frame=[320, 180],
throttle=True,
brake=True,
steering=True,
speed=True,
acceleration=True,
yaw=True,
yawRate=True,
isCollide=True,
location=True,
drivingModeMsg=True
) # lidar=[3, True, 100.0, 1000, 60.0, 300.0, 20, 85.0, 115.0], , vehicles=True, peds=True
# Automatic driving scenario
scenario = Scenario(weather='EXTRASUNNY',vehicle='blista', time=[12,0], drivingMode=[-2, 3, 25.0, 1.0, 1.0],
route=[ \
-1989.000000, -468.250000, 10.562500,
1171.351563, -1925.791748, 36.220097
])
client.sendMessage(Start(scenario=scenario,
dataset=dataset)) # Start request
count = 0
tripNum = 0
old_location = [0, 0, 0]
while True: # Main loop
try:
# Message recieved as a Python dictionary
message = client.recvMessage()
if (count % 500) == 0:
print(count)
dataset = Dataset(rate=30,
frame=[320, 160],
throttle=True,
brake=True,
steering=True,
vehicles=True,
peds=True,
reward=[15.0, 0.0],
direction=None,
speed=True,
yawRate=True,
location=True,
time=True)
# Send the Start request to DeepGTAV.
scenario = Scenario(
drivingMode=[786603, 15.0]
) # Driving style is set to normal, with a speed of 15.0 mph. All other scenario options are random.
client.sendMessage(Start(dataset=dataset, scenario=scenario))
# Start listening for messages coming from DeepGTAV. We do it for 80 hours
stoptime = time.time() + 80 * 3600
while time.time() < stoptime:
try:
# We receive a message as a Python dictionary
message = client.recvMessage()
# The frame is a numpy array and can be displayed using OpenCV or similar
# image = frame2numpy(message['frame'], (320,160))
# cv2.imshow('img',image)
# cv2.waitKey(-1)
except KeyboardInterrupt:
vehicles=args.vehicles,
trafficSigns=args.trafficSigns,
peds=args.peds,
reward=args.reward,
speed=args.speed,
yawRate=args.yawRate,
location=args.if_location,
time=args.dataset_time,
roadinfo=args.roadinfo,
direction=args.des
)
if args.auto_drive:
scenario = Scenario(
drivingMode=args.driving_mode,
vehicle=args.vehicle,
weather=weather,
time=args.time,
location=args.location)
else:
scenario = Scenario(
vehicle=args.vehicle,
weather=weather,
time=args.time,
location=args.location)
client.sendMessage(Start(dataset=dataset, scenario=scenario))
time.sleep(5) # wait for the scene to be ready
# Setup multi-threading for receiving messages
queue = Queue()
manager = Manager()
infosaver = save_game_info(img_dir=info_full_path)
'''
if input("Continue?") == "y": # Wait until you load GTA V to continue, else can't connect to DeepGTAV
print("Conintuing...")
'''
# Loads into a consistent starting setting
print("Loading Scenario...")
client = Client(ip='localhost', port=8000) # Default interface
dataset = Dataset(rate=60,
frame=[800, 600],
throttle=True,
brake=True,
steering=True,
location=True,
drivingMode=True)
scenario = Scenario(
weathers='EXTRASUNNY', vehicle='blista', times=[12, 0], drivingMode=-1
) #, location=[-2573.13916015625, 3292.256103515625, 13.241103172302246])
client.sendMessage(Start(scenario=scenario))
count = 0
print("Starting Loop...")
while True:
try:
lasttime = time.time()
# Collect and preprocess image
message = client.recvMessage()
image = message['frame']
image = grab_screen(region=(0, 0, 800, 600))
image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
# image = frame2numpy(image, (800, 600))
default='localhost',
help='The IP where DeepGTAV is running')
parser.add_argument('-p',
'--port',
default=8000,
help='The port where DeepGTAV is running')
args = parser.parse_args()
# Creates a new connection to DeepGTAV using the specified ip and port.
# If desired, a dataset path and compression level can be set to store in memory all the data received in a gziped pickle file.
# We don't want to save a dataset in this case
client = Client(ip=args.host, port=args.port)
# We set the scenario to be in manual driving, and everything else random (time, weather and location).
# See deepgtav/messages.py to see what options are supported
scenario = Scenario(drivingMode=-1) #manual driving
# Send the Start request to DeepGTAV. Dataset is set as default, we only receive frames at 10Hz (320, 160)
client.sendMessage(Start(scenario=scenario))
# Dummy agent
model = Model()
# Start listening for messages coming from DeepGTAV. We do it for 80 hours
stoptime = time.time() + 80 * 3600
while time.time() < stoptime:
try:
# We receive a message as a Python dictionary
message = client.recvMessage()
# The frame is a numpy array that can we pass through a CNN for example
'--port',
default=8000,
help='The port where DeepGTAV is running')
args = parser.parse_args()
# Creates a new connection to DeepGTAV using the specified ip and port.
# If desired, a dataset path and compression level can be set to store in memory all the data received in a gziped pickle file.
