],
max_hop=3,
no_simulations=1)
nodes = filter_best_spread_nodes(G, best_nodes, error, filter_function)
nodes = filter_min_degree_nodes(G, args["min_degree"], nodes)
return nodes
if __name__ == "__main__":
args = read_arguments()
# load graph
G = load_graph(args["g_file"], args["g_type"], args["g_nodes"],
args["g_new_edges"], args["g_seed"])
prng = random.Random(args["random_seed"])
# load mutation function
mutation_operator = None
mutators_to_alterate = []
if args["mutators_to_alterate"] is not None:
for m in args["mutators_to_alterate"]:
mutators_to_alterate.append(getattr(mutators, m))
if args["mutation_operator"] == "adaptive_mutations":
mutation_operator = mutators.ea_adaptive_mutators_alteration
else:
mutation_operator = getattr(mutators, args["mutation_operator"])
if mutation_operator == mutators.ea_local_activation_mutation \
spread_function = monte_carlo
spread_function_name = "monte_carlo"
models = ["IC", "WC"]
# output directories
degree_dist_dir = "../experiments/datasets/degree_distributions/"
datasets_dir = "../experiments/datasets/"
ground_truth_dir = "../experiments/ground_truth/"
# compute the ground truth for each seed set size
for k in K:
for dataset_name in dataset_names:
max_trials = 100
G = load_graph(g_type=dataset_name)
prng = random.Random(seed)
if community:
G_sampled1 = sampler.random_walk_sampling_with_fly_back(
G, nodes / 2, 0.15, prng)
G_sampled2 = sampler.random_walk_sampling_with_fly_back(
G, nodes / 2, 0.15, prng)
# compose two graphs together
G_sampled = nx.compose(G_sampled1, G_sampled2)
# while nodes in common keep sampling
while len(G_sampled) < nodes and max_trials > 0:
G_sampled1 = sampler.random_walk_sampling_with_fly_back(
G, nodes / 2, 0.15, prng)
G_sampled2 = sampler.random_walk_sampling_with_fly_back(
G, nodes / 2, 0.15, prng)
# compose two graphs together
def main():
"""Load the graph, create the embeddings, evaluate them with link prediction and save the results."""
args = parse_args()
graph = utils.load_graph(args.weighted, args.directed, args.input)
utils.print_graph_info(graph, "original graph")
graph.remove_nodes_from(list(nx.isolates(graph)))
utils.print_graph_info(graph, "graph without isolates")
edge_splitter_test = EdgeSplitter(graph)
graph_test, X_test_edges, y_test = edge_splitter_test.train_test_split(
p=args.test_percentage, method="global")
edge_splitter_train = EdgeSplitter(graph_test, graph)
graph_train, X_edges, y = edge_splitter_train.train_test_split(
p=args.train_percentage, method="global")
X_train_edges, X_model_selection_edges, y_train, y_model_selection = train_test_split(
X_edges, y, train_size=0.75, test_size=0.25)
logger.info(f'\nEmbedding algorithm started.')
start = time.time()
embedding.create_embedding(args, graph_train)
time_diff = time.time() - start
logger.info(f'\nEmbedding algorithm finished in {time_diff:.2f} seconds.')
embeddings = utils.load_embedding(args.output)
logger.info(f'\nEmbedding evaluation started.')
start = time.time()
results = evaluation.evaluate(args.classifier, embeddings, X_train_edges,
y_train, X_model_selection_edges,
y_model_selection)
time_diff = time.time() - start
logger.info(f'Embedding evaluation finished in {time_diff:.2f} seconds.')
best_result = max(results, key=lambda result: result["roc_auc"])
logger.info(
f"\nBest roc_auc_score on train set using '{best_result['binary_operator'].__name__}': {best_result['roc_auc']}."
)
logger.info(f'\nEmbedding algorithm started.')
start = time.time()
embedding.create_embedding(args, graph_test)
time_diff = time.time() - start
logger.info(f'\nEmbedding algorithm finished in {time_diff:.2f} seconds.')
embedding_test = utils.load_embedding(args.output)
roc_auc, average_precision, accuracy, f1 = evaluation.evaluate_model(
best_result["classifier"], embedding_test,
best_result["binary_operator"], X_test_edges, y_test)
logger.info(
f"Scores on test set using '{best_result['binary_operator'].__name__}'."
)
logger.info(f"roc_auc_score: {roc_auc}")
logger.info(f"average_precision_score: {average_precision}")
logger.info(f"accuracy_score: {accuracy}")
logger.info(f"f1_score on test set using: {f1}\n")
if (args.results):
evaluation.save_evaluation_results(
args.dataset, args.method, args.classifier,
(roc_auc, average_precision, accuracy, f1), args.results)