def setUp(self) -> None:
current_folder = os.path.dirname(os.path.abspath(__file__))
dataset_folder = os.path.join(os.path.dirname(current_folder),
"datasets", "kitti")
data_module_factory = KittiDataModuleFactory(range(0, 301, 1),
directory=dataset_folder)
self._data_module = data_module_factory.make_dataset_manager(
final_image_size=(128, 384),
transform_manager_parameters={"filters": True},
batch_size=1,
num_workers=WORKERS_COUNT,
split=(0.8, 0.1, 0.1))
self._data_module = DataModuleMock(self._data_module)
pose_net = PoseNetResNet()
depth_net = DepthNetResNet()
criterion = UnsupervisedCriterion(
self._data_module.get_cameras_calibration(), 1, 1)
params = AttributeDict(
lr=1e-3,
beta1=0.99,
beta2=0.9,
scale_lr=1e-3,
initial_log_scale=0.,
initial_log_min_depth=0.,
initial_log_pose_scale=0.,
)
self._model = ScaledUnsupervisedDepthModel(params, pose_net, depth_net,
criterion).cuda()
def setUp(self) -> None:
current_folder = os.path.dirname(os.path.abspath(__file__))
dataset_folder = os.path.join(os.path.dirname(current_folder),
"datasets", "kitti")
data_module_factory = KittiDataModuleFactory(range(0, 301, 1),
directory=dataset_folder)
self._data_module = data_module_factory.make_dataset_manager(
final_image_size=(128, 384),
transform_manager_parameters={"filters": True},
batch_size=20,
num_workers=WORKERS_COUNT,
split=(0.8, 0.1, 0.1))
self._lengths = (240, 30, 30)
def setUp(self) -> None:
current_folder = os.path.dirname(os.path.abspath(__file__))
dataset_folder = os.path.join(os.path.dirname(current_folder),
"datasets", "kitti")
data_module_factory = KittiDataModuleFactory(range(0, 301, 1),
directory=dataset_folder)
self._data_module = data_module_factory.make_dataset_manager(
final_image_size=(128, 384),
transform_manager_parameters={"filters": True},
batch_size=1,
num_workers=WORKERS_COUNT,
split=(0.8, 0.1, 0.1))
self._data_module = DataModuleMock(self._data_module)
pose_net = PoseNetResNet()
depth_net = DepthNetResNet()
criterion = UnsupervisedCriterion(
self._data_module.get_cameras_calibration(), 1, 1)
result_visualizer = ResultVisualizer(
cameras_calibration=self._data_module.get_cameras_calibration())
params = AttributeDict(lr=1e-3, beta1=0.99, beta2=0.9)
self._model = UnsupervisedDepthModel(
params,
pose_net,
depth_net,
criterion,
result_visualizer=result_visualizer).cuda()
self._tb_logger = TensorBoardLogger('logs/')
self._second_tb_logger = TensorBoardLogger('logs1/')
self._double_tb_logger = LoggerCollection(
[self._tb_logger, self._second_tb_logger])
os.environ[
"MLFLOW_S3_ENDPOINT_URL"] = "http://ec2-3-134-104-174.us-east-2.compute.amazonaws.com:9000"
os.environ["AWS_ACCESS_KEY_ID"] = "depth"
os.environ["AWS_SECRET_ACCESS_KEY"] = "depth123"
self._mlflow_logger = MLFlowLogger(
experiment_name="test",
tracking_uri=
"http://ec2-3-134-104-174.us-east-2.compute.amazonaws.com:5001")
def setUp(self) -> None:
params = AttributeDict(image_size=(128, 384),
batch_size=1,
transform_filters=True,
split=(0.8, 0.1, 0.1),
num_workers=WORKERS_COUNT,
detach=True,
levels=(1, ),
inner_lambda_s=0.15,
lr=1e-3,
beta1=0.99,
beta2=0.9)
current_folder = os.path.dirname(os.path.abspath(__file__))
dataset_folder = os.path.join(os.path.dirname(current_folder),
"datasets", "kitti")
data_module_factory = KittiDataModuleFactory(range(0, 301, 1),
directory=dataset_folder)
self._data_module = data_module_factory.make_data_module_from_params(
params)
self._data_module = DataModuleMock(self._data_module)
self._model = MultiUnsupervisedDepthModelFactory().make_model(
params, self._data_module.get_cameras_calibration())
TensorBoardLogger("lightning_logs"),
MLFlowLogger(experiment_name=arguments.experiment_name,
tracking_uri=mlflow_url)
])
# Make trainer
trainer = pl.Trainer.from_argparse_args(arguments, logger=logger)
# Make data model factory
if arguments.frames is not None:
frames = arguments.frames.split(",")
frames = [int(x) for x in frames]
frames = range(*frames)
else:
frames = None
data_model_factory = KittiDataModuleFactory(frames, arguments.sequences,
arguments.dataset)
# Load parameters
params = load_hparams_from_yaml(arguments.config)
params = AttributeDict(params)
print("Load model from params \n" + str(params))
data_model = data_model_factory.make_data_module_from_params(params)
model = MultiUnsupervisedDepthModelFactory().make_model(
params, data_model.get_cameras_calibration())
if arguments.load_model:
print("Load checkpoint")
load_undeepvo_checkpoint(model, arguments.model_checkpoint)
print("Start training")
trainer.fit(model, data_model)