# We don't want to save a dataset in this case
client = Client(ip=args.host, port=args.port)
# We set the scenario to be in manual driving, and everything else random (time, weather and location).
# See deepgtav/messages.py to see what options are supported
#scenario = Scenario(drivingMode=-1)
scenario = Scenario(weather='EXTRASUNNY',
vehicle='Vader',
time=[12, 0],
drivingMode=[786603, 25.0],
location=[201.8704, -51.1309, 0])
# Send the Start request to DeepGTAV. Dataset is set as default, we only receive frames at 10Hz (320, 160)
client.sendMessage(Start(scenario=scenario))
# Dummy agent
model = Model()
# Start listening for messages coming from DeepGTAV. We do it for 80 hours
stoptime = time.time() + 80 * 3600
while time.time() < stoptime:
try:
# We receive a message as a Python dictionary
message = client.recvMessage()
pass
# Creates a new connection to DeepGTAV using the specified ip and port
client = Client(ip=args.host,
port=args.port,
datasetPath=args.dataset_path,
compressionLevel=9)
# Dataset options
dataset = Dataset(rate=60,
frame=[1920, 1080],
vehicles=True,
location=True)
# Automatic driving scenario
scenario = Scenario(
weather='EXTRASUNNY',
vehicle='packer',
time=[9, 0],
drivingMode=[786603, 20.0]
) #, location=[-661.9974975585938, -1932.245849609375, 27.170656204223633])
client.sendMessage(Start(scenario=scenario,
dataset=dataset)) # Start request
count = 0
old_location = [0, 0, 0]
# Main loop stops when dataset.size < N GB
while os.path.getsize(dataset_path) < (100e+9):
try:
# Message recieved as a Python dictionary
message = client.recvMessage()
# Checks if car is stuck, resets position if it is
if (count % 250) == 0:
#Boolean to choose if lidar
lidar_bool = true;
class Model:
def run(self,frame):
return [0.0, 0.0, 0.0] # throttle, brake, steering
if __name__ == '__main__':
parser = argparse.ArgumentParser(description=None)
parser.add_argument('-l', '--host', default='localhost', help='The IP where DeepGTAV is running')
parser.add_argument('-p', '--port', default=8000, help='The port where DeepGTAV is running')
args = parser.parse_args()
client = Client(ip=args.host, port=args.port)
scenario = Scenario(weather=scen_weather,vehicle=scen_vehicle,time=[12,0],drivingMode=[scen_drivingmode,1.0],location=[-619.2719, -179.77854, 0])
client.sendMessage(Start(scenario=scenario))
model = Model()
stoptime = time.time() + 80*3600
count = 0
lidarcfg = "LiDAR GTA V Configuration File\r\nHorizontal_FOV_Min = 0.0\r\nHorizontal_FOV_Max = 360.0\r\nVertical_FOV_Min = -20.0\r\nVertical_FOV_Max = 10.0\r\nHorizontal_Step = 5\r\nVertical_Step = .25\r\nRange = 50\r\nFilename = LiDAR_PointCloud"
while time.time() < stoptime:
try:
message = client.recvMessage()
image = frame2numpy(message['frame'], (320,160))
#commands = model.run(image)
def __init_scenairo(self):
self.__scenario = Scenario(drivingMode=self.__driving_mode, vehicle=self.__driving_vehicle,
time=self.__starting_time, weather=self.__starting_weather, location=self.__starting_location)
frame=args.frame_resolution,
throttle=args.throttle,
brake=args.brake,
steering=args.steering,
vehicles=args.vehicles,
trafficSigns=args.trafficSigns,
peds=args.peds,
reward=args.reward,
speed=args.speed,
yawRate=args.yawRate,
location=args.if_location,
time=args.dataset_time,
roadinfo=args.roadinfo,
direction=args.des)
scenario = Scenario(vehicle=args.vehicle,
weather=weather,
time=args.time,
location=args.location)
client.sendMessage(Start(dataset=dataset, scenario=scenario))
time.sleep(5) # wait for the scene to be ready
# Setup multi-threading for receiving messages
queue = Queue(maxsize=1)
manager = Manager()
c = BufferClient(('localhost', 8766))
capture_gta_to_queue_only_final(c, queue)
while True:
imgtime, img = queue.get()
imgtime = int(time)
speed, angle = model(Variable(torch.Tensor(img)))
throttle, brake, steering = pid(speed, angle)
client.sendMessage(
def main():
global client, scenario
client = Client(ip='localhost', port=8000) # Default interface
scenario = Scenario(
weather='EXTRASUNNY',
vehicle='blista',
time=[12, 0],
drivingMode=-1,
location=[-2583.6708984375, 3501.88232421875, 12.7711820602417])
client.sendMessage(Start(scenario=scenario, dataset=dataset))
print("load deepGTAV successfully! \nbegin")
# load yolo v3
classes = yolo_util.read_coco_names('./files/coco/coco.names')
num_classes = len(classes)
input_tensor, output_tensors = yolo_util.read_pb_return_tensors(
tf.get_default_graph(), "./files/trained_models/yolov3.pb",
["Placeholder:0", "concat_9:0", "mul_6:0"])
print("load yolo v3 successfully!")
with tf.Session() as sess:
model = load_model("files/trained_models/main_model.h5")
print("load main_model successfully!")
while True:
fo = open(config_position, "r") # 配置1
txt = fo.read()
fo.close()
if txt == '0':
set_gamepad(-1, -1, 0)
time.sleep(0.7)
print('=====================end=====================')
exit(0)
elif txt == '1':
message = client.recvMessage()
frame = frame2numpy(message['frame'], (CAP_IMG_W, CAP_IMG_H))
image_obj = Image.fromarray(frame)
speed = message['speed']
boxes, scores = sess.run(output_tensors,
feed_dict={
input_tensor:
np.expand_dims(
yolo_img_process(frame),
axis=0)
})
boxes, scores, labels = yolo_util.cpu_nms(boxes,
scores,
num_classes,
score_thresh=0.4,
iou_thresh=0.1)
image, warning = yolo_util.draw_boxes(image_obj,
boxes,
scores,
labels,
classes,
(IMAGE_H, IMAGE_W),
show=False)
control, throttle, breakk = drive(model=model,
image=frame,
speed=speed,
warning=warning)
print(warning)
set_gamepad(control, throttle, breakk)