def __init__(self,model_file = "checkpoints/weights.005-0.105.hdf5"):
self.model = get_DronNet_model(3)
self.model = K.models.load_model(str(Path(model_file)))
#self.Gate_Handle = Gate()
self.set_pose = {'p_x':0,'p_y':0,'p_z':0,'r_x':0,'r_y':0,'r_z':0,\
'p_x_gt':0,'p_y_gt':0,'p_z_gt':0,'r_x_gt':0,'r_y_gt':0,'r_z_gt':0}
try:
#thread.start_new_thread(Gate_Handle.set_gate_pose , (set_pose,) )
_thread.start_new_thread(self.Gate_Handle.start, () )
except:
print ("Error: unable to start thread")
plt.show()
if __name__== '__main__':
pass
# generator = TrainImageGenerator(["..\\data\\2019-03-15-16-06-18\\"], batch_size=8,label_size=6)
# val_generator = ValGenerator("..\\data\\val\\")
#print (generator.__getitem__())
# print (val_generator.__getitem__(1))
nb_epochs = 100
lr = 0.001
steps = 1500
loss_type = "mse"
history = LossHistory()
KTF.set_session(get_session(0.6)) # using 40% of total GPU Memory
output_path = Path(__file__).resolve().parent.joinpath("checkpoints")
model = get_DronNet_model(3)
pre_train_model = 'model.hdf5'
if os.path.exists(pre_train_model):
model = K.models.load_model(pre_train_model)
opt = Adam(lr=lr)
model.compile(optimizer=opt, loss=loss_type, metrics=['mae'])
generator = TrainImageGenerator(["..\\data\\2019-03-21-14-05-35\\"], batch_size=1,label_size=4)
val_generator = ValGenerator("..\\data\\test\\")
output_path.mkdir(parents=True, exist_ok=True)
callbacks = [
LearningRateScheduler(schedule=Schedule(nb_epochs, lr)),
ModelCheckpoint(str(output_path) + "/weights.{epoch:03d}-{val_loss:.3f}.hdf5",
monitor="val_loss",
if __name__ == '__main__':
pass
# generator = TrainImageGenerator(["..\\data\\2019-05-03-18-01-45\\"], batch_size=8,label_size=6)
# val_generator = ValGenerator("..\\data\\val\\")
#print (generator.__getitem__())
# print (val_generator.__getitem__(1))
nb_epochs = 50
lr = 0.0001
steps = 5000
history = LossHistory()
#KTF.set_session(get_session(0.6)) # using 40% of total GPU Memory
output_path = Path(__file__).resolve().parent.joinpath("checkpoints")
model = get_DronNet_model(3, lr)
pre_train_model = 'model.hdf5'
if os.path.exists(pre_train_model):
model = K.models.load_model(pre_train_model)
generator = TrainImageGenerator(
["../data/2019-06-16-17-38-29/", "../data/2019-06-26-17-34-32/"],
batch_size=1,
label_size=4)
val_generator = ValGenerator("../data/test-real/")
output_path.mkdir(parents=True, exist_ok=True)
callbacks = [
LearningRateScheduler(schedule=Schedule(nb_epochs, lr)),
ModelCheckpoint(str(output_path) +
"/weights.{epoch:03d}-{val_loss:.3f}.hdf5",